Timothy Baldwin

Thinh Hung Truong, Timothy Baldwin, Karin Verspoor et al.

Negation has been shown to be a major bottleneck for masked language models, such as BERT. However, whether this finding still holds for larger-sized auto-regressive language models (``LLMs'') has not been studied comprehensively. With the ever-increasing volume of research and applications of LLMs, we take a step back to evaluate the ability of current-generation LLMs to handle negation, a fundamental linguistic phenomenon that is central to language understanding. We evaluate different LLMs -- including the open-source GPT-neo, GPT-3, and InstructGPT -- against a wide range of negation benchmarks. Through systematic experimentation with varying model sizes and prompts, we show that LLMs have several limitations including insensitivity to the presence of negation, an inability to capture the lexical semantics of negation, and a failure to reason under negation.

Xudong Han, Aili Shen, Yitong Li et al.

This paper presents fairlib, an open-source framework for assessing and improving classification fairness. It provides a systematic framework for quickly reproducing existing baseline models, developing new methods, evaluating models with different metrics, and visualizing their results. Its modularity and extensibility enable the framework to be used for diverse types of inputs, including natural language, images, and audio. In detail, we implement 14 debiasing methods, including pre-processing, at-training-time, and post-processing approaches. The built-in metrics cover the most commonly used fairness criterion and can be further generalized and customized for fairness evaluation.

Thinh Hung Truong, Timothy Baldwin, Trevor Cohn et al.

Negation is a common linguistic feature that is crucial in many language understanding tasks, yet it remains a hard problem due to diversity in its expression in different types of text. Recent work has shown that state-of-the-art NLP models underperform on samples containing negation in various tasks, and that negation detection models do not transfer well across domains. We propose a new negation-focused pre-training strategy, involving targeted data augmentation and negation masking, to better incorporate negation information into language models. Extensive experiments on common benchmarks show that our proposed approach improves negation detection performance and generalizability over the strong baseline NegBERT (Khandewal and Sawant, 2020).

Thinh Hung Truong, Yulia Otmakhova, Timothy Baldwin et al.

Negation is poorly captured by current language models, although the extent of this problem is not widely understood. We introduce a natural language inference (NLI) test suite to enable probing the capabilities of NLP methods, with the aim of understanding sub-clausal negation. The test suite contains premise--hypothesis pairs where the premise contains sub-clausal negation and the hypothesis is constructed by making minimal modifications to the premise in order to reflect different possible interpretations. Aside from adopting standard NLI labels, our test suite is systematically constructed under a rigorous linguistic framework. It includes annotation of negation types and constructions grounded in linguistic theory, as well as the operations used to construct hypotheses. This facilitates fine-grained analysis of model performance. We conduct experiments using pre-trained language models to demonstrate that our test suite is more challenging than existing benchmarks focused on negation, and show how our annotation supports a deeper understanding of the current NLI capabilities in terms of negation and quantification.

Artem Vazhentsev, Lyudmila Rvanova, Gleb Kuzmin et al.

While large language models (LLMs) have become highly capable, they remain prone to factual inaccuracies, commonly referred to as "hallucinations." Uncertainty quantification (UQ) offers a promising way to mitigate this issue, but most existing methods are computationally intensive and/or require supervision. In this work, we propose Recurrent Attention-based Uncertainty Quantification (RAUQ), an unsupervised and efficient framework for identifying hallucinations. The method leverages an observation about transformer attention behavior: when incorrect information is generated, certain "uncertainty-aware" attention heads tend to reduce their focus on preceding tokens. RAUQ automatically detects these attention heads and combines their activation patterns with token-level confidence measures in a recurrent scheme, producing a sequence-level uncertainty estimate in just a single forward pass. Through experiments on twelve datasets spanning question answering, summarization, and translation across nine different LLMs, we show that RAUQ consistently outperforms state-of-the-art UQ baselines. Importantly, it incurs minimal overhead, requiring less than 1\% additional computation. Since it requires neither labeled data nor extensive parameter tuning, RAUQ serves as a lightweight, plug-and-play solution for real-time hallucination detection in white-box LLMs.

Yuxia Wang, Shimin Tao, Ning Xie et al.

Despite the subjective nature of semantic textual similarity (STS) and pervasive disagreements in STS annotation, existing benchmarks have used averaged human ratings as the gold standard. Averaging masks the true distribution of human opinions on examples of low agreement, and prevents models from capturing the semantic vagueness that the individual ratings represent. In this work, we introduce USTS, the first Uncertainty-aware STS dataset with ~15,000 Chinese sentence pairs and 150,000 labels, to study collective human opinions in STS. Analysis reveals that neither a scalar nor a single Gaussian fits a set of observed judgements adequately. We further show that current STS models cannot capture the variance caused by human disagreement on individual instances, but rather reflect the predictive confidence over the aggregate dataset.

Yulia Otmakhova, Hung Thinh Truong, Timothy Baldwin et al.

In this paper we report on our submission to the Multidocument Summarisation for Literature Review (MSLR) shared task. Specifically, we adapt PRIMERA (Xiao et al., 2022) to the biomedical domain by placing global attention on important biomedical entities in several ways. We analyse the outputs of the 23 resulting models, and report patterns in the results related to the presence of additional global attention, number of training steps, and the input configuration.

Xudong Han, Timothy Baldwin, Trevor Cohn

Adversarial training is a common approach for bias mitigation in natural language processing. Although most work on debiasing is motivated by equal opportunity, it is not explicitly captured in standard adversarial training. In this paper, we propose an augmented discriminator for adversarial training, which takes the target class as input to create richer features and more explicitly model equal opportunity. Experimental results over two datasets show that our method substantially improves over standard adversarial debiasing methods, in terms of the performance--fairness trade-off.

Xudong Han, Aili Shen, Trevor Cohn et al.

Mitigating bias in training on biased datasets is an important open problem. Several techniques have been proposed, however the typical evaluation regime is very limited, considering very narrow data conditions. For instance, the effect of target class imbalance and stereotyping is under-studied. To address this gap, we examine the performance of various debiasing methods across multiple tasks, spanning binary classification (Twitter sentiment), multi-class classification (profession prediction), and regression (valence prediction). Through extensive experimentation, we find that data conditions have a strong influence on relative model performance, and that general conclusions cannot be drawn about method efficacy when evaluating only on standard datasets, as is current practice in fairness research.

Gisela Vallejo, Timothy Baldwin, Lea Frermann

The manifestation and effect of bias in news reporting have been central topics in the social sciences for decades, and have received increasing attention in the NLP community recently. While NLP can help to scale up analyses or contribute automatic procedures to investigate the impact of biased news in society, we argue that methodologies that are currently dominant fall short of addressing the complex questions and effects addressed in theoretical media studies. In this survey paper, we review social science approaches and draw a comparison with typical task formulations, methods, and evaluation metrics used in the analysis of media bias in NLP. We discuss open questions and suggest possible directions to close identified gaps between theory and predictive models, and their evaluation. These include model transparency, considering document-external information, and cross-document reasoning rather than single-label assignment.

Gleb Kuzmin, Neemesh Yadav, Ivan Smirnov et al.

We propose selective debiasing -- an inference-time safety mechanism designed to enhance the overall model quality in terms of prediction performance and fairness, especially in scenarios where retraining the model is impractical. The method draws inspiration from selective classification, where at inference time, predictions with low quality, as indicated by their uncertainty scores, are discarded. In our approach, we identify the potentially biased model predictions and, instead of discarding them, we remove bias from these predictions using LEACE -- a post-processing debiasing method. To select problematic predictions, we propose a bias quantification approach based on KL divergence, which achieves better results than standard uncertainty quantification methods. Experiments on text classification datasets with encoder-based classification models demonstrate that selective debiasing helps to reduce the performance gap between post-processing methods and debiasing techniques from the at-training and pre-processing categories.

Masahiro Kaneko, Danushka Bollegala, Timothy Baldwin

Recent studies have demonstrated that large language models (LLMs) have ethical-related problems such as social biases, lack of moral reasoning, and generation of offensive content. The existing evaluation metrics and methods to address these ethical challenges use datasets intentionally created by instructing humans to create instances including ethical problems. Therefore, the data does not reflect prompts that users actually provide when utilizing LLM services in everyday contexts. This may not lead to the development of safe LLMs that can address ethical challenges arising in real-world applications. In this paper, we create Eagle datasets extracted from real interactions between ChatGPT and users that exhibit social biases, toxicity, and immoral problems. Our experiments show that Eagle captures complementary aspects, not covered by existing datasets proposed for evaluation and mitigation of such ethical challenges. Our code is publicly available at https://huggingface.co/datasets/MasahiroKaneko/eagle.

Sukmin Yun, Haokun Lin, Rusiru Thushara et al.

Multimodal large language models (MLLMs) have shown impressive success across modalities such as image, video, and audio in a variety of understanding and generation tasks. However, current MLLMs are surprisingly poor at understanding webpage screenshots and generating their corresponding HTML code. To address this problem, we propose $\texttt{Web2Code}$, a benchmark consisting of a new large-scale webpage-to-code dataset for instruction tuning and an evaluation framework for the webpage understanding and HTML code translation abilities of MLLMs. For dataset construction, we leverage pretrained LLMs to enhance existing webpage-to-code datasets as well as generate a diverse pool of new webpages rendered into images. Specifically, the inputs are webpage images and instructions, while the responses are the webpage's HTML code. We further include diverse natural language QA pairs about the webpage content in the responses to enable a more comprehensive understanding of the web content. To evaluate model performance in these tasks, we develop an evaluation framework for testing MLLMs' abilities in webpage understanding and web-to-code generation. Extensive experiments show that our proposed dataset is beneficial not only to our proposed tasks but also in the general visual domain. We hope our work will contribute to the development of general MLLMs suitable for web-based content generation and task automation. Our data and code are available at https://github.com/MBZUAI-LLM/web2code.

Haonan Li, Xudong Han, Zenan Zhai et al.

To address this gap, we introduce Libra-Leaderboard, a comprehensive framework designed to rank LLMs through a balanced evaluation of performance and safety. Combining a dynamic leaderboard with an interactive LLM arena, Libra-Leaderboard encourages the joint optimization of capability and safety. Unlike traditional approaches that average performance and safety metrics, Libra-Leaderboard uses a distance-to-optimal-score method to calculate the overall rankings. This approach incentivizes models to achieve a balance rather than excelling in one dimension at the expense of some other ones. In the first release, Libra-Leaderboard evaluates 26 mainstream LLMs from 14 leading organizations, identifying critical safety challenges even in state-of-the-art models.

Thinh Hung Truong, Yulia Otmakhova, Karin Verspoor et al.

In this work, we measure the impact of affixal negation on modern English large language models (LLMs). In affixal negation, the negated meaning is expressed through a negative morpheme, which is potentially challenging for LLMs as their tokenizers are often not morphologically plausible. We conduct extensive experiments using LLMs with different subword tokenization methods, which lead to several insights on the interaction between tokenization performance and negation sensitivity. Despite some interesting mismatches between tokenization accuracy and negation detection performance, we show that models can, on the whole, reliably recognize the meaning of affixal negation.

Maiya Goloburda, Nurkhan Laiyk, Diana Turmakhan et al.

Large language models (LLMs) are known to have the potential to generate harmful content, posing risks to users. While significant progress has been made in developing taxonomies for LLM risks and safety evaluation prompts, most studies have focused on monolingual contexts, primarily in English. However, language- and region-specific risks in bilingual contexts are often overlooked, and core findings can diverge from those in monolingual settings. In this paper, we introduce Qorgau, a novel dataset specifically designed for safety evaluation in Kazakh and Russian, reflecting the unique bilingual context in Kazakhstan, where both Kazakh (a low-resource language) and Russian (a high-resource language) are spoken. Experiments with both multilingual and language-specific LLMs reveal notable differences in safety performance, emphasizing the need for tailored, region-specific datasets to ensure the responsible and safe deployment of LLMs in countries like Kazakhstan. Warning: this paper contains example data that may be offensive, harmful, or biased.

Thinh Hung Truong, Karin Verspoor, Trevor Cohn et al.

Despite rapid adoption of autoregressive large language models, smaller text encoders still play an important role in text understanding tasks that require rich contextualized representations. Negation is an important semantic function that is still not properly captured by such methods, affecting many downstream applications relying on text embeddings. We propose a strategy to improve negation robustness of text encoders, by distilling data from large language models using diverse patterns of negation and hedging. We adopt a standard contrastive learning strategy to finetune a strong BERT-based model, and observe large improvement in negation understanding capabilities while maintaining competitive performance on general benchmarks. In addition, we also show that our method can be adapted to LLMs, leading to improved performance on negation benchmarks.

Thinh Hung Truong, Yulia Otmakhova, Rahmad Mahendra et al.

This paper describes the submissions of the Natural Language Processing (NLP) team from the Australian Research Council Industrial Transformation Training Centre (ITTC) for Cognitive Computing in Medical Technologies to the TREC 2021 Clinical Trials Track. The task focuses on the problem of matching eligible clinical trials to topics constituting a summary of a patient's admission notes. We explore different ways of representing trials and topics using NLP techniques, and then use a common retrieval model to generate the ranked list of relevant trials for each topic. The results from all our submitted runs are well above the median scores for all topics, but there is still plenty of scope for improvement.

Xudong Han, Timothy Baldwin, Trevor Cohn

Group bias in natural language processing tasks manifests as disparities in system error rates across texts authorized by different demographic groups, typically disadvantaging minority groups. Dataset balancing has been shown to be effective at mitigating bias, however existing approaches do not directly account for correlations between author demographics and linguistic variables, limiting their effectiveness. To achieve Equal Opportunity fairness, such as equal job opportunity without regard to demographics, this paper introduces a simple, but highly effective, objective for countering bias using balanced training. We extend the method in the form of a gated model, which incorporates protected attributes as input, and show that it is effective at reducing bias in predictions through demographic input perturbation, outperforming all other bias mitigation techniques when combined with balanced training.

Fajri Koto, Jey Han Lau, Timothy Baldwin

We present IndoBERTweet, the first large-scale pretrained model for Indonesian Twitter that is trained by extending a monolingually-trained Indonesian BERT model with additive domain-specific vocabulary. We focus in particular on efficient model adaptation under vocabulary mismatch, and benchmark different ways of initializing the BERT embedding layer for new word types. We find that initializing with the average BERT subword embedding makes pretraining five times faster, and is more effective than proposed methods for vocabulary adaptation in terms of extrinsic evaluation over seven Twitter-based datasets.

Simon Šuster, Karin Verspoor, Timothy Baldwin et al.

The COVID-19 pandemic has driven ever-greater demand for tools which enable efficient exploration of biomedical literature. Although semi-structured information resulting from concept recognition and detection of the defining elements of clinical trials (e.g. PICO criteria) has been commonly used to support literature search, the contributions of this abstraction remain poorly understood, especially in relation to text-based retrieval. In this study, we compare the results retrieved by a standard search engine with those filtered using clinically-relevant concepts and their relations. With analysis based on the annotations from the TREC-COVID shared task, we obtain quantitative as well as qualitative insights into characteristics of relational and concept-based literature exploration. Most importantly, we find that the relational concept selection filters the original retrieved collection in a way that decreases the proportion of unjudged documents and increases the precision, which means that the user is likely to be exposed to a larger number of relevant documents.

Karin Verspoor, Simon Šuster, Yulia Otmakhova et al.

We present COVID-SEE, a system for medical literature discovery based on the concept of information exploration, which builds on several distinct text analysis and natural language processing methods to structure and organise information in publications, and augments search by providing a visual overview supporting exploration of a collection to identify key articles of interest. We developed this system over COVID-19 literature to help medical professionals and researchers explore the literature evidence, and improve findability of relevant information. COVID-SEE is available at http://covid-see.com.

Nitika Mathur, Timothy Baldwin, Trevor Cohn

Automatic metrics are fundamental for the development and evaluation of machine translation systems. Judging whether, and to what extent, automatic metrics concur with the gold standard of human evaluation is not a straightforward problem. We show that current methods for judging metrics are highly sensitive to the translations used for assessment, particularly the presence of outliers, which often leads to falsely confident conclusions about a metric's efficacy. Finally, we turn to pairwise system ranking, developing a method for thresholding performance improvement under an automatic metric against human judgements, which allows quantification of type I versus type II errors incurred, i.e., insignificant human differences in system quality that are accepted, and significant human differences that are rejected. Together, these findings suggest improvements to the protocols for metric evaluation and system performance evaluation in machine translation.

Preslav Nakov, Lluís Màrquez, Alessandro Moschitti et al.

This paper describes the SemEval--2016 Task 3 on Community Question Answering, which we offered in English and Arabic. For English, we had three subtasks: Question--Comment Similarity (subtask A), Question--Question Similarity (B), and Question--External Comment Similarity (C). For Arabic, we had another subtask: Rerank the correct answers for a new question (D). Eighteen teams participated in the task, submitting a total of 95 runs (38 primary and 57 contrastive) for the four subtasks. A variety of approaches and features were used by the participating systems to address the different subtasks, which are summarized in this paper. The best systems achieved an official score (MAP) of 79.19, 76.70, 55.41, and 45.83 in subtasks A, B, C, and D, respectively. These scores are significantly better than those for the baselines that we provided. For subtask A, the best system improved over the 2015 winner by 3 points absolute in terms of Accuracy.

Preslav Nakov, Doris Hoogeveen, Lluís Màrquez et al.

We describe SemEval-2017 Task 3 on Community Question Answering. This year, we reran the four subtasks from SemEval-2016:(A) Question-Comment Similarity,(B) Question-Question Similarity,(C) Question-External Comment Similarity, and (D) Rerank the correct answers for a new question in Arabic, providing all the data from 2015 and 2016 for training, and fresh data for testing. Additionally, we added a new subtask E in order to enable experimentation with Multi-domain Question Duplicate Detection in a larger-scale scenario, using StackExchange subforums. A total of 23 teams participated in the task, and submitted a total of 85 runs (36 primary and 49 contrastive) for subtasks A-D. Unfortunately, no teams participated in subtask E. A variety of approaches and features were used by the participating systems to address the different subtasks. The best systems achieved an official score (MAP) of 88.43, 47.22, 15.46, and 61.16 in subtasks A, B, C, and D, respectively. These scores are better than the baselines, especially for subtasks A-C.

Shivashankar Subramanian, Trevor Cohn, Timothy Baldwin

Many pledges are made in the course of an election campaign, forming important corpora for political analysis of campaign strategy and governmental accountability. At present, there are no publicly available annotated datasets of pledges, and most political analyses rely on manual analysis. In this paper we collate a novel dataset of manifestos from eleven Australian federal election cycles, with over 12,000 sentences annotated with specificity (e.g., rhetorical vs.\ detailed pledge) on a fine-grained scale. We propose deep ordinal regression approaches for specificity prediction, under both supervised and semi-supervised settings, and provide empirical results demonstrating the effectiveness of the proposed techniques over several baseline approaches. We analyze the utility of pledge specificity modeling across a spectrum of policy issues in performing ideology prediction, and further provide qualitative analysis in terms of capturing party-specific issue salience across election cycles.

Yitong Li, Timothy Baldwin, Trevor Cohn

Supervised models of NLP rely on large collections of text which closely resemble the intended testing setting. Unfortunately matching text is often not available in sufficient quantity, and moreover, within any domain of text, data is often highly heterogenous. In this paper we propose a method to distill the important domain signal as part of a multi-domain learning system, using a latent variable model in which parts of a neural model are stochastically gated based on the inferred domain. We compare the use of discrete versus continuous latent variables, operating in a domain-supervised or a domain semi-supervised setting, where the domain is known only for a subset of training inputs. We show that our model leads to substantial performance improvements over competitive benchmark domain adaptation methods, including methods using adversarial learning.

Shivashankar Subramanian, Trevor Cohn, Timothy Baldwin

Election manifestos document the intentions, motives, and views of political parties. They are often used for analysing a party's fine-grained position on a particular issue, as well as for coarse-grained positioning of a party on the left--right spectrum. In this paper we propose a two-stage model for automatically performing both levels of analysis over manifestos. In the first step we employ a hierarchical multi-task structured deep model to predict fine- and coarse-grained positions, and in the second step we perform post-hoc calibration of coarse-grained positions using probabilistic soft logic. We empirically show that the proposed model outperforms state-of-art approaches at both granularities using manifestos from twelve countries, written in ten different languages.

Afshin Rahimi, Trevor Cohn, Timothy Baldwin

Social media user geolocation is vital to many applications such as event detection. In this paper, we propose GCN, a multiview geolocation model based on Graph Convolutional Networks, that uses both text and network context. We compare GCN to the state-of-the-art, and to two baselines we propose, and show that our model achieves or is competitive with the state- of-the-art over three benchmark geolocation datasets when sufficient supervision is available. We also evaluate GCN under a minimal supervision scenario, and show it outperforms baselines. We find that highway network gates are essential for controlling the amount of useful neighbourhood expansion in GCN.

Fei Liu, Timothy Baldwin, Trevor Cohn

Despite successful applications across a broad range of NLP tasks, conditional random fields ("CRFs"), in particular the linear-chain variant, are only able to model local features. While this has important benefits in terms of inference tractability, it limits the ability of the model to capture long-range dependencies between items. Attempts to extend CRFs to capture long-range dependencies have largely come at the cost of computational complexity and approximate inference. In this work, we propose an extension to CRFs by integrating external memory, taking inspiration from memory networks, thereby allowing CRFs to incorporate information far beyond neighbouring steps. Experiments across two tasks show substantial improvements over strong CRF and LSTM baselines.

Afshin Rahimi, Trevor Cohn, Timothy Baldwin

We propose a label propagation approach to geolocation prediction based on Modified Adsorption, with two enhancements:(1) the removal of "celebrity" nodes to increase location homophily and boost tractability, and (2) he incorporation of text-based geolocation priors for test users. Experiments over three Twitter benchmark datasets achieve state-of-the-art results, and demonstrate the effectiveness of the enhancements.