Chenghua Lin

Ruibin Yuan, Yinghao Ma, Yizhi Li et al. · deepmind, mila

In the era of extensive intersection between art and Artificial Intelligence (AI), such as image generation and fiction co-creation, AI for music remains relatively nascent, particularly in music understanding. This is evident in the limited work on deep music representations, the scarcity of large-scale datasets, and the absence of a universal and community-driven benchmark. To address this issue, we introduce the Music Audio Representation Benchmark for universaL Evaluation, termed MARBLE. It aims to provide a benchmark for various Music Information Retrieval (MIR) tasks by defining a comprehensive taxonomy with four hierarchy levels, including acoustic, performance, score, and high-level description. We then establish a unified protocol based on 14 tasks on 8 public-available datasets, providing a fair and standard assessment of representations of all open-sourced pre-trained models developed on music recordings as baselines. Besides, MARBLE offers an easy-to-use, extendable, and reproducible suite for the community, with a clear statement on copyright issues on datasets. Results suggest recently proposed large-scale pre-trained musical language models perform the best in most tasks, with room for further improvement. The leaderboard and toolkit repository are published at https://marble-bm.shef.ac.uk to promote future music AI research.

Yizhi Li, Ruibin Yuan, Ge Zhang et al. · deepmind

The deep learning community has witnessed an exponentially growing interest in self-supervised learning (SSL). However, it still remains unexplored how to build a framework for learning useful representations of raw music waveforms in a self-supervised manner. In this work, we design Music2Vec, a framework exploring different SSL algorithmic components and tricks for music audio recordings. Our model achieves comparable results to the state-of-the-art (SOTA) music SSL model Jukebox, despite being significantly smaller with less than 2% of parameters of the latter. The model will be released on Huggingface(Please refer to: https://huggingface.co/m-a-p/music2vec-v1)

Ge Zhang, Yemin Shi, Ruibo Liu et al. · deepmind

Instruction tuning is widely recognized as a key technique for building generalist language models, which has attracted the attention of researchers and the public with the release of InstructGPT~\citep{ouyang2022training} and ChatGPT\footnote{\url{https://chat.openai.com/}}. Despite impressive progress in English-oriented large-scale language models (LLMs), it is still under-explored whether English-based foundation LLMs can perform similarly on multilingual tasks compared to English tasks with well-designed instruction tuning and how we can construct the corpora needed for the tuning. To remedy this gap, we propose the project as an attempt to create a Chinese instruction dataset by various methods adapted to the intrinsic characteristics of 4 sub-tasks. We collect around 200k Chinese instruction tuning samples, which have been manually checked to guarantee high quality. We also summarize the existing English and Chinese instruction corpora and briefly describe some potential applications of the newly constructed Chinese instruction corpora. The resulting \textbf{C}hinese \textbf{O}pen \textbf{I}nstruction \textbf{G}eneralist (\textbf{COIG}) corpora are available in Huggingface\footnote{\url{https://huggingface.co/datasets/BAAI/COIG}} and Github\footnote{\url{https://github.com/BAAI-Zlab/COIG}}, and will be continuously updated.

Shun Wang, Yucheng Li, Chenghua Lin et al. · meta-ai

We propose a novel RoBERTa-based model, RoPPT, which introduces a target-oriented parse tree structure in metaphor detection. Compared to existing models, RoPPT focuses on semantically relevant information and achieves the state-of-the-art on several main metaphor datasets. We also compare our approach against several popular denoising and pruning methods, demonstrating the effectiveness of our approach in context denoising. Our code and dataset can be found at https://github.com/MajiBear000/RoPPT

Bohao Yang, Chen Tang, Kun Zhao et al.

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing tasks. However, their enormous parameter size and extremely high requirements for compute power pose challenges for their practical deployment. Recent research has revealed that specific capabilities of LLMs, such as numerical reasoning, can be transferred to smaller models through distillation. Some studies explore the potential of leveraging LLMs to perform table-based reasoning. However, there has been no prior work focusing on table reasoning skills in smaller models specifically tailored for scientific table-to-text generation tasks. In this paper, we propose a novel table-based reasoning distillation approach, with the aim of distilling LLMs into tailored smaller models. Our experimental results have shown that a 220 million parameter model (Flan-T5-base) fine-tuned using distilled data, not only achieves a significant improvement compared to traditionally fine-tuned baselines, but also surpasses specific LLMs on a scientific table-to-text generation dataset. Our code is available at https://github.com/Bernard-Yang/DistillTableCoT.

Yizhi Li, Ge Zhang, Bohao Yang et al. · mila

Fairness has become a trending topic in natural language processing (NLP), which addresses biases targeting certain social groups such as genders and religions. However, regional bias in language models (LMs), a long-standing global discrimination problem, still remains unexplored. This paper bridges the gap by analysing the regional bias learned by the pre-trained language models that are broadly used in NLP tasks. In addition to verifying the existence of regional bias in LMs, we find that the biases on regional groups can be strongly influenced by the geographical clustering of the groups. We accordingly propose a HiErarchical Regional Bias evaluation method (HERB) utilising the information from the sub-region clusters to quantify the bias in pre-trained LMs. Experiments show that our hierarchical metric can effectively evaluate the regional bias with respect to comprehensive topics and measure the potential regional bias that can be propagated to downstream tasks. Our codes are available at https://github.com/Bernard-Yang/HERB.

Yizhi Li, Yinghao Ma, Ge Zhang et al.

Recent advancements in multimodal large language models (MLLMs) have aimed to integrate and interpret data across diverse modalities. However, the capacity of these models to concurrently process and reason about multiple modalities remains underexplored, partly due to the lack of comprehensive modality-wise benchmarks. We introduce OmniBench, a novel benchmark designed to rigorously evaluate models' ability to recognize, interpret, and reason across visual, acoustic, and textual inputs simultaneously. We define language models capable of such tri-modal processing as the omni-language models (OLMs). OmniBench is distinguished by high-quality human annotations, ensuring that accurate responses require integrated understanding and reasoning across all three modalities. Our main findings reveal that: i) open-source OLMs exhibit critical limitations in instruction-following and reasoning capabilities within tri-modal contexts; and ii) most baselines models perform poorly (below 50% accuracy) even when provided with alternative textual representations of images or/and audio. These results suggest that the ability to construct a consistent context from text, image, and audio is often overlooked in existing MLLM training paradigms. To address this gap, we curate an instruction tuning dataset of 84.5K training samples, OmniInstruct, for training OLMs to adapt to tri-modal contexts. We advocate for future research to focus on developing more robust tri-modal integration techniques and training strategies to enhance OLMs. Codes, data and live leaderboard could be found at https://m-a-p.ai/OmniBench.

Yucheng Li, Shun Wang, Chenghua Lin et al. · meta-ai

In this paper, we propose FrameBERT, a RoBERTa-based model that can explicitly learn and incorporate FrameNet Embeddings for concept-level metaphor detection. FrameBERT not only achieves better or comparable performance to the state-of-the-art, but also is more explainable and interpretable compared to existing models, attributing to its ability of accounting for external knowledge of FrameNet.

Yinghao Ma, Ruibin Yuan, Yizhi Li et al. · deepmind, mila

Self-supervised learning (SSL) has shown promising results in various speech and natural language processing applications. However, its efficacy in music information retrieval (MIR) still remains largely unexplored. While previous SSL models pre-trained on music recordings may have been mostly closed-sourced, recent speech models such as wav2vec2.0 have shown promise in music modelling. Nevertheless, research exploring the effectiveness of applying speech SSL models to music recordings has been limited. We explore the music adaption of SSL with two distinctive speech-related models, data2vec1.0 and Hubert, and refer to them as music2vec and musicHuBERT, respectively. We train $12$ SSL models with 95M parameters under various pre-training configurations and systematically evaluate the MIR task performances with 13 different MIR tasks. Our findings suggest that training with music data can generally improve performance on MIR tasks, even when models are trained using paradigms designed for speech. However, we identify the limitations of such existing speech-oriented designs, especially in modelling polyphonic information. Based on the experimental results, empirical suggestions are also given for designing future musical SSL strategies and paradigms.

Chen Tang, Hongbo Zhang, Tyler Loakman et al.

Incorporating external graph knowledge into neural chatbot models has been proven effective for enhancing dialogue generation. However, in conventional graph neural networks (GNNs), message passing on a graph is independent from text, resulting in the graph representation hidden space differing from that of the text. This training regime of existing models therefore leads to a semantic gap between graph knowledge and text. In this study, we propose a novel framework for knowledge graph enhanced dialogue generation. We dynamically construct a multi-hop knowledge graph with pseudo nodes to involve the language model in feature aggregation within the graph at all steps. To avoid the semantic biases caused by learning on vanilla subgraphs, the proposed framework applies hierarchical graph attention to aggregate graph features on pseudo nodes and then attains a global feature. Therefore, the framework can better utilise the heterogeneous features from both the post and external graph knowledge. Extensive experiments demonstrate that our framework outperforms state-of-the-art (SOTA) baselines on dialogue generation. Further analysis also shows that our representation learning framework can fill the semantic gap by coagulating representations of both text and graph knowledge. Moreover, the language model also learns how to better select knowledge triples for a more informative response via exploiting subgraph patterns within our feature aggregation process. Our code and resources are available at https://github.com/tangg555/SaBART.

Chen Tang, Hongbo Zhang, Tyler Loakman et al.

Medical dialogue generation aims to generate responses according to a history of dialogue turns between doctors and patients. Unlike open-domain dialogue generation, this requires background knowledge specific to the medical domain. Existing generative frameworks for medical dialogue generation fall short of incorporating domain-specific knowledge, especially with regard to medical terminology. In this paper, we propose a novel framework to improve medical dialogue generation by considering features centered on domain-specific terminology. We leverage an attention mechanism to incorporate terminologically centred features, and fill in the semantic gap between medical background knowledge and common utterances by enforcing language models to learn terminology representations with an auxiliary terminology recognition task. Experimental results demonstrate the effectiveness of our approach, in which our proposed framework outperforms SOTA language models. Additionally, we provide a new dataset with medical terminology annotations to support the research on medical dialogue generation. Our dataset and code are available at https://github.com/tangg555/meddialog.

Manar Abouzaid, Yang Wang, Chenghua Lin et al.

Large Language Models (LLMs) are vulnerable both to hallucination and adversarial manipulation. Although these problems are closely related, existing defences typically address them separately. We investigate a hybrid defence framework that combines entropy-based models, designed to reduce hallucinations, with uncertainty-based models and geometric-based models, designed to reduce vulnerability. Under in-domain tests on Natural Language Understanding datasets (FEVER, HotpotQA, CSQA, SIQA) we find our hybrid model improves both clean-task performance (up to 43.34\% increase in accuracy) and adversarial robustness (up to 64.92\% improvement in accuracy and 62.27\% reduction in attack success rate). For out-of-distribution datasets (AeroEngQA, CPIQA) we see similar adversarial robustness from our hybrid model (up to 57.14\% improvement in accuracy). For prompt injection (SafeGuard) and jailbreak detection (AdvBench, DAN) datasets our hybrid model is also very strong (up to 51\% reduction in attack success rate compared to state of the art baseline models). Overall, our results show that combining entropy, uncertainty and geometric features provides a more effective defence strategy than using any single feature alone for both in-domain and out-of-distribution tasks.

Le Zhuo, Ruibin Yuan, Jiahao Pan et al. · mila

We introduce LyricWhiz, a robust, multilingual, and zero-shot automatic lyrics transcription method achieving state-of-the-art performance on various lyrics transcription datasets, even in challenging genres such as rock and metal. Our novel, training-free approach utilizes Whisper, a weakly supervised robust speech recognition model, and GPT-4, today's most performant chat-based large language model. In the proposed method, Whisper functions as the "ear" by transcribing the audio, while GPT-4 serves as the "brain," acting as an annotator with a strong performance for contextualized output selection and correction. Our experiments show that LyricWhiz significantly reduces Word Error Rate compared to existing methods in English and can effectively transcribe lyrics across multiple languages. Furthermore, we use LyricWhiz to create the first publicly available, large-scale, multilingual lyrics transcription dataset with a CC-BY-NC-SA copyright license, based on MTG-Jamendo, and offer a human-annotated subset for noise level estimation and evaluation. We anticipate that our proposed method and dataset will advance the development of multilingual lyrics transcription, a challenging and emerging task.

Yizhi Li, Wei Fan, Chao Liu et al.

Knowledge graph embedding methods are important for the knowledge graph completion (or link prediction) task. One existing efficient method, PairRE, leverages two separate vectors to model complex relations (i.e., 1-to-N, N-to-1, and N-to-N) in knowledge graphs. However, such a method strictly restricts entities on the hyper-ellipsoid surfaces which limits the optimization of entity distribution, leading to suboptimal performance of knowledge graph completion. To address this issue, we propose a novel score function TranSHER, which leverages relation-specific translations between head and tail entities to relax the constraint of hyper-ellipsoid restrictions. By introducing an intuitive and simple relation-specific translation, TranSHER can provide more direct guidance on optimization and capture more semantic characteristics of entities with complex relations. Experimental results show that TranSHER achieves significant performance improvements on link prediction and generalizes well to datasets in different domains and scales. Our codes are public available at https://github.com/yizhilll/TranSHER.

Yucheng Li, Frank Guerin, Chenghua Lin

Data contamination in model evaluation has become increasingly prevalent with the growing popularity of large language models. It allows models to "cheat" via memorisation instead of displaying true capabilities. Therefore, contamination analysis has become an crucial part of reliable model evaluation to validate results. However, existing contamination analysis is usually conducted internally by large language model developers and often lacks transparency and completeness. This paper presents an extensive data contamination report for over 15 popular large language models across six popular multiple-choice QA benchmarks. We also introduce an open-source pipeline that enables the community to perform contamination analysis on customised data and models. Our experiments reveal varying contamination levels ranging from 1\% to 45\% across benchmarks, with the contamination degree increasing rapidly over time. Performance analysis of large language models indicates that data contamination does not necessarily lead to increased model metrics: while significant accuracy boosts of up to 14\% and 7\% are observed on contaminated C-Eval and Hellaswag benchmarks, only a minimal increase is noted on contaminated MMLU. We also find larger models seem able to gain more advantages than smaller models on contaminated test sets.

Jian Yang, Wei Zhang, Jiajun Wu et al.

Recent code large language models have achieved remarkable progress on general programming tasks. Nevertheless, their performance degrades significantly in industrial scenarios that require reasoning about hardware semantics, specialized language constructs, and strict resource constraints. To address these challenges, we introduce InCoder-32B (Industrial-Coder-32B), the first 32B-parameter code foundation model unifying code intelligence across chip design, GPU kernel optimization, embedded systems, compiler optimization, and 3D modeling. By adopting an efficient architecture, we train InCoder-32B from scratch with general code pre-training, curated industrial code annealing, mid-training that progressively extends context from 8K to 128K tokens with synthetic industrial reasoning data, and post-training with execution-grounded verification. We conduct extensive evaluation on 14 mainstream general code benchmarks and 9 industrial benchmarks spanning 4 specialized domains. Results show InCoder-32B achieves highly competitive performance on general tasks while establishing strong open-source baselines across industrial domains.

King Zhu, Qianbo Zang, Shian Jia et al.

Multimodal Large Language Models (MLLMs) are evaluated on various benchmarks, such as image captioning, visual question answering, and reasoning. However, many of these benchmarks include overly simple or uninformative samples, complicating the effective distinction of different MLLMs' performance. Furthermore, evaluating models across numerous benchmarks incurs a significant computational burden. To address these issues, we propose LIME (Less Is More for MLLM Evaluation), a refined and efficient benchmark curated through a semi-automated pipeline. This pipeline filters out uninformative samples and eliminates answer leakage by focusing on tasks that necessitate image-based understanding. Our experiments indicate that LIME reduces the number of samples by 76% and evaluation time by 77%, while also providing a more effective means of distinguishing the capabilities of different models. Notably, we find that traditional automatic metrics, such as CIDEr, are inadequate for assessing MLLMs' captioning performance; excluding the caption task score yields a more accurate reflection of overall model performance. All code and data are available at https://github.com/kangreen0210/LIME.

Ge Zhang, Yizhi Li, Yaoyao Wu et al. · mila

As natural language processing (NLP) for gender bias becomes a significant interdisciplinary topic, the prevalent data-driven techniques such as large-scale language models suffer from data inadequacy and biased corpus, especially for languages with insufficient resources such as Chinese. To this end, we propose a Chinese cOrpus foR Gender bIas Probing and Mitigation CORGI-PM, which contains 32.9k sentences with high-quality labels derived by following an annotation scheme specifically developed for gender bias in the Chinese context. Moreover, we address three challenges for automatic textual gender bias mitigation, which requires the models to detect, classify, and mitigate textual gender bias. We also conduct experiments with state-of-the-art language models to provide baselines. To our best knowledge, CORGI-PM is the first sentence-level Chinese corpus for gender bias probing and mitigation.

Tomas Goldsack, Zheheng Luo, Qianqian Xie et al.

This paper presents the results of the shared task on Lay Summarisation of Biomedical Research Articles (BioLaySumm), hosted at the BioNLP Workshop at ACL 2023. The goal of this shared task is to develop abstractive summarisation models capable of generating "lay summaries" (i.e., summaries that are comprehensible to non-technical audiences) in both a controllable and non-controllable setting. There are two subtasks: 1) Lay Summarisation, where the goal is for participants to build models for lay summary generation only, given the full article text and the corresponding abstract as input; and 2) Readability-controlled Summarisation, where the goal is for participants to train models to generate both the technical abstract and the lay summary, given an article's main text as input. In addition to overall results, we report on the setup and insights from the BioLaySumm shared task, which attracted a total of 20 participating teams across both subtasks.

Bohao Yang, Chen Tang, Chenghua Lin

Medical Dialogue Generation serves a critical role in telemedicine by facilitating the dissemination of medical expertise to patients. Existing studies focus on incorporating textual representations, which have limited their ability to represent the semantics of text, such as ignoring important medical entities. To enhance the model's understanding of the textual semantics and the medical knowledge including entities and relations, we introduce the use of Abstract Meaning Representations (AMR) to construct graphical representations that delineate the roles of language constituents and medical entities within the dialogues. In this paper, We propose a novel framework that models dialogues between patients and healthcare professionals using AMR graphs, where the neural networks incorporate textual and graphical knowledge with a dual attention mechanism. Experimental results show that our framework outperforms strong baseline models in medical dialogue generation, demonstrating the effectiveness of AMR graphs in enhancing the representations of medical knowledge and logical relationships. Furthermore, to support future research in this domain, we provide the corresponding source code at https://github.com/Bernard-Yang/MedDiaAMR.

Yinghao Ma, Anders Øland, Anton Ragni et al.

In recent years, foundation models (FMs) such as large language models (LLMs) and latent diffusion models (LDMs) have profoundly impacted diverse sectors, including music. This comprehensive review examines state-of-the-art (SOTA) pre-trained models and foundation models in music, spanning from representation learning, generative learning and multimodal learning. We first contextualise the significance of music in various industries and trace the evolution of AI in music. By delineating the modalities targeted by foundation models, we discover many of the music representations are underexplored in FM development. Then, emphasis is placed on the lack of versatility of previous methods on diverse music applications, along with the potential of FMs in music understanding, generation and medical application. By comprehensively exploring the details of the model pre-training paradigm, architectural choices, tokenisation, finetuning methodologies and controllability, we emphasise the important topics that should have been well explored, like instruction tuning and in-context learning, scaling law and emergent ability, as well as long-sequence modelling etc. A dedicated section presents insights into music agents, accompanied by a thorough analysis of datasets and evaluations essential for pre-training and downstream tasks. Finally, by underscoring the vital importance of ethical considerations, we advocate that following research on FM for music should focus more on such issues as interpretability, transparency, human responsibility, and copyright issues. The paper offers insights into future challenges and trends on FMs for music, aiming to shape the trajectory of human-AI collaboration in the music realm.

Tomas Goldsack, Zhihao Zhang, Chenghua Lin et al.

Lay summarisation aims to jointly summarise and simplify a given text, thus making its content more comprehensible to non-experts. Automatic approaches for lay summarisation can provide significant value in broadening access to scientific literature, enabling a greater degree of both interdisciplinary knowledge sharing and public understanding when it comes to research findings. However, current corpora for this task are limited in their size and scope, hindering the development of broadly applicable data-driven approaches. Aiming to rectify these issues, we present two novel lay summarisation datasets, PLOS (large-scale) and eLife (medium-scale), each of which contains biomedical journal articles alongside expert-written lay summaries. We provide a thorough characterisation of our lay summaries, highlighting differing levels of readability and abstractiveness between datasets that can be leveraged to support the needs of different applications. Finally, we benchmark our datasets using mainstream summarisation approaches and perform a manual evaluation with domain experts, demonstrating their utility and casting light on the key challenges of this task.

Owen Millwood, Jack Miskelly, Bohao Yang et al.

As the demand for highly secure and dependable lightweight systems increases in the modern world, Physically Unclonable Functions (PUFs) continue to promise a lightweight alternative to high-cost encryption techniques and secure key storage. While the security features promised by PUFs are highly attractive for secure system designers, they have been shown to be vulnerable to various sophisticated attacks - most notably Machine Learning (ML) based modelling attacks (ML-MA) which attempt to digitally clone the PUF behaviour and thus undermine their security. More recent ML-MA have even exploited publicly known helper data required for PUF error correction in order to predict PUF responses without requiring knowledge of response data. In response to this, research is beginning to emerge regarding the authentication of PUF devices with the assistance of ML as opposed to traditional PUF techniques of storage and comparison of pre-known Challenge-Response pairs (CRPs). In this article, we propose a classification system using ML based on a novel `PUF-Phenotype' concept to accurately identify the origin and determine the validity of noisy memory derived (DRAM) PUF responses as an alternative to helper data-reliant denoising techniques. To our best knowledge, we are the first to perform classification over multiple devices per model to enable a group-based PUF authentication scheme. We achieve up to 98\% classification accuracy using a modified deep convolutional neural network (CNN) for feature extraction in conjunction with several well-established classifiers. We also experimentally verified the performance of our model on a Raspberry Pi device to determine the suitability of deploying our proposed model in a resource-constrained environment.

Yucheng Li, Bo Dong, Chenghua Lin et al.

Large language models (LLMs) achieved remarkable performance across various tasks. However, they face challenges in managing long documents and extended conversations, due to significantly increased computational requirements, both in memory and inference time, and potential context truncation when the input exceeds the LLM's fixed context length. This paper proposes a method called Selective Context that enhances the inference efficiency of LLMs by identifying and pruning redundancy in the input context to make the input more compact. We test our approach using common data sources requiring long context processing: arXiv papers, news articles, and long conversations, on tasks of summarisation, question answering, and response generation. Experimental results show that Selective Context significantly reduces memory cost and decreases generation latency while maintaining comparable performance compared to that achieved when full context is used. Specifically, we achieve a 50\% reduction in context cost, resulting in a 36\% reduction in inference memory usage and a 32\% reduction in inference time, while observing only a minor drop of .023 in BERTscore and .038 in faithfulness on four downstream applications, indicating that our method strikes a good balance between efficiency and performance.

Shekoufeh Kolahdouz-Rahimi, Kevin Lano, Chenghua Lin

Improvement of software development methodologies attracts developers to automatic Requirement Formalisation (RF) in the Requirement Engineering (RE) field. The potential advantages by applying Natural Language Processing (NLP) and Machine Learning (ML) in reducing the ambiguity and incompleteness of requirement written in natural languages is reported in different studies. The goal of this paper is to survey and classify existing work on NLP and ML for RF, identifying challenges in this domain and providing promising future research directions. To achieve this, we conducted a systematic literature review to outline the current state-of-the-art of NLP and ML techniques in RF by selecting 257 papers from common used libraries. The search result is filtered by defining inclusion and exclusion criteria and 47 relevant studies between 2012 and 2022 are selected. We found that heuristic NLP approaches are the most common NLP techniques used for automatic RF, primary operating on structured and semi-structured data. This study also revealed that Deep Learning (DL) technique are not widely used, instead classical ML techniques are predominant in the surveyed studies. More importantly, we identified the difficulty of comparing the performance of different approaches due to the lack of standard benchmark cases for RF.

Yiqi Liu, Nafise Sadat Moosavi, Chenghua Lin

Automatic evaluation of generated textual content presents an ongoing challenge within the field of NLP. Given the impressive capabilities of modern language models (LMs) across diverse NLP tasks, there is a growing trend to employ these models in creating innovative evaluation metrics for automated assessment of generation tasks. This paper investigates a pivotal question: Do language model-driven evaluation metrics inherently exhibit bias favoring texts generated by the same underlying language model? Specifically, we assess whether prominent LM-based evaluation metrics (e.g. BARTScore, T5Score, and GPTScore) demonstrate a favorable bias toward their respective underlying LMs in the context of summarization tasks. Our findings unveil a latent bias, particularly pronounced when such evaluation metrics are used in a reference-free manner without leveraging gold summaries. These results underscore that assessments provided by generative evaluation models can be influenced by factors beyond the inherent text quality, highlighting the necessity of developing more reliable evaluation protocols in the future.

Tyler Loakman, Chen Tang, Chenghua Lin

Previous work in phonetically-grounded language generation has mainly focused on domains such as lyrics and poetry. In this paper, we present work on the generation of tongue twisters - a form of language that is required to be phonetically conditioned to maximise sound overlap, whilst maintaining semantic consistency with an input topic, and still being grammatically correct. We present \textbf{TwistList}, a large annotated dataset of tongue twisters, consisting of 2.1K+ human-authored examples. We additionally present several benchmark systems (referred to as TwisterMisters) for the proposed task of tongue twister generation, including models that both do and do not require training on in-domain data. We present the results of automatic and human evaluation to demonstrate the performance of existing mainstream pre-trained models in this task with limited (or no) task specific training and data, and no explicit phonetic knowledge. We find that the task of tongue twister generation is challenging for models under these conditions, yet some models are still capable of generating acceptable examples of this language type.

Chen Tang, Chenghua Lin, Henglin Huang et al.

One of the key challenges of automatic story generation is how to generate a long narrative that can maintain fluency, relevance, and coherence. Despite recent progress, current story generation systems still face the challenge of how to effectively capture contextual and event features, which has a profound impact on a model's generation performance. To address these challenges, we present EtriCA, a novel neural generation model, which improves the relevance and coherence of the generated stories through residually mapping context features to event sequences with a cross-attention mechanism. Such a feature capturing mechanism allows our model to better exploit the logical relatedness between events when generating stories. Extensive experiments based on both automatic and human evaluations show that our model significantly outperforms state-of-the-art baselines, demonstrating the effectiveness of our model in leveraging context and event features.

Chen Tang, Frank Guerin, Chenghua Lin

In recent years, considerable research has been dedicated to the application of neural models in the field of natural language generation (NLG). The primary objective is to generate text that is both linguistically natural and human-like, while also exerting control over the generation process. This paper offers a comprehensive and task-agnostic survey of the recent advancements in neural text generation. These advancements have been facilitated through a multitude of developments, which we categorize into four key areas: data construction, neural frameworks, training and inference strategies, and evaluation metrics. By examining these different aspects, we aim to provide a holistic overview of the progress made in the field. Furthermore, we explore the future directions for the advancement of neural text generation, which encompass the utilization of neural pipelines and the incorporation of background knowledge. These avenues present promising opportunities to further enhance the capabilities of NLG systems. Overall, this survey serves to consolidate the current state of the art in neural text generation and highlights potential avenues for future research and development in this dynamic field.

Chen Tang, Zhihao Zhang, Tyler Loakman et al.

To improve the performance of long text generation, recent studies have leveraged automatically planned event structures (i.e. storylines) to guide story generation. Such prior works mostly employ end-to-end neural generation models to predict event sequences for a story. However, such generation models struggle to guarantee the narrative coherence of separate events due to the hallucination problem, and additionally the generated event sequences are often hard to control due to the end-to-end nature of the models. To address these challenges, we propose NGEP, an novel event planning framework which generates an event sequence by performing inference on an automatically constructed event graph and enhances generalisation ability through a neural event advisor. We conduct a range of experiments on multiple criteria, and the results demonstrate that our graph-based neural framework outperforms the state-of-the-art (SOTA) event planning approaches, considering both the performance of event sequence generation and the effectiveness on the downstream task of story generation.

Henglin Huang, Chen Tang, Tyler Loakman et al.

Story generation aims to generate a long narrative conditioned on a given input. In spite of the success of prior works with the application of pre-trained models, current neural models for Chinese stories still struggle to generate high-quality long text narratives. We hypothesise that this stems from ambiguity in syntactically parsing the Chinese language, which does not have explicit delimiters for word segmentation. Consequently, neural models suffer from the inefficient capturing of features in Chinese narratives. In this paper, we present a new generation framework that enhances the feature capturing mechanism by informing the generation model of dependencies between words and additionally augmenting the semantic representation learning through synonym denoising training. We conduct a range of experiments, and the results demonstrate that our framework outperforms the state-of-the-art Chinese generation models on all evaluation metrics, demonstrating the benefits of enhanced dependency and semantic representation learning.

Yucheng Li, Chenghua Lin, Frank Geurin

Metaphor generation is a challenging task which can impact many downstream tasks such as improving user satisfaction with dialogue systems and story generation. This paper tackles the problem of Chinese nominal metaphor generation by introducing a multitask metaphor generation framework with self-training and metaphor identification mechanisms. Self-training addresses the data scarcity issue of metaphor datasets. That is, instead of solely relying on labelled metaphor datasets which are usually small in size, self-training helps identify potential metaphors from a large-scale unlabelled corpus for metaphor generation. The metaphor weighting mechanism enables our model to focus on the metaphor-related parts of the input (e.g., the comparison of the metaphor and comparator) during model learning and thus improves the metaphoricity of the generated metaphors. Our model is trained on an annotated corpus consisting of 6.3k sentences that contain diverse metaphorical expressions. Experimental results show that our model is able to generate metaphors with better readability and creativity compared to the baseline models, even in the situation where training data is insufficient.

Yiming Liang, Ge Zhang, Xingwei Qu et al.

Large Language Models (LLMs) have achieved significant advancements, however, the common learning paradigm treats LLMs as passive information repositories, neglecting their potential for active learning and alignment. Some approaches train LLMs using their own generated synthetic data, exploring the possibility of active alignment. However, there is still a huge gap between these one-time alignment methods and the continuous automatic alignment of humans. In this paper, we introduce \textbf{I-SHEEP}, an \textbf{I}terative \textbf{S}elf-En\textbf{H}anc\textbf{E}m\textbf{E}nt \textbf{P}aradigm.This human-like paradigm enables LLMs to \textbf{continuously self-align from scratch with nothing}. Compared to the one-time alignment method Dromedary \cite{sun2023principledriven}, which refers to the first iteration in this paper, I-SHEEP can significantly enhance capacities on both Qwen and Llama models. I-SHEEP achieves a maximum relative improvement of 78.2\% in the Alpaca Eval, 24.0\% in the MT Bench, and an absolute increase of 8.88\% in the IFEval accuracy over subsequent iterations in Qwen-1.5 72B model. Additionally, I-SHEEP surpasses the base model in various standard benchmark generation tasks, achieving an average improvement of 24.77\% in code generation tasks, 12.04\% in TrivialQA, and 20.29\% in SQuAD. We also provide new insights based on the experiment results. Our codes, datasets, and models are available at \textbf{https://anonymous.4open.science/r/I-SHEEP}.

Jianfei Zhang, Jun Bai, Chenghua Lin et al.

Variational autoencoders (VAEs) are one of the powerful unsupervised learning frameworks in NLP for latent representation learning and latent-directed generation. The classic optimization goal of VAEs is to maximize the Evidence Lower Bound (ELBo), which consists of a conditional likelihood for generation and a negative Kullback-Leibler (KL) divergence for regularization. In practice, optimizing ELBo often leads the posterior distribution of all samples converge to the same degenerated local optimum, namely posterior collapse or KL vanishing. There are effective ways proposed to prevent posterior collapse in VAEs, but we observe that they in essence make trade-offs between posterior collapse and hole problem, i.e., mismatch between the aggregated posterior distribution and the prior distribution. To this end, we introduce new training objectives to tackle both two problems through a novel regularization based on the probabilistic density gap between the aggregated posterior distribution and the prior distribution. Through experiments on language modeling, latent space visualization and interpolation, we show that our proposed method can solve both problems effectively and thus outperforms the existing methods in latent-directed generation. To the best of our knowledge, we are the first to jointly solve the hole problem and the posterior collapse.

Yucheng Li, Frank Guerin, Chenghua Lin

Metaphors are proven to have stronger emotional impact than literal expressions. Although this conclusion is shown to be promising in benefiting various NLP applications, the reasons behind this phenomenon are not well studied. This paper conducts the first study in exploring how metaphors convey stronger emotion than their literal counterparts. We find that metaphors are generally more specific than literal expressions. The more specific property of metaphor can be one of the reasons for metaphors' superiority in emotion expression. When we compare metaphors with literal expressions with the same specificity level, the gap of emotion expressing ability between both reduces significantly. In addition, we observe specificity is crucial in literal language as well, as literal language can express stronger emotion by making it more specific.

Hanhua Hong, Yizhi LI, Jiaoyan Chen et al.

Recent advances in large language models have highlighted their potential to automate computational research, particularly reproducing experimental results. However, existing approaches still use fixed sequential agent pipelines with weak global coordination, which limits their robustness and overall performance. In this work, we propose Hierarchical Research Agent System (HiRAS), a hierarchical multi-agent framework for end-to-end experiment reproduction that employs supervisory manager agents to coordinate specialised agents across fine-grained stages. We also identify limitations in the reference-free evaluation of the Paper2Code benchmark and introduce Paper2Code-Extra (P2C-Ex), a refined protocol that incorporates repository-level information and better aligns with the original reference-based metric. We conduct extensive evaluation, validating the effectiveness and robustness of our proposed methods, and observing improvements, including >10\% relative performance gain beyond the previous state-of-the-art using open-source backbone models and significantly reduced hallucination in evaluation. Our work is available on GitHub: https://github.com/KOU-199024/HiRAS.

Tomas Goldsack, Carolina Scarton, Matthew Shardlow et al.

This paper presents the setup and results of the second edition of the BioLaySumm shared task on the Lay Summarisation of Biomedical Research Articles, hosted at the BioNLP Workshop at ACL 2024. In this task edition, we aim to build on the first edition's success by further increasing research interest in this important task and encouraging participants to explore novel approaches that will help advance the state-of-the-art. Encouragingly, we found research interest in the task to be high, with this edition of the task attracting a total of 53 participating teams, a significant increase in engagement from the previous edition. Overall, our results show that a broad range of innovative approaches were adopted by task participants, with a predictable shift towards the use of Large Language Models (LLMs).

Siwei Wu, Kang Zhu, Yu Bai et al.

Given the remarkable success that large visual language models (LVLMs) have achieved in image perception tasks, the endeavor to make LVLMs perceive the world like humans is drawing increasing attention. Current multi-modal benchmarks primarily focus on facts or specific topic-related knowledge contained within individual images. However, they often overlook the associative relations between multiple images, which require the identification and analysis of similarities among entities or content present in different images. Therefore, we propose the multi-image relation association task and a meticulously curated Multi-granularity Multi-image Relational Association (MMRA) benchmark, comprising 1,024 samples. In order to systematically and comprehensively evaluate current LVLMs, we establish an associational relation system among images that contain 11 subtasks (e.g, UsageSimilarity, SubEvent) at two granularity levels (i.e., image and entity) according to the relations in ConceptNet. Our experiments reveal that on the MMRA benchmark, current multi-image LVLMs exhibit distinct advantages and disadvantages across various subtasks. Notably, fine-grained, entity-level multi-image perception tasks pose a greater challenge for LVLMs compared to image-level tasks. Moreover, LVLMs perform poorly on spatial-related tasks, indicating that LVLMs still have limited spatial awareness. Additionally, our findings indicate that while LVLMs demonstrate a strong capability to perceive image details, enhancing their ability to associate information across multiple images hinges on improving the reasoning capabilities of their language model component. Moreover, we explored the ability of LVLMs to perceive image sequences within the context of our multi-image association task. Our experiments show that the majority of current LVLMs do not adequately model image sequences during the pre-training process.

Chenghao Xiao, Yizhi Li, G Thomas Hudson et al.

In recent years, contrastive learning (CL) has been extensively utilized to recover sentence and document-level encoding capability from pre-trained language models. In this work, we question the length generalizability of CL-based models, i.e., their vulnerability towards length-induced semantic shift. We verify not only that length vulnerability is a significant yet overlooked research gap, but we can devise unsupervised CL methods solely depending on the semantic signal provided by document length. We first derive the theoretical foundations underlying length attacks, showing that elongating a document would intensify the high intra-document similarity that is already brought by CL. Moreover, we found that isotropy promised by CL is highly dependent on the length range of text exposed in training. Inspired by these findings, we introduce a simple yet universal document representation learning framework, LA(SER)$^{3}$: length-agnostic self-reference for semantically robust sentence representation learning, achieving state-of-the-art unsupervised performance on the standard information retrieval benchmark.

Xingwei Qu, Ge Zhang, Siwei Wu et al.

This paper presents the results of the shared task on Chinese metaphor generation, hosted at the 13th CCF Conference on Natural Language Processing and Chinese Computing (NLPCC 2024). The goal of this shared task is to generate Chinese metaphors using machine learning techniques and effectively identifying basic components of metaphorical sentences. It is divided into two subtasks: 1) Metaphor Generation, which involves creating a metaphor from a provided tuple consisting of TENOR, GROUND, and VEHICLE. The goal here is to synthesize a metaphor that connects the subject (i.e. TENOR) with the object (i.e. VEHICLE), guided by the concept of the GROUND. 2) Metaphor Components Identification, which extracts the most fitting TENORs, GROUNDs, and VEHICLEs from a metaphorical sentence. This component requires the identification of the most fitting metaphor elements that correspond to the specified grounds. In addition to overall results, we report on the setup and insights from the metaphor generation shared task, which attracted a total of 4 participating teams across both subtasks.

Tomas Goldsack, Zhihao Zhang, Chen Tang et al.

Previous approaches for automatic lay summarisation are exclusively reliant on the source article that, given it is written for a technical audience (e.g., researchers), is unlikely to explicitly define all technical concepts or state all of the background information that is relevant for a lay audience. We address this issue by augmenting eLife, an existing biomedical lay summarisation dataset, with article-specific knowledge graphs, each containing detailed information on relevant biomedical concepts. Using both automatic and human evaluations, we systematically investigate the effectiveness of three different approaches for incorporating knowledge graphs within lay summarisation models, with each method targeting a distinct area of the encoder-decoder model architecture. Our results confirm that integrating graph-based domain knowledge can significantly benefit lay summarisation by substantially increasing the readability of generated text and improving the explanation of technical concepts.

Ruibin Yuan, Hanfeng Lin, Yi Wang et al.

While Large Language Models (LLMs) demonstrate impressive capabilities in text generation, we find that their ability has yet to be generalized to music, humanity's creative language. We introduce ChatMusician, an open-source LLM that integrates intrinsic musical abilities. It is based on continual pre-training and finetuning LLaMA2 on a text-compatible music representation, ABC notation, and the music is treated as a second language. ChatMusician can understand and generate music with a pure text tokenizer without any external multi-modal neural structures or tokenizers. Interestingly, endowing musical abilities does not harm language abilities, even achieving a slightly higher MMLU score. Our model is capable of composing well-structured, full-length music, conditioned on texts, chords, melodies, motifs, musical forms, etc, surpassing GPT-4 baseline. On our meticulously curated college-level music understanding benchmark, MusicTheoryBench, ChatMusician surpasses LLaMA2 and GPT-3.5 on zero-shot setting by a noticeable margin. Our work reveals that LLMs can be an excellent compressor for music, but there remains significant territory to be conquered. We release our 4B token music-language corpora MusicPile, the collected MusicTheoryBench, code, model and demo in GitHub.

Abdullah Alabdullah, Lifeng Han, Chenghua Lin

Dialectal Arabic to Modern Standard Arabic (DA-MSA) translation is a challenging task in Machine Translation (MT) due to significant lexical, syntactic, and semantic divergences between Arabic dialects and MSA. Existing automatic evaluation metrics and general-purpose human evaluation frameworks struggle to capture dialect-specific MT errors, hindering progress in translation assessment. This paper introduces Ara-HOPE, a human-centric post-editing evaluation framework designed to systematically address these challenges. The framework includes a five-category error taxonomy and a decision-tree annotation protocol. Through comparative evaluation of three MT systems (Arabic-centric Jais, general-purpose GPT-3.5, and baseline NLLB-200), Ara-HOPE effectively highlights systematic performance differences between these systems. Our results show that dialect-specific terminology and semantic preservation remain the most persistent challenges in DA-MSA translation. Ara-HOPE establishes a new framework for evaluating Dialectal Arabic MT quality and provides actionable guidance for improving dialect-aware MT systems. For reproducibility, we make the annotation files and related materials publicly available at https://github.com/abdullahalabdullah/Ara-HOPE

Noor Fazilla Abd Yusof, Chenghua Lin

Despite the importance of emphasizing the right psychotherapy treatment for an individual patient, assessing the outcome of the therapy session is equally crucial. Evidence showed that continuous monitoring patient's progress can significantly improve the therapy outcomes to an expected change. By monitoring the outcome, the patient's progress can be tracked closely to help clinicians identify patients who are not progressing in the treatment. These monitoring can help the clinician to consider any necessary actions for the patient's treatment as early as possible, e.g., recommend different types of treatment, or adjust the style of approach. Currently, the evaluation system is based on the clinical-rated and self-report questionnaires that measure patients' progress pre- and post-treatment. While outcome monitoring tends to improve the therapy outcomes, however, there are many challenges in the current method, e.g. time and financial burden for administering questionnaires, scoring and analysing the results. Therefore, a computational method for measuring and monitoring patient progress over the course of treatment is needed, in order to enhance the likelihood of positive treatment outcome. Moreover, this computational method could potentially lead to an inexpensive monitoring tool to evaluate patients' progress in clinical care that could be administered by a wider range of health-care professionals.

Yang Wang, Qibin Liang, Chenghao Xiao et al.

Standard fine-tuning of pre-trained audio models couples representation learning with classifier training, which can obscure the true quality of the learned representations. In this work, we advocate for a disentangled two-stage framework that separates representation refinement from downstream evaluation. First, we employ a "contrastive-tuning" stage to explicitly improve the geometric structure of the model's embedding space. Subsequently, we introduce a dual-probe evaluation protocol to assess the quality of these refined representations from a geometric perspective. This protocol uses a linear probe to measure global linear separability and a k-Nearest Neighbours probe to investigate the local structure of class clusters. Our experiments on a diverse set of audio classification tasks show that our framework provides a better foundation for classification, leading to improved accuracy. Our newly proposed dual-probing framework acts as a powerful analytical lens, demonstrating why contrastive learning is more effective by revealing a superior embedding space. It significantly outperforms vanilla fine-tuning, particularly on single-label datasets with a large number of classes, and also surpasses strong baselines on multi-label tasks using a Jaccard-weighted loss. Our findings demonstrate that decoupling representation refinement from classifier training is a broadly effective strategy for unlocking the full potential of pre-trained audio models. Our code will be publicly available.

Yuelin Bai, Xinrun Du, Yiming Liang et al.

Remarkable progress on English instruction tuning has facilitated the efficacy and reliability of large language models (LLMs). However, there remains a noticeable gap in instruction tuning for Chinese, where the complex linguistic features pose significant challenges. Existing datasets, generally distilled from English-centric LLMs, are not well-aligned with Chinese users' interaction patterns. To bridge this gap, we introduce COIG-CQIA, a new Chinese instruction tuning dataset derived from various real-world resources and undergoing rigorous human verification. We conduct extensive experiments on COIG-CQIA, and compare them with strong baseline models and datasets. The experimental results show that models trained on COIG-CQIA achieve highly competitive performance in diverse benchmarks. Additionally, our findings offer several insights for designing effective Chinese instruction-tuning datasets and data-mixing strategies. Our dataset are available at https://huggingface.co/datasets/m-a-p/COIG-CQIA.

Chen Tang, Shun Wang, Tomas Goldsack et al.

Abstracts derived from biomedical literature possess distinct domain-specific characteristics, including specialised writing styles and biomedical terminologies, which necessitate a deep understanding of the related literature. As a result, existing language models struggle to generate technical summaries that are on par with those produced by biomedical experts, given the absence of domain-specific background knowledge. This paper aims to enhance the performance of language models in biomedical abstractive summarisation by aggregating knowledge from external papers cited within the source article. We propose a novel attention-based citation aggregation model that integrates domain-specific knowledge from citation papers, allowing neural networks to generate summaries by leveraging both the paper content and relevant knowledge from citation papers. Furthermore, we construct and release a large-scale biomedical summarisation dataset that serves as a foundation for our research. Extensive experiments demonstrate that our model outperforms state-of-the-art approaches and achieves substantial improvements in abstractive biomedical text summarisation.

Yucheng Li, Frank Guerin, Chenghua Lin

Data contamination in evaluation is getting increasingly prevalent with the emergence of language models pre-trained on super large, automatically crawled corpora. This problem leads to significant challenges in the accurate assessment of model capabilities and generalisations. In this paper, we propose LatestEval, an automatic method that leverages the most recent texts to create uncontaminated reading comprehension evaluations. LatestEval avoids data contamination by only using texts published within a recent time window, ensuring no overlap with the training corpora of pre-trained language models. We develop the LatestEval automated pipeline to 1) gather the latest texts; 2) identify key information, and 3) construct questions targeting the information while removing the existing answers from the context. This encourages models to infer the answers themselves based on the remaining context, rather than just copy-paste. Our experiments demonstrate that language models exhibit negligible memorisation behaviours on LatestEval as opposed to previous benchmarks, suggesting a significantly reduced risk of data contamination and leading to a more robust evaluation. Data and code are publicly available at: https://github.com/liyucheng09/LatestEval.

Ge Zhang, Xinrun Du, Bei Chen et al.

As the capabilities of large multimodal models (LMMs) continue to advance, evaluating the performance of LMMs emerges as an increasing need. Additionally, there is an even larger gap in evaluating the advanced knowledge and reasoning abilities of LMMs in non-English contexts such as Chinese. We introduce CMMMU, a new Chinese Massive Multi-discipline Multimodal Understanding benchmark designed to evaluate LMMs on tasks demanding college-level subject knowledge and deliberate reasoning in a Chinese context. CMMMU is inspired by and strictly follows the annotation and analysis pattern of MMMU. CMMMU includes 12k manually collected multimodal questions from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering, like its companion, MMMU. These questions span 30 subjects and comprise 39 highly heterogeneous image types, such as charts, diagrams, maps, tables, music sheets, and chemical structures. CMMMU focuses on complex perception and reasoning with domain-specific knowledge in the Chinese context. We evaluate 11 open-source LLMs and one proprietary GPT-4V(ision). Even GPT-4V only achieves accuracies of 42%, indicating a large space for improvement. CMMMU will boost the community to build the next-generation LMMs towards expert artificial intelligence and promote the democratization of LMMs by providing diverse language contexts.

Tyler Loakman, Aaron Maladry, Chenghua Lin

Human evaluation is often considered to be the gold standard method of evaluating a Natural Language Generation system. However, whilst its importance is accepted by the community at large, the quality of its execution is often brought into question. In this position paper, we argue that the generation of more esoteric forms of language - humour, irony and sarcasm - constitutes a subdomain where the characteristics of selected evaluator panels are of utmost importance, and every effort should be made to report demographic characteristics wherever possible, in the interest of transparency and replicability. We support these claims with an overview of each language form and an analysis of examples in terms of how their interpretation is affected by different participant variables. We additionally perform a critical survey of recent works in NLG to assess how well evaluation procedures are reported in this subdomain, and note a severe lack of open reporting of evaluator demographic information, and a significant reliance on crowdsourcing platforms for recruitment.