ACL 2024 论文列表

The present level of proliferation of fake, biased, and propagandistic content online has made it impossible to fact-check every single suspicious claim or article, either manually or automatically. An increasing number of scholars are focusing on a coarser granularity, aiming to profile entire news outlets, which allows fast identification of potential “fake news” by checking the reliability of their source. Source factuality is also an important element of systems for automatic fact-checking and “fake news” detection, as they need to assess the reliability of the evidence they retrieve online. Political bias detection, which in the Western political landscape is about predicting left-center-right bias, is an equally important topic, which has experienced a similar shift toward profiling entire news outlets. Moreover, there is a clear connection between the two, as highly biased media are less likely to be factual; yet, the two problems have been addressed separately. In this survey, we review the state of the art on media profiling for factuality and bias, arguing for the need to model them jointly. We also shed light on some of the major challenges for modeling bias and factuality jointly. We further discuss interesting recent advances in using different information sources and modalities, which go beyond the text of the articles the target news outlet has published. Finally, we discuss current challenges and outline future research directions.

In this survey, we provide a systematic review of recent work on modelling morality in text, an area of research that has garnered increasing attention in recent years. Our survey is motivated by the importance of modelling decisions on the created resources, the models trained on these resources and the analyses that result from the models’ predictions. We review work at the interface of NLP, Computational Social Science and Psychology and give an overview of the different goals and research questions addressed in the papers, their underlying theoretical backgrounds and the methods that have been applied to pursue these goals. We then identify and discuss challenges and research gaps, such as the lack of a theoretical framework underlying the operationalisation of morality in text, the low IAA reported for manyhuman-annotated resulting resources and the lack of validation of newly proposed resources and analyses.

We show that content on the web is often translated into many languages, and the low quality of these multi-way translations indicates they were likely created using Machine Translation (MT). Multi-way parallel, machine generated content not only dominates the translations in lower resource languages; it also constitutes a large fraction of the total web content in those languages. We also find evidence of a selection bias in the type of content which is translated into many languages, consistent with low quality English content being translated en masse into many lower resource languages, via MT. Our work raises serious concerns about training models such as multilingual large language models on both monolingual and bilingual data scraped from the web.

In the realm of text manipulation and linguistic transformation, the question of authorship has been a subject of fascination and philosophical inquiry. Much like the Ship of Theseus paradox, which ponders whether a ship remains the same when each of its original planks is replaced, our research delves into an intriguing question: Does a text retain its original authorship when it undergoes numerous paraphrasing iterations? Specifically, since Large Language Models (LLMs) have demonstrated remarkable proficiency in both the generation of original content and the modification of human-authored texts, a pivotal question emerges concerning the determination of authorship in instances where LLMs or similar paraphrasing tools are employed to rephrase the text–i.e., whether authorship should be attributed to the original human author or the AI-powered tool. Therefore, we embark on a philosophical voyage through the seas of language and authorship to unravel this intricate puzzle. Using a computational approach, we discover that the diminishing performance in text classification models, with each successive paraphrasing iteration, is closely associated with the extent of deviation from the original author’s style, thus provoking a reconsideration of the current notion of authorship.

Modern natural language generation systems with Large Language Models (LLMs) exhibit the capability to generate a plausible summary of multiple documents; however, it is uncertain if they truly possess the capability of information consolidation to generate summaries, especially on documents with opinionated information. We focus on meta-review generation, a form of sentiment summarisation for the scientific domain. To make scientific sentiment summarization more grounded, we hypothesize that human meta-reviewers follow a three-layer framework of sentiment consolidation to write meta-reviews. Based on the framework, we propose novel prompting methods for LLMs to generate meta-reviews and evaluation metrics to assess the quality of generated meta-reviews. Our framework is validated empirically as we find that prompting LLMs based on the framework — compared with prompting them with simple instructions — generates better meta-reviews.

Detecting temporal semantic changes of words is an important task for various NLP applications that must make time-sensitive predictions.Lexical Semantic Change Detection (SCD) task involves predicting whether a given target word, w, changes its meaning between two different text corpora, C1 and C2.For this purpose, we propose a supervised two-staged SCD method that uses existing Word-in-Context (WiC) datasets.In the first stage, for a target word w, we learn two sense-aware encoders that represent the meaning of w in a given sentence selected from a corpus.Next, in the second stage, we learn a sense-aware distance metric that compares the semantic representations of a target word across all of its occurrences in C1 and C2.Experimental results on multiple benchmark datasets for SCD show that our proposed method achieves strong performance in multiple languages.Additionally, our method achieves significant improvements on WiC benchmarks compared to a sense-aware encoder with conventional distance functions.

Natural language inference (NLI), the task of recognizing the entailment relationship in sentence pairs, is an actively studied topic serving as a proxy for natural language understanding. Despite the relevance of the task in building conversational agents and improving text classification, machine translation and other NLP tasks, to the best of our knowledge, there is no publicly available NLI corpus for the Romanian language. To this end, we introduce the first Romanian NLI corpus (RoNLI) comprising 58K training sentence pairs, which are obtained via distant supervision, and 6K validation and test sentence pairs, which are manually annotated with the correct labels. We conduct experiments with multiple machine learning methods based on distant learning, ranging from shallow models based on word embeddings to transformer-based neural networks, to establish a set of competitive baselines. Furthermore, we improve on the best model by employing a new curriculum learning strategy based on data cartography. Our dataset and code to reproduce the baselines are available at https://github.com/Eduard6421/RONLI.

Simultaneous translation models play a crucial role in facilitating communication. However, existing research primarily focuses on text-to-text or speech-to-text models, necessitating additional cascade components to achieve speech-to-speech translation. These pipeline methods suffer from error propagation and accumulate delays in each cascade component, resulting in reduced synchronization between the speaker and listener. To overcome these challenges, we propose a novel non-autoregressive generation framework for simultaneous speech translation (NAST-S2x), which integrates speech-to-text and speech-to-speech tasks into a unified end-to-end framework.We develop a non-autoregressive decoder capable of concurrently generating multiple text or acoustic unit tokens upon receiving fixed-length speech chunks. The decoder can generate blank or repeated tokens and employ CTC decoding to dynamically adjust its latency. Experimental results show that NAST-S2x outperforms state-of-the-art models in both speech-to-text and speech-to-speech tasks. It achieves high-quality simultaneous interpretation within a delay of less than 3 seconds and provides a 28× decoding speedup in offline generation.

Historical linguists have identified multiple forms of lexical semantic change. We present a three-dimensional framework for integrating these forms and a unified computational methodology for evaluating them concurrently. The dimensions represent increases or decreases in semantic 1) sentiment (valence of a target word’s collocates), 2) intensity (emotional arousal of collocates or the frequency of intensifiers), and 3) breadth (diversity of contexts in which the target word appears). These dimensions can be complemented by evaluation of shifts in the frequency of the target words and the thematic content of its collocates. This framework enables lexical semantic change to be mapped economically and systematically and has applications in computational social science. We present an illustrative analysis of semantic shifts in mental health and mental illness in two corpora, demonstrating patterns of semantic change that illuminate contemporary concerns about pathologization, stigma, and concept creep.

LLMs confront inherent limitations in terms of its knowledge, memory, and action. The retrieval augmentation stands as a vital mechanism to address these limitations, which brings in useful information from external sources to augment the LLM. However, existing retrieval methods encounter two pressing issues. On one hand, the general retrievers are not properly optimized for retrieval augmentation hence exhibit limited effectiveness; on the other hand, the task-specific retrievers excel in the targeted retrieval augmentation scenario, while lack the versatility to handle diverse scenarios. In this work, we propose LLM-Embedder for the unified support of diverse retrieval augmentation scenarios. Our method presents three technical contributions. Firstly, we introduce a new reward formulation, namely rank-aware reward. It exploits the ranking position of the desired output among N sampled outputs from the LLM, which leads to fine-grained and robust computation of reward from the LLM’s feedback. Secondly, we design a novel distillation objective, called graded distillation. It incorporates both the absolute value and the relative order of the reward for more sufficient utilization of the LLM’s feedback. Thirdly, we systematically optimize the multi-task learning, which effectively unifies the multiple retrieval functionalities into one model. In our experiment, LLM-Embedder substantially improves the LLM’s performances in various downstream tasks, while introducing superior retrieval augmentation’s effect over both general and task-specifc retrievers. Our data, code, and model have been released at https://github.com/FlagOpen/FlagEmbedding.

In this paper we address the task of summarizing television shows, which touches key areas in AI research: complex reasoning, multiple modalities, and long narratives. We present a modular approach where separate components perform specialized sub-tasks which we argue affords greater flexibility compared to end-to-end methods. Our modules involve detecting scene boundaries, reordering scenes so as to minimize the number of cuts between different events, converting visual information to text, summarizing the dialogue in each scene, and fusing the scene summaries into a final summary for the entire episode. We also present a new metric, PRISMA (**P**recision and **R**ecall Evaluat**i**on of **s**ummary F**a**cts), to measure both precision and recall of generated summaries, which we decompose into atomic facts. Tested on the recently released SummScreen3D dataset (Papalampidi & Lapata, 2023), our method produces higher quality summaries than comparison models, as measured with ROUGE and our new fact-based metric.

The Transformer architecture has become prominent in developing large causal language models. However, mechanisms to explain its capabilities are not well understood. Focused on the training process, here we establish a meta-learning view of the Transformer architecture when trained for the causal language modeling task, by explicating an inner optimization process that may happen within the Transformer. Further, from within the inner optimization, we discover and theoretically analyze a special characteristic of the norms of learned token representations within Transformer-based causal language models. Our analysis is supported by experiments conducted on pre-trained large language models and real-world data.

Transformers demonstrate impressive performance on a range of reasoning benchmarks. To evaluate the degree to which these abilities are a result of actual reasoning, existing work has focused on developing sophisticated benchmarks for behavioral studies. However, these studies do not provide insights into the internal mechanisms driving the observed capabilities. To improve our understanding of the internal mechanisms of transformers, we present a comprehensive mechanistic analysis of a transformer trained on a synthetic reasoning task. We identify a set of interpretable mechanisms the model uses to solve the task, and validate our findings using correlational and causal evidence. Our results suggest that it implements a depth-bounded recurrent mechanisms that operates in parallel and stores intermediate results in selected token positions. We anticipate that the motifs we identified in our synthetic setting can provide valuable insights into the broader operating principles of transformers and thus provide a basis for understanding more complex models.

Mitigating the generation of contradictory responses poses a substantial challenge in dialogue response generation. The quality and quantity of available contradictory response data play a vital role in suppressing these contradictions, offering two significant benefits. First, having access to large contradiction data enables a comprehensive examination of their characteristics. Second, data-driven methods to mitigate contradictions may be enhanced with large-scale contradiction data for training. Nevertheless, no attempt has been made to build an extensive collection of model-generated contradictory responses. In this paper, we build a large dataset of response generation models’ contradictions for the first time. Then, we acquire valuable insights into the characteristics of model-generated contradictions through an extensive analysis of the collected responses. Lastly, we also demonstrate how this dataset substantially enhances the performance of data-driven contradiction suppression methods.

Most existing work on aspect-based sentiment analysis (ABSA) focuses on the sentence level, while research at the document level has not received enough attention. Compared to sentence-level ABSA, the document-level ABSA is not only more practical but also requires holistic document-level understanding capabilities such as coreference resolution. To investigate the impact of coreference information on document-level ABSA, we conduct a three-stage research for the document-level target sentiment analysis (DTSA) task: 1) exploring the effectiveness of coreference information for the DTSA task; 2) reducing the reliance on manually annotated coreference information; 3) alleviating the evaluation bias caused by missing the coreference information of opinion targets. Specifically, we first manually annotate the coreferential opinion targets and propose a multi-task learning framework to jointly model the DTSA task and the coreference resolution task. Then we annotate the coreference information with ChatGPT for joint training. Finally, to address the issue of missing coreference targets, we modify the metrics from strict matching to a loose matching method based on the clusters of targets. The experimental results not only demonstrate the effectiveness of our framework but also reflect the feasibility of using ChatGPT-annotated coreferential entities and the applicability of the modified metrics. Our source code is publicly released at https://github.com/NUSTM/DTSA-Coref.

Despite LLMs’ recent advancements, they still suffer from factual inconsistency and hallucination. An often-opted remedy is retrieval-augmented generation – however, there is no guarantee that the model will strictly adhere to retrieved grounding. Fundamentally, LLMs need to be aligned to be more faithful to grounding, which will require high-quality preference annotations. This paper investigates whether we can create high-quality grounded preference data for model alignment without using annotations from humans or large proprietary models. We experimented with existing entailment data and proposed approaches to generate synthetic grounded preference data, with which we train a Grounded Preference Model(GPM). We demonstrate through Proximal Policy Optimization(PPO) training of Mistral-7B-Instruct that our GPM model can successfully align powerful LLMs to generate much better grounded responses as judged by GPT4. Moreover, we show that our GPM is also a great faithfulness classifier, achieving SoTA in dialogue sub-tasks of the TRUE faithfulness Benchmark. We will release our GPM under the Apache 2.0 license.

Reasoning about subjective natural language descriptions, such as opinions and preferences, is a challenging topic that largely remains unsolved to date. In particular, state-of-the-art large language models (LLMs) perform disappointingly in this task, show strong biases, and do not meet the interpretability requirements often needed in these kinds of applications. We propose a novel approach for reasoning about subjective knowledge that integrates potential and implicit meanings and explicitly models the relational nature of the information. We apply supervised graph learning, offer explanations for the model’s reasoning, and show that our model performs well across all 15 topics of OpinionQA, outperforming several prominent LLMs. Our detailed analysis further shows its unique advantages and the complementary nature it offers in comparison to LLMs.

Large language models (LLMs) have an impressive ability to draw on novel information supplied in their context. Yet the mechanisms underlying this contextual grounding remain unknown, especially in situations where contextual information contradicts factual knowledge stored in the parameters, which LLMs also excel at recalling. Favoring the contextual information is critical for retrieval-augmented generation methods, which enrich the context with up-to-date information, hoping that grounding can rectify outdated or noisy stored knowledge. We present a novel method to study grounding abilities using Fakepedia, a novel dataset of counterfactual texts constructed to clash with a model’s internal parametric knowledge. In this study, we introduce Fakepedia, a counterfactual dataset designed to evaluate grounding abilities when the internal parametric knowledge clashes with the contextual information. We benchmark various LLMs with Fakepedia and conduct a causal mediation analysis of LLM components when answering Fakepedia queries, based on our Masked Grouped Causal Tracing (MGCT) method. Through this analysis, we identify distinct computational patterns between grounded and ungrounded responses. We finally demonstrate that distinguishing grounded from ungrounded responses is achievable through computational analysis alone. Our results, together with existing findings about factual recall mechanisms, provide a coherent narrative of how grounding and factual recall mechanisms interact within LLMs.

Large language models are first pre-trained on trillions of tokens and then instruction-tuned or aligned to specific preferences. While pre-training remains out of reach for most researchers due to the compute required, fine-tuning has become affordable thanks to parameter-efficient methods such as LoRA and QLoRA. Alignment is known to be sensitive to the many factors involved, including the quantity and quality of data, the alignment method, and the adapter rank. However, there has not yet been an extensive study of their effect on downstream performance. To address this gap, we conduct an in-depth investigation of the impact of popular choices for three crucial axes: (i) the alignment dataset (HH-RLHF and BeaverTails), (ii) the alignment technique (SFT and DPO), and (iii) the model (LLaMA-1, Vicuna-v1.3, Mistral-7b, and Mistral-7b-Instruct). Our extensive setup spanning over 300 experiments reveals consistent trends and unexpected findings. We observe how more informative data helps with preference alignment, cases where supervised fine-tuning outperforms preference optimization, and how aligning to a distinct preference boosts performance on downstream tasks. Through our in-depth analyses, we put forward key guidelines to help researchers perform more effective parameter-efficient LLM alignment.