Mark Gales

Adian Liusie, Potsawee Manakul, Mark J. F. Gales

Current developments in large language models (LLMs) have enabled impressive zero-shot capabilities across various natural language tasks. An interesting application of these systems is in the automated assessment of natural language generation (NLG), a highly challenging area with great practical benefit. In this paper, we explore two options for exploiting the emergent abilities of LLMs for zero-shot NLG assessment: absolute score prediction, and comparative assessment which uses relative comparisons between pairs of candidates. Though comparative assessment has not been extensively studied in NLG assessment, we note that humans often find it more intuitive to compare two options rather than scoring each one independently. This work examines comparative assessment from multiple perspectives: performance compared to absolute grading; positional biases in the prompt; and efficient ranking in terms of the number of comparisons. We illustrate that LLM comparative assessment is a simple, general and effective approach for NLG assessment. For moderate-sized open-source LLMs, such as FlanT5 and Llama2-chat, comparative assessment is superior to prompt scoring, and in many cases can achieve performance competitive with state-of-the-art methods. Additionally, we demonstrate that LLMs often exhibit strong positional biases when making pairwise comparisons, and we propose debiasing methods that can further improve performance.

Nataliia Molchanova, Vatsal Raina, Andrey Malinin et al.

This paper focuses on the uncertainty estimation for white matter lesions (WML) segmentation in magnetic resonance imaging (MRI). On one side, voxel-scale segmentation errors cause the erroneous delineation of the lesions; on the other side, lesion-scale detection errors lead to wrong lesion counts. Both of these factors are clinically relevant for the assessment of multiple sclerosis patients. This work aims to compare the ability of different voxel- and lesion-scale uncertainty measures to capture errors related to segmentation and lesion detection, respectively. Our main contributions are (i) proposing new measures of lesion-scale uncertainty that do not utilise voxel-scale uncertainties; (ii) extending an error retention curves analysis framework for evaluation of lesion-scale uncertainty measures. Our results obtained on the multi-center testing set of 58 patients demonstrate that the proposed lesion-scale measure achieves the best performance among the analysed measures. All code implementations are provided at https://github.com/NataliiaMolch/MS_WML_uncs

Potsawee Manakul, Adian Liusie, Mark J. F. Gales

Generative Large Language Models (LLMs) such as GPT-3 are capable of generating highly fluent responses to a wide variety of user prompts. However, LLMs are known to hallucinate facts and make non-factual statements which can undermine trust in their output. Existing fact-checking approaches either require access to the output probability distribution (which may not be available for systems such as ChatGPT) or external databases that are interfaced via separate, often complex, modules. In this work, we propose "SelfCheckGPT", a simple sampling-based approach that can be used to fact-check the responses of black-box models in a zero-resource fashion, i.e. without an external database. SelfCheckGPT leverages the simple idea that if an LLM has knowledge of a given concept, sampled responses are likely to be similar and contain consistent facts. However, for hallucinated facts, stochastically sampled responses are likely to diverge and contradict one another. We investigate this approach by using GPT-3 to generate passages about individuals from the WikiBio dataset, and manually annotate the factuality of the generated passages. We demonstrate that SelfCheckGPT can: i) detect non-factual and factual sentences; and ii) rank passages in terms of factuality. We compare our approach to several baselines and show that our approach has considerably higher AUC-PR scores in sentence-level hallucination detection and higher correlation scores in passage-level factuality assessment compared to grey-box methods.

Nataliia Molchanova, Vatsal Raina, Andrey Malinin et al.

This paper explores uncertainty quantification (UQ) as an indicator of the trustworthiness of automated deep-learning (DL) tools in the context of white matter lesion (WML) segmentation from magnetic resonance imaging (MRI) scans of multiple sclerosis (MS) patients. Our study focuses on two principal aspects of uncertainty in structured output segmentation tasks. First, we postulate that a reliable uncertainty measure should indicate predictions likely to be incorrect with high uncertainty values. Second, we investigate the merit of quantifying uncertainty at different anatomical scales (voxel, lesion, or patient). We hypothesize that uncertainty at each scale is related to specific types of errors. Our study aims to confirm this relationship by conducting separate analyses for in-domain and out-of-domain settings. Our primary methodological contributions are (i) the development of novel measures for quantifying uncertainty at lesion and patient scales, derived from structural prediction discrepancies, and (ii) the extension of an error retention curve analysis framework to facilitate the evaluation of UQ performance at both lesion and patient scales. The results from a multi-centric MRI dataset of 444 patients demonstrate that our proposed measures more effectively capture model errors at the lesion and patient scales compared to measures that average voxel-scale uncertainty values. We provide the UQ protocols code at https://github.com/Medical-Image-Analysis-Laboratory/MS_WML_uncs.

Vatsal Raina, Nataliia Molchanova, Mara Graziani et al.

The development of automatic segmentation techniques for medical imaging tasks requires assessment metrics to fairly judge and rank such approaches on benchmarks. The Dice Similarity Coefficient (DSC) is a popular choice for comparing the agreement between the predicted segmentation against a ground-truth mask. However, the DSC metric has been shown to be biased to the occurrence rate of the positive class in the ground-truth, and hence should be considered in combination with other metrics. This work describes a detailed analysis of the recently proposed normalised Dice Similarity Coefficient (nDSC) for binary segmentation tasks as an adaptation of DSC which scales the precision at a fixed recall rate to tackle this bias. White matter lesion segmentation on magnetic resonance images of multiple sclerosis patients is selected as a case study task to empirically assess the suitability of nDSC. We validate the normalised DSC using two different models across 59 subject scans with a wide range of lesion loads. It is found that the nDSC is less biased than DSC with lesion load on standard white matter lesion segmentation benchmarks measured using standard rank correlation coefficients. An implementation of nDSC is made available at: https://github.com/NataliiaMolch/nDSC .

Rao Ma, Mengjie Qian, Potsawee Manakul et al.

ASR error correction is an interesting option for post processing speech recognition system outputs. These error correction models are usually trained in a supervised fashion using the decoding results of a target ASR system. This approach can be computationally intensive and the model is tuned to a specific ASR system. Recently generative large language models (LLMs) have been applied to a wide range of natural language processing tasks, as they can operate in a zero-shot or few shot fashion. In this paper we investigate using ChatGPT, a generative LLM, for ASR error correction. Based on the ASR N-best output, we propose both unconstrained and constrained, where a member of the N-best list is selected, approaches. Additionally, zero and 1-shot settings are evaluated. Experiments show that this generative LLM approach can yield performance gains for two different state-of-the-art ASR architectures, transducer and attention-encoder-decoder based, and multiple test sets.

Rao Ma, Mark J. F. Gales, Kate M. Knill et al.

Error correction models form an important part of Automatic Speech Recognition (ASR) post-processing to improve the readability and quality of transcriptions. Most prior works use the 1-best ASR hypothesis as input and therefore can only perform correction by leveraging the context within one sentence. In this work, we propose a novel N-best T5 model for this task, which is fine-tuned from a T5 model and utilizes ASR N-best lists as model input. By transferring knowledge from the pre-trained language model and obtaining richer information from the ASR decoding space, the proposed approach outperforms a strong Conformer-Transducer baseline. Another issue with standard error correction is that the generation process is not well-guided. To address this a constrained decoding process, either based on the N-best list or an ASR lattice, is used which allows additional information to be propagated.

Vatsal Raina, Mark Gales

Automated question generation is an important approach to enable personalisation of English comprehension assessment. Recently, transformer-based pretrained language models have demonstrated the ability to produce appropriate questions from a context paragraph. Typically, these systems are evaluated against a reference set of manually generated questions using n-gram based metrics, or manual qualitative assessment. Here, we focus on a fully automated multiple-choice question generation (MCQG) system where both the question and possible answers must be generated from the context paragraph. Applying n-gram based approaches is challenging for this form of system as the reference set is unlikely to capture the full range of possible questions and answer options. Conversely manual assessment scales poorly and is expensive for MCQG system development. In this work, we propose a set of performance criteria that assess different aspects of the generated multiple-choice questions of interest. These qualities include: grammatical correctness, answerability, diversity and complexity. Initial systems for each of these metrics are described, and individually evaluated on standard multiple-choice reading comprehension corpora.

Potsawee Manakul, Adian Liusie, Mark J. F. Gales

State-of-the-art summarization systems can generate highly fluent summaries. These summaries, however, may contain factual inconsistencies and/or information not present in the source. Hence, an important component of assessing the quality of summaries is to determine whether there is information consistency between the source and the summary. Existing approaches are typically based on lexical matching or representation-based methods. In this work, we introduce an alternative scheme based on standard information-theoretic measures in which the information present in the source and summary is directly compared. We propose a Multiple-choice Question Answering and Generation framework, MQAG, which approximates the information consistency by computing the expected statistical distance between summary and source answer distributions over automatically generated multiple-choice questions. This approach exploits multiple-choice answer probabilities, as predicted answer distributions can be compared. We conduct experiments on four summary evaluation datasets: QAG-CNNDM/XSum, XSum-Hallucination, Podcast Assessment, and SummEval. Experiments show that MQAG, using models trained on SQuAD or RACE, outperforms existing evaluation methods on the majority of tasks.

Andrey Malinin, Andreas Athanasopoulos, Muhamed Barakovic et al.

Distributional shift, or the mismatch between training and deployment data, is a significant obstacle to the usage of machine learning in high-stakes industrial applications, such as autonomous driving and medicine. This creates a need to be able to assess how robustly ML models generalize as well as the quality of their uncertainty estimates. Standard ML baseline datasets do not allow these properties to be assessed, as the training, validation and test data are often identically distributed. Recently, a range of dedicated benchmarks have appeared, featuring both distributionally matched and shifted data. Among these benchmarks, the Shifts dataset stands out in terms of the diversity of tasks as well as the data modalities it features. While most of the benchmarks are heavily dominated by 2D image classification tasks, Shifts contains tabular weather forecasting, machine translation, and vehicle motion prediction tasks. This enables the robustness properties of models to be assessed on a diverse set of industrial-scale tasks and either universal or directly applicable task-specific conclusions to be reached. In this paper, we extend the Shifts Dataset with two datasets sourced from industrial, high-risk applications of high societal importance. Specifically, we consider the tasks of segmentation of white matter Multiple Sclerosis lesions in 3D magnetic resonance brain images and the estimation of power consumption in marine cargo vessels. Both tasks feature ubiquitous distributional shifts and a strict safety requirement due to the high cost of errors. These new datasets will allow researchers to further explore robust generalization and uncertainty estimation in new situations. In this work, we provide a description of the dataset and baseline results for both tasks.

Mengjie Qian, Rao Ma, Adian Liusie et al. · cambridge

Multimodal Video Search by Examples (MVSE) investigates using video clips as the query term for information retrieval, rather than the more traditional text query. This enables far richer search modalities such as images, speaker, content, topic, and emotion. A key element for this process is highly rapid and flexible search to support large archives, which in MVSE is facilitated by representing video attributes with embeddings. This work aims to compensate for any performance loss from this rapid archive search by examining reranking approaches. In particular, zero-shot reranking methods using large language models (LLMs) are investigated as these are applicable to any video archive audio content. Performance is evaluated for topic-based retrieval on a publicly available video archive, the BBC Rewind corpus. Results demonstrate that reranking significantly improves retrieval ranking without requiring any task-specific in-domain training data. Furthermore, three sources of information (ASR transcriptions, automatic summaries and synopses) as input for LLM reranking were compared. To gain a deeper understanding and further insights into the performance differences and limitations of these text sources, we employ a fact-checking approach to analyse the information consistency among them.

Rao Ma, Mengjie Qian, Mark J. F. Gales et al.

A crucial part of an accurate and reliable spoken language assessment system is the underlying ASR model. Recently, large-scale pre-trained ASR foundation models such as Whisper have been made available. As the output of these models is designed to be human readable, punctuation is added, numbers are presented in Arabic numeric form and abbreviations are included. Additionally, these models have a tendency to skip disfluencies and hesitations in the output. Though useful for readability, these attributes are not helpful for assessing the ability of a candidate and providing feedback. Here a precise transcription of what a candidate said is needed. In this paper, we give a detailed analysis of Whisper outputs and propose two solutions: fine-tuning and soft prompt tuning. Experiments are conducted on both public speech corpora and an English learner dataset. Results show that we can effectively alter the decoding behaviour of Whisper to generate the exact words spoken in the response.

Mengjie Qian, Siyuan Tang, Rao Ma et al.

Foundation ASR models often support many languages, e.g. 100 languages in Whisper. However, there has been limited work on integrating an additional, typically low-resource, language, while maintaining performance on the original language set. Fine-tuning, while simple, may degrade the accuracy of the original set. We compare three approaches that exploit adaptation parameters: soft language code tuning, train only the language code; soft prompt tuning, train prepended tokens; and LoRA where a small set of additional parameters are optimised. Elastic Weight Consolidation (EWC) offers an alternative compromise with the potential to maintain performance in specific target languages. Results show that direct fine-tuning yields the best performance for the new language but degrades existing language capabilities. EWC can address this issue for specific languages. If only adaptation parameters are used, the language capabilities are maintained but at the cost of performance in the new language.

Rao Ma, Adian Liusie, Mark J. F. Gales et al.

Text and vision foundation models can perform many tasks in a zero-shot setting, a desirable property that enables these systems to be applied in general and low-resource settings. There has been far less work, however, on the zero-shot abilities of ASR foundation models, with these systems typically fine-tuned to specific tasks or constrained to applications that match their training criterion and data annotation. In this work we investigate the ability of Whisper and MMS, ASR foundation models trained primarily for speech recognition, to perform zero-shot audio classification. We use simple template-based text prompts at the decoder and use the resulting decoding probabilities to generate zero-shot predictions. Without training the model on extra data or adding any new parameters, we demonstrate that Whisper shows promising zero-shot classification performance on a range of 8 audio-classification datasets, outperforming the accuracy of existing state-of-the-art zero-shot baselines by an average of 9%. One important step to unlock the emergent ability is debiasing, where a simple unsupervised reweighting method of the class probabilities yields consistent significant performance gains. We further show that performance increases with model size, implying that as ASR foundation models scale up, they may exhibit improved zero-shot performance.

Potsawee Manakul, Yassir Fathullah, Adian Liusie et al.

In this paper, we consider the challenge of summarizing patients' medical progress notes in a limited data setting. For the Problem List Summarization (shared task 1A) at the BioNLP Workshop 2023, we demonstrate that Clinical-T5 fine-tuned to 765 medical clinic notes outperforms other extractive, abstractive and zero-shot baselines, yielding reasonable baseline systems for medical note summarization. Further, we introduce Hierarchical Ensemble of Summarization Models (HESM), consisting of token-level ensembles of diverse fine-tuned Clinical-T5 models, followed by Minimum Bayes Risk (MBR) decoding. Our HESM approach lead to a considerable summarization performance boost, and when evaluated on held-out challenge data achieved a ROUGE-L of 32.77, which was the best-performing system at the top of the shared task leaderboard.

Vyas Raina, Mark Gales

Deep learning based systems are susceptible to adversarial attacks, where a small, imperceptible change at the input alters the model prediction. However, to date the majority of the approaches to detect these attacks have been designed for image processing systems. Many popular image adversarial detection approaches are able to identify adversarial examples from embedding feature spaces, whilst in the NLP domain existing state of the art detection approaches solely focus on input text features, without consideration of model embedding spaces. This work examines what differences result when porting these image designed strategies to Natural Language Processing (NLP) tasks - these detectors are found to not port over well. This is expected as NLP systems have a very different form of input: discrete and sequential in nature, rather than the continuous and fixed size inputs for images. As an equivalent model-focused NLP detection approach, this work proposes a simple sentence-embedding "residue" based detector to identify adversarial examples. On many tasks, it out-performs ported image domain detectors and recent state of the art NLP specific detectors.

Yassir Fathullah, Mark J. F. Gales

Deep learning is increasingly being applied in safety-critical domains. For these scenarios it is important to know the level of uncertainty in a model's prediction to ensure appropriate decisions are made by the system. Deep ensembles are the de-facto standard approach to obtaining various measures of uncertainty. However, ensembles often significantly increase the resources required in the training and/or deployment phases. Approaches have been developed that typically address the costs in one of these phases. In this work we propose a novel training approach, self-distribution distillation (S2D), which is able to efficiently train a single model that can estimate uncertainties. Furthermore it is possible to build ensembles of these models and apply hierarchical ensemble distillation approaches. Experiments on CIFAR-100 showed that S2D models outperformed standard models and Monte-Carlo dropout. Additional out-of-distribution detection experiments on LSUN, Tiny ImageNet, SVHN showed that even a standard deep ensemble can be outperformed using S2D based ensembles and novel distilled models.

Stefano Bannò, Rao Ma, Mengjie Qian et al.

Grammatical feedback is crucial for L2 learners, teachers, and testers. Spoken grammatical error correction (GEC) aims to supply feedback to L2 learners on their use of grammar when speaking. This process usually relies on a cascaded pipeline comprising an ASR system, disfluency removal, and GEC, with the associated concern of propagating errors between these individual modules. In this paper, we introduce an alternative "end-to-end" approach to spoken GEC, exploiting a speech recognition foundation model, Whisper. This foundation model can be used to replace the whole framework or part of it, e.g., ASR and disfluency removal. These end-to-end approaches are compared to more standard cascaded approaches on the data obtained from a free-speaking spoken language assessment test, Linguaskill. Results demonstrate that end-to-end spoken GEC is possible within this architecture, but the lack of available data limits current performance compared to a system using large quantities of text-based GEC data. Conversely, end-to-end disfluency detection and removal, which is easier for the attention-based Whisper to learn, does outperform cascaded approaches. Additionally, the paper discusses the challenges of providing feedback to candidates when using end-to-end systems for spoken GEC.

Stefano Bannò, Kate M. Knill, Marco Matassoni et al.

There has been a growing demand for automated spoken language assessment systems in recent years. A standard pipeline for this process is to start with a speech recognition system and derive features, either hand-crafted or based on deep-learning, that exploit the transcription and audio. Though these approaches can yield high performance systems, they require speech recognition systems that can be used for L2 speakers, and preferably tuned to the specific form of test being deployed. Recently a self-supervised speech representation based scheme, requiring no speech recognition, was proposed. This work extends the initial analysis conducted on this approach to a large scale proficiency test, Linguaskill, that comprises multiple parts, each designed to assess different attributes of a candidate's speaking proficiency. The performance of the self-supervised, wav2vec 2.0, system is compared to a high performance hand-crafted assessment system and a BERT-based text system both of which use speech transcriptions. Though the wav2vec 2.0 based system is found to be sensitive to the nature of the response, it can be configured to yield comparable performance to systems requiring a speech transcription, and yields gains when appropriately combined with standard approaches.

Adian Liusie, Potsawee Manakul, Mark J. F. Gales

Prompt-based classifiers are an attractive approach for zero-shot classification. However, the precise choice of the prompt template and label words can largely influence performance, with semantically equivalent settings often showing notable performance difference. This discrepancy can be partly attributed to word biases, where the classifier may be biased towards classes. To address this problem, it is possible to optimise classification thresholds on a labelled data set, however, this mitigates some of the advantages of prompt-based classifiers. This paper instead approaches this problem by examining the expected marginal probabilities of the classes. Here, probabilities are reweighted to have a uniform prior over classes, in an unsupervised fashion. Further, we draw a theoretical connection between the class priors and the language models' word prior, and offer the ability to set a threshold in a zero-resource fashion. We show that matching class priors correlates strongly with the oracle upper bound performance and demonstrate large consistent performance gains for prompt settings over a range of NLP tasks.

Adian Liusie, Vatsal Raina, Mark Gales

Recently it has been shown that without any access to the contextual passage, multiple choice reading comprehension (MCRC) systems are able to answer questions significantly better than random on average. These systems use their accumulated "world knowledge" to directly answer questions, rather than using information from the passage. This paper examines the possibility of exploiting this observation as a tool for test designers to ensure that the use of "world knowledge" is acceptable for a particular set of questions. We propose information-theory based metrics that enable the level of "world knowledge" exploited by systems to be assessed. Two metrics are described: the expected number of options, which measures whether a passage-free system can identify the answer a question using world knowledge; and the contextual mutual information, which measures the importance of context for a given question. We demonstrate that questions with low expected number of options, and hence answerable by the shortcut system, are often similarly answerable by humans without context. This highlights that the general knowledge 'shortcuts' could be equally used by exam candidates, and that our proposed metrics may be helpful for future test designers to monitor the quality of questions.

Potsawee Manakul, Mark J. F. Gales

Automatic summary assessment is useful for both machine-generated and human-produced summaries. Automatically evaluating the summary text given the document enables, for example, summary generation system development and detection of inappropriate summaries. Summary assessment can be run in a number of modes: ranking summary generation systems; ranking summaries of a particular document; and estimating the quality of a document-summary pair on an absolute scale. Existing datasets with annotation for summary assessment are usually based on news summarization datasets such as CNN/DailyMail or XSum. In this work, we describe a new dataset, the podcast summary assessment corpus, a collection of podcast summaries that were evaluated by human experts at TREC2020. Compared to existing summary assessment data, this dataset has two unique aspects: (i) long-input, speech podcast based, documents; and (ii) an opportunity to detect inappropriate reference summaries in podcast corpus. First, we examine existing assessment methods, including model-free and model-based methods, and provide benchmark results for this long-input summary assessment dataset. Second, with the aim of filtering reference summary-document pairings for training, we apply summary assessment for data selection. The experimental results on these two aspects provide interesting insights on the summary assessment and generation tasks. The podcast summary assessment data is available.

Adian Liusie, Vatsal Raina, Andrew Mullooly et al.

Multiple choice exams are widely used to assess candidates across a diverse range of domains and tasks. To moderate question quality, newly proposed questions often pass through pre-test evaluation stages before being deployed into real-world exams. Currently, this evaluation process is manually intensive, which can lead to time lags in the question development cycle. Streamlining this process via automation can significantly enhance efficiency, however, there's a current lack of datasets with adequate pre-test analysis information. In this paper we analyse a subset of the public Cambridge Multiple-Choice Questions Reading Database released by Cambridge University Press & Assessment; a multiple-choice comprehension dataset of questions at different target levels, with corresponding candidate selection distributions. We introduce the task of candidate distribution matching, propose several evaluation metrics for the task, and demonstrate that automatic systems trained on RACE++ can be leveraged as baselines for our task. We further demonstrate that these automatic systems can be used for practical pre-test evaluation tasks such as detecting underperforming distractors, where our detection systems can automatically identify poor distractors that few candidates select.

Vatsal Raina, Adian Liusie, Mark Gales

Multiple-choice reading and listening comprehension tests are an important part of language assessment. Content creators for standard educational tests need to carefully curate questions that assess the comprehension abilities of candidates taking the tests. However, recent work has shown that a large number of questions in general multiple-choice reading comprehension datasets can be answered without comprehension, by leveraging world knowledge instead. This work investigates how much of a contextual passage needs to be read in multiple-choice reading based on conversation transcriptions and listening comprehension tests to be able to work out the correct answer. We find that automated reading comprehension systems can perform significantly better than random with partial or even no access to the context passage. These findings offer an approach for content creators to automatically capture the trade-off between comprehension and world knowledge required for their proposed questions.

Rao Ma, Mengjie Qian, Mark J. F. Gales et al.

As speech recognition model sizes and training data requirements grow, it is increasingly common for systems to only be available via APIs from online service providers rather than having direct access to models themselves. In this scenario it is challenging to adapt systems to a specific target domain. To address this problem we consider the recently released OpenAI Whisper ASR as an example of a large-scale ASR system to assess adaptation methods. An error correction based approach is adopted, as this does not require access to the model, but can be trained from either 1-best or N-best outputs that are normally available via the ASR API. LibriSpeech is used as the primary target domain for adaptation. The generalization ability of the system in two distinct dimensions are then evaluated. First, whether the form of correction model is portable to other speech recognition domains, and secondly whether it can be used for ASR models having a different architecture.

Vyas Raina, Mark Gales

Adversarial attacks insert small, imperceptible perturbations to input samples that cause large, undesired changes to the output of deep learning models. Despite extensive research on generating adversarial attacks and building defense systems, there has been limited research on understanding adversarial attacks from an input-data perspective. This work introduces the notion of sample attackability, where we aim to identify samples that are most susceptible to adversarial attacks (attackable samples) and conversely also identify the least susceptible samples (robust samples). We propose a deep-learning-based detector to identify the adversarially attackable and robust samples in an unseen dataset for an unseen target model. Experiments on standard image classification datasets enables us to assess the portability of the deep attackability detector across a range of architectures. We find that the deep attackability detector performs better than simple model uncertainty-based measures for identifying the attackable/robust samples. This suggests that uncertainty is an inadequate proxy for measuring sample distance to a decision boundary. In addition to better understanding adversarial attack theory, it is found that the ability to identify the adversarially attackable and robust samples has implications for improving the efficiency of sample-selection tasks.

Stefano Bannò, Kate Knill, Mark J. F. Gales

Grammatical feedback is crucial for consolidating second language (L2) learning. Most research in computer-assisted language learning has focused on feedback through grammatical error correction (GEC) systems, rather than examining more holistic feedback that may be more useful for learners. This holistic feedback will be referred to as grammatical error feedback (GEF). In this paper, we present a novel implicit evaluation approach to GEF that eliminates the need for manual feedback annotations. Our method adopts a grammatical lineup approach where the task is to pair feedback and essay representations from a set of possible alternatives. This matching process can be performed by appropriately prompting a large language model (LLM). An important aspect of this process, explored here, is the form of the lineup, i.e., the selection of foils. This paper exploits this framework to examine the quality and need for GEC to generate feedback, as well as the system used to generate feedback, using essays from the Cambridge Learner Corpus.

Vyas Raina, Mark Gales

Adversarial attack research in natural language processing (NLP) has made significant progress in designing powerful attack methods and defence approaches. However, few efforts have sought to identify which source samples are the most attackable or robust, i.e. can we determine for an unseen target model, which samples are the most vulnerable to an adversarial attack. This work formally extends the definition of sample attackability/robustness for NLP attacks. Experiments on two popular NLP datasets, four state of the art models and four different NLP adversarial attack methods, demonstrate that sample uncertainty is insufficient for describing characteristics of attackable/robust samples and hence a deep learning based detector can perform much better at identifying the most attackable and robust samples for an unseen target model. Nevertheless, further analysis finds that there is little agreement in which samples are considered the most attackable/robust across different NLP attack methods, explaining a lack of portability of attackability detection methods across attack methods.

Qingyun Dou, Mark Gales

Attention-based autoregressive models have achieved state-of-the-art performance in various sequence-to-sequence tasks, including Text-To-Speech (TTS) and Neural Machine Translation (NMT), but can be difficult to train. The standard training approach, teacher forcing, guides a model with the reference back-history. During inference, the generated back-history must be used. This mismatch limits the evaluation performance. Attention forcing has been introduced to address the mismatch, guiding the model with the generated back-history and reference attention. While successful in tasks with continuous outputs like TTS, attention forcing faces additional challenges in tasks with discrete outputs like NMT. This paper introduces the two extensions of attention forcing to tackle these challenges. (1) Scheduled attention forcing automatically turns attention forcing on and off, which is essential for tasks with discrete outputs. (2) Parallel attention forcing makes training parallel, and is applicable to Transformer-based models. The experiments show that the proposed approaches improve the performance of models based on RNNs and Transformers.

Qingyun Dou, Mark Gales

Deliberation networks are a family of sequence-to-sequence models, which have achieved state-of-the-art performance in a wide range of tasks such as machine translation and speech synthesis. A deliberation network consists of multiple standard sequence-to-sequence models, each one conditioned on the initial input and the output of the previous model. During training, there are several key questions: whether to apply Monte Carlo approximation to the gradients or the loss, whether to train the standard models jointly or separately, whether to run an intermediate model in teacher forcing or free running mode, whether to apply task-specific techniques. Previous work on deliberation networks typically explores one or two training options for a specific task. This work introduces a unifying framework, covering various training options, and addresses the above questions. In general, it is simpler to approximate the gradients. When parallel training is essential, separate training should be adopted. Regardless of the task, the intermediate model should be in free running mode. For tasks where the output is continuous, a guided attention loss can be used to prevent degradation into a standard model.

Vyas Raina, Mark Gales

Grammatical Error Correction (GEC) systems perform a sequence-to-sequence task, where an input word sequence containing grammatical errors, is corrected for these errors by the GEC system to output a grammatically correct word sequence. With the advent of deep learning methods, automated GEC systems have become increasingly popular. For example, GEC systems are often used on speech transcriptions of English learners as a form of assessment and feedback - these powerful GEC systems can be used to automatically measure an aspect of a candidate's fluency. The count of \textit{edits} from a candidate's input sentence (or essay) to a GEC system's grammatically corrected output sentence is indicative of a candidate's language ability, where fewer edits suggest better fluency. The count of edits can thus be viewed as a \textit{fluency score} with zero implying perfect fluency. However, although deep learning based GEC systems are extremely powerful and accurate, they are susceptible to adversarial attacks: an adversary can introduce a small, specific change at the input of a system that causes a large, undesired change at the output. When considering the application of GEC systems to automated language assessment, the aim of an adversary could be to cheat by making a small change to a grammatically incorrect input sentence that conceals the errors from a GEC system, such that no edits are found and the candidate is unjustly awarded a perfect fluency score. This work examines a simple universal substitution adversarial attack that non-native speakers of English could realistically employ to deceive GEC systems used for assessment.

Stefano Bannò, Penny Karanasou, Kate Knill et al.

Evaluating the grammatical competence of second language (L2) learners is essential both for providing targeted feedback and for assessing proficiency. To achieve this, we propose a novel framework leveraging the English Grammar Profile (EGP), a taxonomy of grammatical constructs mapped to the proficiency levels of the Common European Framework of Reference (CEFR), to detect learners' attempts at grammatical constructs and classify them as successful or unsuccessful. This detection can then be used to provide fine-grained feedback. Moreover, the grammatical constructs are used as predictors of proficiency assessment by using automatically detected attempts as predictors of holistic CEFR proficiency. For the selection of grammatical constructs derived from the EGP, rule-based and LLM-based classifiers are compared. We show that LLMs outperform rule-based methods on semantically and pragmatically nuanced constructs, while rule-based approaches remain competitive for constructs that rely purely on morphological or syntactic features and do not require semantic interpretation. For proficiency assessment, we evaluate both rule-based and hybrid pipelines and show that a hybrid approach combining a rule-based pre-filter with an LLM consistently yields the strongest performance. Since our framework operates on pairs of original learner sentences and their corrected counterparts, we also evaluate a fully automated pipeline using automatic grammatical error correction. This pipeline closely approaches the performance of semi-automated systems based on manual corrections, particularly for the detection of successful attempts at grammatical constructs. Overall, our framework emphasises learners' successful attempts in addition to unsuccessful ones, enabling positive, formative feedback and providing actionable insights into grammatical development.

Rao Ma, Mengjie Qian, Yassir Fathullah et al.

There has been increasing interest in building multilingual foundation models for NLP and speech research. This paper examines how to expand the speech translation capability of these models with restricted data. Whisper, a speech foundation model with strong performance on speech recognition and English translation, is used as the example model. Using speech-to-speech retrieval to analyse the audio representations generated by the encoder, we show that utterances from different languages are mapped to a shared semantic space. This shared embedding space can then be leveraged for zero-shot cross-lingual transfer in speech translation. By fine-tuning the Whisper decoder with only English-to-Chinese speech translation data, improved performance for translation to Chinese can be obtained for multiple languages, in addition to English. Furthermore, for languages related to those seen in training it is possible to perform speech translation, despite the model never seeing the language in training, or being able to perform transcription.

Rao Ma, Mengjie Qian, Mark Gales et al.

Error correction (EC) models play a crucial role in refining Automatic Speech Recognition (ASR) transcriptions, enhancing the readability and quality of transcriptions. Without requiring access to the underlying code or model weights, EC can improve performance and provide domain adaptation for black-box ASR systems. This work investigates the use of large language models (LLMs) for error correction across diverse scenarios. 1-best ASR hypotheses are commonly used as the input to EC models. We propose building high-performance EC models using ASR N-best lists which should provide more contextual information for the correction process. Additionally, the generation process of a standard EC model is unrestricted in the sense that any output sequence can be generated. For some scenarios, such as unseen domains, this flexibility may impact performance. To address this, we introduce a constrained decoding approach based on the N-best list or an ASR lattice. Finally, most EC models are trained for a specific ASR system requiring retraining whenever the underlying ASR system is changed. This paper explores the ability of EC models to operate on the output of different ASR systems. This concept is further extended to zero-shot error correction using LLMs, such as ChatGPT. Experiments on three standard datasets demonstrate the efficacy of our proposed methods for both Transducer and attention-based encoder-decoder ASR systems. In addition, the proposed method can serve as an effective method for model ensembling.

Vatsal Raina, Adian Liusie, Mark Gales

Multiple-choice tests are a common approach for assessing candidates' comprehension skills. Standard multiple-choice reading comprehension exams require candidates to select the correct answer option from a discrete set based on a question in relation to a contextual passage. For appropriate assessment, the distractor answer options must by definition be incorrect but plausible and diverse. However, generating good quality distractors satisfying these criteria is a challenging task for content creators. We propose automated assessment metrics for the quality of distractors in multiple-choice reading comprehension tests. Specifically, we define quality in terms of the incorrectness, plausibility and diversity of the distractor options. We assess incorrectness using the classification ability of a binary multiple-choice reading comprehension system. Plausibility is assessed by considering the distractor confidence - the probability mass associated with the distractor options for a standard multi-class multiple-choice reading comprehension system. Diversity is assessed by pairwise comparison of an embedding-based equivalence metric between the distractors of a question. To further validate the plausibility metric we compare against candidate distributions over multiple-choice questions and agreement with a ChatGPT model's interpretation of distractor plausibility and diversity.

Vyas Raina, Mark Gales

Speech enabled foundation models, either in the form of flexible speech recognition based systems or audio-prompted large language models (LLMs), are becoming increasingly popular. One of the interesting aspects of these models is their ability to perform tasks other than automatic speech recognition (ASR) using an appropriate prompt. For example, the OpenAI Whisper model can perform both speech transcription and speech translation. With the development of audio-prompted LLMs there is the potential for even greater control options. In this work we demonstrate that with this greater flexibility the systems can be susceptible to model-control adversarial attacks. Without any access to the model prompt it is possible to modify the behaviour of the system by appropriately changing the audio input. To illustrate this risk, we demonstrate that it is possible to prepend a short universal adversarial acoustic segment to any input speech signal to override the prompt setting of an ASR foundation model. Specifically, we successfully use a universal adversarial acoustic segment to control Whisper to always perform speech translation, despite being set to perform speech transcription. Overall, this work demonstrates a new form of adversarial attack on multi-tasking speech enabled foundation models that needs to be considered prior to the deployment of this form of model.

Vyas Raina, Mark Gales

For sequence-to-sequence tasks it is challenging to combine individual system outputs. Further, there is also often a mismatch between the decoding criterion and the one used for assessment. Minimum Bayes' Risk (MBR) decoding can be used to combine system outputs in a manner that encourages better alignment with the final assessment criterion. This paper examines MBR decoding for Grammatical Error Correction (GEC) systems, where performance is usually evaluated in terms of edits and an associated F-score. Hence, we propose a novel MBR loss function directly linked to this form of criterion. Furthermore, an approach to expand the possible set of candidate sentences is described. This builds on a current max-voting combination scheme, as well as individual edit-level selection. Experiments on three popular GEC datasets and with state-of-the-art GEC systems demonstrate the efficacy of the proposed MBR approach. Additionally, the paper highlights how varying reward metrics within the MBR decoding framework can provide control over precision, recall, and the F-score in combined GEC systems.

Vatsal Raina, Adian Liusie, Mark Gales

Automated assessment in natural language generation is a challenging task. Instruction-tuned large language models (LLMs) have shown promise in reference-free evaluation, particularly through comparative assessment. However, the quadratic computational complexity of pairwise comparisons limits its scalability. To address this, efficient comparative assessment has been explored by applying comparative strategies on zero-shot LLM probabilities. We propose a framework for finetuning LLMs for comparative assessment to align the model's output with the target distribution of comparative probabilities. By training on soft probabilities, our approach improves state-of-the-art performance while maintaining high performance with an efficient subset of comparisons.

Asma Farajidizaji, Vatsal Raina, Mark Gales

Text simplification is a common task where the text is adapted to make it easier to understand. Similarly, text elaboration can make a passage more sophisticated, offering a method to control the complexity of reading comprehension tests. However, text simplification and elaboration tasks are limited to only relatively alter the readability of texts. It is useful to directly modify the readability of any text to an absolute target readability level to cater to a diverse audience. Ideally, the readability of readability-controlled generated text should be independent of the source text. Therefore, we propose a novel readability-controlled text modification task. The task requires the generation of 8 versions at various target readability levels for each input text. We introduce novel readability-controlled text modification metrics. The baselines for this task use ChatGPT and Llama-2, with an extension approach introducing a two-step process (generating paraphrases by passing through the language model twice). The zero-shot approaches are able to push the readability of the paraphrases in the desired direction but the final readability remains correlated with the original text's readability. We also find greater drops in semantic and lexical similarity between the source and target texts with greater shifts in the readability.

Luran Wang, Mark Gales, Vatsal Raina

Understanding the importance of the inputs on the output is useful across many tasks. This work provides an information-theoretic framework to analyse the influence of inputs for text classification tasks. Natural language processing (NLP) tasks take either a single element input or multiple element inputs to predict an output variable, where an element is a block of text. Each text element has two components: an associated semantic meaning and a linguistic realization. Multiple-choice reading comprehension (MCRC) and sentiment classification (SC) are selected to showcase the framework. For MCRC, it is found that the context influence on the output compared to the question influence reduces on more challenging datasets. In particular, more challenging contexts allow a greater variation in complexity of questions. Hence, test creators need to carefully consider the choice of the context when designing multiple-choice questions for assessment. For SC, it is found the semantic meaning of the input text dominates (above 80\% for all datasets considered) compared to its linguistic realisation when determining the sentiment. The framework is made available at: https://github.com/WangLuran/nlp-element-influence

Vyas Raina, Adian Liusie, Mark Gales

Large Language Models (LLMs) are powerful zero-shot assessors used in real-world situations such as assessing written exams and benchmarking systems. Despite these critical applications, no existing work has analyzed the vulnerability of judge-LLMs to adversarial manipulation. This work presents the first study on the adversarial robustness of assessment LLMs, where we demonstrate that short universal adversarial phrases can be concatenated to deceive judge LLMs to predict inflated scores. Since adversaries may not know or have access to the judge-LLMs, we propose a simple surrogate attack where a surrogate model is first attacked, and the learned attack phrase then transferred to unknown judge-LLMs. We propose a practical algorithm to determine the short universal attack phrases and demonstrate that when transferred to unseen models, scores can be drastically inflated such that irrespective of the assessed text, maximum scores are predicted. It is found that judge-LLMs are significantly more susceptible to these adversarial attacks when used for absolute scoring, as opposed to comparative assessment. Our findings raise concerns on the reliability of LLM-as-a-judge methods, and emphasize the importance of addressing vulnerabilities in LLM assessment methods before deployment in high-stakes real-world scenarios.

Kate Knill, Diane Nicholls, Mark J. F. Gales et al.

We introduce the Speak & Improve Corpus 2025, a dataset of L2 learner English data with holistic scores and language error annotation, collected from open (spontaneous) speaking tests on the Speak & Improve learning platform. The aim of the corpus release is to address a major challenge to developing L2 spoken language processing systems, the lack of publicly available data with high-quality annotations. It is being made available for non-commercial use on the ELiT website. In designing this corpus we have sought to make it cover a wide-range of speaker attributes, from their L1 to their speaking ability, as well as providing manual annotations. This enables a range of language-learning tasks to be examined, such as assessing speaking proficiency or providing feedback on grammatical errors in a learner's speech. Additionally the data supports research into the underlying technology required for these tasks including automatic speech recognition (ASR) of low resource L2 learner English, disfluency detection or spoken grammatical error correction (GEC). The corpus consists of around 315 hours of L2 English learners audio with holistic scores, and a subset of audio annotated with transcriptions and error labels.

Vatsal Raina, Mark Gales

Enterprise retrieval augmented generation (RAG) offers a highly flexible framework for combining powerful large language models (LLMs) with internal, possibly temporally changing, documents. In RAG, documents are first chunked. Relevant chunks are then retrieved for a user query, which are passed as context to a synthesizer LLM to generate the query response. However, the retrieval step can limit performance, as incorrect chunks can lead the synthesizer LLM to generate a false response. This work applies a zero-shot adaptation of standard dense retrieval steps for more accurate chunk recall. Specifically, a chunk is first decomposed into atomic statements. A set of synthetic questions are then generated on these atoms (with the chunk as the context). Dense retrieval involves finding the closest set of synthetic questions, and associated chunks, to the user query. It is found that retrieval with the atoms leads to higher recall than retrieval with chunks. Further performance gain is observed with retrieval using the synthetic questions generated over the atoms. Higher recall at the retrieval step enables higher performance of the enterprise LLM using the RAG pipeline.

Mengjie Qian, Kate Knill, Stefano Banno et al.

This paper presents the "Speak & Improve Challenge 2025: Spoken Language Assessment and Feedback" -- a challenge associated with the ISCA SLaTE 2025 Workshop. The goal of the challenge is to advance research on spoken language assessment and feedback, with tasks associated with both the underlying technology and language learning feedback. Linked with the challenge, the Speak & Improve (S&I) Corpus 2025 is being pre-released, a dataset of L2 learner English data with holistic scores and language error annotation, collected from open (spontaneous) speaking tests on the Speak & Improve learning platform. The corpus consists of approximately 315 hours of audio data from second language English learners with holistic scores, and a 55-hour subset with manual transcriptions and error labels. The Challenge has four shared tasks: Automatic Speech Recognition (ASR), Spoken Language Assessment (SLA), Spoken Grammatical Error Correction (SGEC), and Spoken Grammatical Error Correction Feedback (SGECF). Each of these tasks has a closed track where a predetermined set of models and data sources are allowed to be used, and an open track where any public resource may be used. Challenge participants may do one or more of the tasks. This paper describes the challenge, the S&I Corpus 2025, and the baseline systems released for the Challenge.

Stefano Bannò, Hari Krishna Vydana, Kate M. Knill et al.

Automated essay scoring (AES) to evaluate second language (L2) proficiency has been a firmly established technology used in educational contexts for decades. Although holistic scoring has seen advancements in AES that match or even exceed human performance, analytic scoring still encounters issues as it inherits flaws and shortcomings from the human scoring process. The recent introduction of large language models presents new opportunities for automating the evaluation of specific aspects of L2 writing proficiency. In this paper, we perform a series of experiments using GPT-4 in a zero-shot fashion on a publicly available dataset annotated with holistic scores based on the Common European Framework of Reference and aim to extract detailed information about their underlying analytic components. We observe significant correlations between the automatically predicted analytic scores and multiple features associated with the individual proficiency components.

Guangzhi Sun, Potsawee Manakul, Adian Liusie et al.

Multimodal foundation models are prone to hallucination, generating outputs that either contradict the input or are not grounded by factual information. Given the diversity in architectures, training data and instruction tuning techniques, there can be large variations in systems' susceptibility to hallucinations. To assess system hallucination robustness, hallucination ranking approaches have been developed for specific tasks such as image captioning, question answering, summarization, or biography generation. However, these approaches typically compare model outputs to gold-standard references or labels, limiting hallucination benchmarking for new domains. This work proposes "CrossCheckGPT", a reference-free universal hallucination ranking for multimodal foundation models. The core idea of CrossCheckGPT is that the same hallucinated content is unlikely to be generated by different independent systems, hence cross-system consistency can provide meaningful and accurate hallucination assessment scores. CrossCheckGPT can be applied to any model or task, provided that the information consistency between outputs can be measured through an appropriate distance metric. Focusing on multimodal large language models that generate text, we explore two information consistency measures: CrossCheck-explicit and CrossCheck-implicit. We showcase the applicability of our method for hallucination ranking across various modalities, namely the text, image, and audio-visual domains. Further, we propose the first audio-visual hallucination benchmark, "AVHalluBench", and illustrate the effectiveness of CrossCheckGPT, achieving correlations of 98% and 89% with human judgements on MHaluBench and AVHalluBench, respectively.

Akash Gupta, Ivaxi Sheth, Vyas Raina et al.

With the recent emergence of powerful instruction-tuned large language models (LLMs), various helpful conversational Artificial Intelligence (AI) systems have been deployed across many applications. When prompted by users, these AI systems successfully perform a wide range of tasks as part of a conversation. To provide some sort of memory and context, such approaches typically condition their output on the entire conversational history. Although this sensitivity to the conversational history can often lead to improved performance on subsequent tasks, we find that performance can in fact also be negatively impacted, if there is a task-switch. To the best of our knowledge, our work makes the first attempt to formalize the study of such vulnerabilities and interference of tasks in conversational LLMs caused by task-switches in the conversational history. Our experiments across 5 datasets with 15 task switches using popular LLMs reveal that many of the task-switches can lead to significant performance degradation.

Piotr Molenda, Adian Liusie, Mark J. F. Gales

Watermarking generative-AI systems, such as LLMs, has gained considerable interest, driven by their enhanced capabilities across a wide range of tasks. Although current approaches have demonstrated that small, context-dependent shifts in the word distributions can be used to apply and detect watermarks, there has been little work in analyzing the impact that these perturbations have on the quality of generated texts. Balancing high detectability with minimal performance degradation is crucial in terms of selecting the appropriate watermarking setting; therefore this paper proposes a simple analysis framework where comparative assessment, a flexible NLG evaluation framework, is used to assess the quality degradation caused by a particular watermark setting. We demonstrate that our framework provides easy visualization of the quality-detection trade-off of watermark settings, enabling a simple solution to find an LLM watermark operating point that provides a well-balanced performance. This approach is applied to two different summarization systems and a translation system, enabling cross-model analysis for a task, and cross-task analysis.

Adian Liusie, Yassir Fathullah, Mark J. F. Gales

Large Language Models (LLMs) have demonstrated impressive zero-shot capabilities and versatility in NLP tasks, however they sometimes fail to maintain crucial invariances for specific tasks. One example is permutation sensitivity, where LLMs' outputs may significantly vary depending on the order of the input options. While debiasing techniques can mitigate these issues, and yield better performance and reliability, they often come with a high computational cost at inference. This paper addresses this inefficiency at inference time. The aim is to distill the capabilities of a computationally intensive, debiased, teacher model into a more compact student model. We explore two variants of student models: one based on pure distillation, and the other on an error-correction approach for more complex tasks, where the student corrects a single biased decision from the teacher to achieve a debiased output. Our approach is general and can be applied to both black-box and white-box LLMs. Furthermore, we demonstrate that our compact, encoder-only student models can outperform their larger, biased teacher counterparts, achieving better results with significantly fewer parameters.

Vatsal Raina, Mark Gales

Multiple-choice (MC) tests are an efficient method to assess English learners. It is useful for test creators to rank candidate MC questions by difficulty during exam curation. Typically, the difficulty is determined by having human test takers trial the questions in a pretesting stage. However, this is expensive and not scalable. Therefore, we explore automated approaches to rank MC questions by difficulty. However, there is limited data for explicit training of a system for difficulty scores. Hence, we compare task transfer and zero-shot approaches: task transfer adapts level classification and reading comprehension systems for difficulty ranking while zero-shot prompting of instruction finetuned language models contrasts absolute assessment against comparative. It is found that level classification transfers better than reading comprehension. Additionally, zero-shot comparative assessment is more effective at difficulty ranking than the absolute assessment and even the task transfer approaches at question difficulty ranking with a Spearman's correlation of 40.4%. Combining the systems is observed to further boost the correlation.