论文检索

Andreas Waldis, Yufang Hou, Iryna Gurevych

The advent of pre-trained Language Models (LMs) has markedly advanced natural language processing, but their efficacy in out-of-distribution (OOD) scenarios remains a significant challenge. Computational argumentation (CA), modeling human argumentation processes, is a field notably impacted by these challenges because complex annotation schemes and high annotation costs naturally lead to resources barely covering the multiplicity of available text sources and topics. Due to this data scarcity, generalization to data from uncovered covariant distributions is a common challenge for CA tasks like stance detection or argument classification. This work systematically assesses LMs’ capabilities for such OOD scenarios. While previous work targets specific OOD types like topic shifts or OOD uniformly, we address three prevalent OOD scenarios in CA: topic shift, domain shift, and language shift. Our findings challenge the previously asserted general superiority of in-context learning (ICL) for OOD. We find that the efficacy of such learning paradigms varies with the type of OOD. Specifically, while ICL excels for domain shifts, prompt-based fine-tuning surpasses for topic shifts. To sum up, we navigate the heterogeneity of OOD scenarios in CA and empirically underscore the potential of base-sized LMs in overcoming these challenges.

Junhao Zheng, Shengjie Qiu, Qianli Ma

Incremental Learning (IL) has been a long-standing problem in both vision and Natural Language Processing (NLP) communities.In recent years, as Pre-trained Language Models (PLMs) have achieved remarkable progress in various NLP downstream tasks, utilizing PLMs as backbones has become a common practice in recent research of IL in NLP.Most assume that catastrophic forgetting is the biggest obstacle to achieving superior IL performance and propose various techniques to overcome this issue.However, we find that this assumption is problematic.Specifically, we revisit more than 20 methods on four classification tasks (Text Classification, Intent Classification, Relation Extraction, and Named Entity Recognition) under the two most popular IL settings (Class-Incremental and Task-Incremental) and reveal that most of them severely underestimate the inherent anti-forgetting ability of PLMs.Based on the observation, we propose a frustratingly easy method called SEQ* for IL with PLMs.The results show that SEQ* has competitive or superior performance compared with state-of-the-art (SOTA) IL methods yet requires considerably less trainable parameters and training time.These findings urge us to revisit the IL with PLMs and encourage future studies to have a fundamental understanding of the catastrophic forgetting in PLMs.

Ivan Vykopal, Matúš Pikuliak, Ivan Srba, Robert Moro, Dominik Macko, Maria Bielikova

Automated disinformation generation is often listed as one of the risks of large language models (LLMs). The theoretical ability to flood the information space with disinformation content might have dramatic consequences for democratic societies around the world. This paper presents a comprehensive study of the disinformation capabilities of the current generation of LLMs to generate false news articles in English language. In our study, we evaluated the capabilities of 10 LLMs using 20 disinformation narratives. We evaluated several aspects of the LLMs: how well they are at generating news articles, how strongly they tend to agree or disagree with the disinformation narratives, how often they generate safety warnings, etc. We also evaluated the abilities of detection models to detect these articles as LLM-generated. We conclude that LLMs are able to generate convincing news articles that agree with dangerous disinformation narratives.

Salman Elgamal, Ossama Obeid, Mhd Kabbani, Go Inoue, Nizar Habash

The widespread absence of diacritical marks in Arabic text poses a significant challenge for Arabic natural language processing (NLP). This paper explores instances of naturally occurring diacritics, referred to as “diacritics in the wild,” to unveil patterns and latent information across six diverse genres: news articles, novels, children’s books, poetry, political documents, and ChatGPT outputs. We present a new annotated dataset that maps real-world partially diacritized words to their maximal full diacritization in context. Additionally, we propose extensions to the analyze-and-disambiguate approach in Arabic NLP to leverage these diacritics, resulting in notable improvements. Our contributions encompass a thorough analysis, valuable datasets, and an extended diacritization algorithm. We release our code and datasets as open source.

Zihan Liao, Hang Yu, Jianguo Li, Jun Wang, Wei Zhang

The key challenge in semantic search is to create models that are both accurate and efficient in pinpointing relevant sentences for queries. While BERT-style bi-encoders excel in efficiency with pre-computed embeddings, they often miss subtle nuances in search tasks. Conversely, GPT-style LLMs with cross-encoder designs capture these nuances but are computationally intensive, hindering real-time applications. In this paper, we present D2LLMs—Decomposed and Distilled LLMs for semantic search—that combines the best of both worlds. We decompose a cross-encoder into an efficient bi-encoder integrated with Pooling by Multihead Attention and an Interaction Emulation Module, achieving nuanced understanding and pre-computability. Knowledge from the LLM is distilled into this model using contrastive, rank, and feature imitation techniques. Our experiments show that D2LLM surpasses five leading baselines in terms of all metrics across three tasks, particularly improving NLI task performance by at least 6.45%

Roshan Sharma, Suwon Shon, Mark Lindsey, Hira Dhamyal, Bhiksha Raj

Reference summaries for abstractive speech summarization require human annotation, which can be performed by listening to an audio recording or by reading textual transcripts of the recording. In this paper, we examine whether summaries based on annotators listening to the recordings differ from those based on annotators reading transcripts. Using existing intrinsic evaluation based on human evaluation, automatic metrics, LLM-based evaluation, and a retrieval-based reference-free method, we find that summaries are indeed different based on the source modality, and that speech-based summaries are more factually consistent and information-selective than transcript-based summaries. Transcript-based summaries are impacted by recognition errors in the source, and expert-written summaries are more informative and reliable. We make all the collected data and analysis code public to facilitate the reproduction of our work and advance research in this area.

Marco Gaido, Sara Papi, Matteo Negri, Luisa Bentivogli

The field of natural language processing (NLP) has recently witnessed a transformative shift with the emergence of foundation models, particularly Large Language Models (LLMs) that have revolutionized text-based NLP. This paradigm has extended to other modalities, including speech, where researchers are actively exploring the combination of Speech Foundation Models (SFMs) and LLMs into single, unified models capable of addressing multimodal tasks. Among such tasks, this paper focuses on speech-to-text translation (ST). By examining the published papers on the topic, we propose a unified view of the architectural solutions and training strategies presented so far, highlighting similarities and differences among them. Based on this examination, we not only organize the lessons learned but also show how diverse settings and evaluation approaches hinder the identification of the best-performing solution for each architectural building block and training choice. Lastly, we outline recommendations for future works on the topic aimed at better understanding the strengths and weaknesses of the SFM+LLM solutions for ST.

Liang Lu, Peirong Xie, David Mortensen

Existing work implementing comparative reconstruction of ancestral languages (proto-languages) has usually required full supervision. However, historical reconstruction models are only of practical value if they can be trained with a limited amount of labeled data. We propose a semisupervised historical reconstruction task in which the model is trained on only a small amount of labeled data (cognate sets with proto-forms) and a large amount of unlabeled data (cognate sets without proto-forms). We propose a neural architecture for comparative reconstruction (DPD-BiReconstructor) incorporating an essential insight from linguists’ comparative method: that reconstructed words should not only be reconstructable from their daughter words, but also deterministically transformable back into their daughter words. We show that this architecture is able to leverage unlabeled cognate sets to outperform strong semisupervised baselines on this novel task.

Julie Kallini, Isabel Papadimitriou, Richard Futrell, Kyle Mahowald, Christopher Potts

Chomsky and others have very directly claimed that large language models (LLMs) are equally capable of learning languages that are possible and impossible for humans to learn. However, there is very little published experimental evidence to support such a claim. Here, we develop a set of synthetic impossible languages of differing complexity, each designed by systematically altering English data with unnatural word orders and grammar rules. These languages lie on an impossibility continuum: at one end are languages that are inherently impossible, such as random and irreversible shuffles of English words, and on the other, languages that may not be intuitively impossible but are often considered so in linguistics, particularly those with rules based on counting word positions. We report on a wide range of evaluations to assess the capacity of GPT-2 small models to learn these uncontroversially impossible languages, and crucially, we perform these assessments at various stages throughout training to compare the learning process for each language. Our core finding is that GPT-2 struggles to learn impossible languages when compared to English as a control, challenging the core claim. More importantly, we hope our approach opens up a productive line of inquiry in which different LLM architectures are tested on a variety of impossible languages in an effort to learn more about how LLMs can be used as tools for these cognitive and typological investigations.

Shangbin Feng, Weijia Shi, Yike Wang, Wenxuan Ding, Vidhisha Balachandran, Yulia Tsvetkov

Despite efforts to expand the knowledge of large language models (LLMs), knowledge gaps—missing or outdated information in LLMs—might always persist given the evolving nature of knowledge. In this work, we study approaches to identify LLM knowledge gaps and abstain from answering questions when knowledge gaps are present. We first adapt existing approaches to model calibration or adaptation through fine-tuning/prompting and analyze their ability to abstain from generating low-confidence outputs. Motivated by their failures in self-reflection and over-reliance on held-out sets, we propose two novel approaches that are based on model collaboration, i.e., LLMs probing other LLMs for knowledge gaps, either cooperatively or competitively. Extensive experiments with three LLMs on four QA tasks featuring diverse knowledge domains demonstrate that both cooperative and competitive approaches to unveiling LLM knowledge gaps achieve up to 19.3% improvements on abstain accuracy against the strongest baseline. Further analysis reveals that our abstention methods pinpoint failure cases in retrieval augmentation and knowledge gaps in multi-hop reasoning.

Aryaman Arora, Dan Jurafsky, Christopher Potts

Language models (LMs) have proven to be powerful tools for psycholinguistic research, but most prior work has focused on purely behavioural measures (e.g., surprisal comparisons). At the same time, research in model interpretability has begun to illuminate the abstract causal mechanisms shaping LM behavior. To help bring these strands of research closer together, we introduce CausalGym. We adapt and expand the SyntaxGym suite of tasks to benchmark the ability of interpretability methods to causally affect model behaviour. To illustrate how CausalGym can be used, we study the pythia models (14M–6.9B) and assess the causal efficacy of a wide range of interpretability methods, including linear probing and distributed alignment search (DAS). We find that DAS outperforms the other methods, and so we use it to study the learning trajectory of two difficult linguistic phenomena in pythia-1b: negative polarity item licensing and filler–gap dependencies. Our analysis shows that the mechanism implementing both of these tasks is learned in discrete stages, not gradually.

Chun Hei Lo, Wai Lam, Hong Cheng, Guy Emerson

Functional Distributional Semantics (FDS) models the meaning of words by truth-conditional functions. This provides a natural representation for hypernymy but no guarantee that it can be learnt when FDS models are trained on a corpus. In this paper, we probe into FDS models and study the representations learnt, drawing connections between quantifications, the Distributional Inclusion Hypothesis (DIH), and the variational-autoencoding objective of FDS model training. Using synthetic data sets, we reveal that FDS models learn hypernymy on a restricted class of corpus that strictly follows the DIH. We further introduce a training objective that both enables hypernymy learning under the reverse of the DIH and improves hypernymy detection from real corpora.

Tianshuo Zhou, Sen Mei, Xinze Li, Zhenghao Liu, Chenyan Xiong, Zhiyuan Liu, Yu Gu, Ge Yu

This paper proposes Multi-modAl Retrieval model via Visual modulE pLugin (MARVEL), which learns an embedding space for queries and multi-modal documents to conduct retrieval. MARVEL encodes queries and multi-modal documents with a unified encoder model, which helps to alleviate the modality gap between images and texts. Specifically, we enable the image understanding ability of the well-trained dense retriever, T5-ANCE, by incorporating the visual module’s encoded image features as its inputs. To facilitate the multi-modal retrieval tasks, we build the ClueWeb22-MM dataset based on the ClueWeb22 dataset, which regards anchor texts as queries, and extracts the related text and image documents from anchor-linked web pages. Our experiments show that MARVEL significantly outperforms the state-of-the-art methods on the multi-modal retrieval dataset WebQA and ClueWeb22-MM. MARVEL provides an opportunity to broaden the advantages of text retrieval to the multi-modal scenario. Besides, we also illustrate that the language model has the ability to extract image semantics and partly map the image features to the input word embedding space. All codes are available at https://github.com/OpenMatch/MARVEL.

Jintian Zhang, Xin Xu, Ningyu Zhang, Ruibo Liu, Bryan Hooi, Shumin Deng

As Natural Language Processing (NLP) systems are increasingly employed in intricate social environments, a pressing query emerges: *Can these NLP systems mirror human-esque collaborative intelligence, in a multi-agent society consisting of multiple large language models (LLMs)?* This paper probes the collaboration mechanisms among contemporary NLP systems by melding practical experiments with theoretical insights. We fabricate four unique ‘societies’ comprised of LLM agents, where each agent is characterized by a specific ‘trait’ (easy-going or overconfident) and engages in collaboration with a distinct ‘thinking pattern’ (debate or reflection). Through evaluating these multi-agent societies on three benchmark datasets, we discern that certain collaborative strategies not only outshine previous top-tier approaches but also optimize efficiency (using fewer API tokens). Moreover, our results further illustrate that LLM agents manifest human-like social behaviors, such as conformity and consensus reaching, mirroring foundational social psychology theories. In conclusion, we integrate insights from social psychology to contextualize the collaboration of LLM agents, inspiring further investigations into the collaboration mechanism for LLMs. We commit to sharing our code and datasets, hoping to catalyze further research in this promising avenue.

Tatsuki Kuribayashi, Ryo Ueda, Ryo Yoshida, Yohei Oseki, Ted Briscoe, Timothy Baldwin

The world’s languages exhibit certain so-called typological or implicational universals; for example, Subject-Object-Verb (SOV) languages typically use postpositions. Explaining the source of such biases is a key goal of linguistics.We study word-order universals through a computational simulation with language models (LMs).Our experiments show that typologically-typical word orders tend to have lower perplexity estimated by LMs with cognitively plausible biases: syntactic biases, specific parsing strategies, and memory limitations. This suggests that the interplay of cognitive biases and predictability (perplexity) can explain many aspects of word-order universals.It also showcases the advantage of cognitively-motivated LMs, typically employed in cognitive modeling, in the simulation of language universals.

Mingxin Li, Richong Zhang, Zhijie Nie

Sentence Representation Learning (SRL) is a crucial task in Natural Language Processing (NLP), where contrastive Self-Supervised Learning (SSL) is currently a mainstream approach. However, the reasons behind its remarkable effectiveness remain unclear. Specifically, many studies have investigated the similarities between contrastive and non-contrastive SSL from a theoretical perspective. Such similarities can be verified in classification tasks, where the two approaches achieve comparable performance. But in ranking tasks (i.e., Semantic Textual Similarity (STS) in SRL), contrastive SSL significantly outperforms non-contrastive SSL. Therefore, two questions arise: First, *what commonalities enable various contrastive losses to achieve superior performance in STS?* Second, *how can we make non-contrastive SSL also effective in STS?* To address these questions, we start from the perspective of gradients and discover that four effective contrastive losses can be integrated into a unified paradigm, which depends on three components: the **Gradient Dissipation**, the **Weight**, and the **Ratio**. Then, we conduct an in-depth analysis of the roles these components play in optimization and experimentally demonstrate their significance for model performance. Finally, by adjusting these components, we enable non-contrastive SSL to achieve outstanding performance in STS.

Qisen Yang, Zekun Wang, Honghui Chen, Shenzhi Wang, Yifan Pu, Xin Gao, Wenhao Huang, Shiji Song, Gao Huang

Psychological measurement is essential for mental health, self-understanding, and personal development. Traditional methods, such as self-report scales and psychologist interviews, often face challenges with engagement and accessibility. While game-based and LLM-based tools have been explored to improve user interest and automate assessment, they struggle to balance engagement with generalizability. In this work, we propose PsychoGAT (Psychological Game AgenTs) to achieve a generic gamification of psychological assessment. The main insight is that powerful LLMs can function both as adept psychologists and innovative game designers. By incorporating LLM agents into designated roles and carefully managing their interactions, PsychoGAT can transform any standardized scales into personalized and engaging interactive fiction games. To validate the proposed method, we conduct psychometric evaluations to assess its effectiveness and employ human evaluators to examine the generated content across various psychological constructs, including depression, cognitive distortions, and personality traits. Results demonstrate that PsychoGAT serves as an effective assessment tool, achieving statistically significant excellence in psychometric metrics such as reliability, convergent validity, and discriminant validity. Moreover, human evaluations confirm PsychoGAT’s enhancements in content coherence, interactivity, interest, immersion, and satisfaction.

Zhouhao Sun, Li Du, Xiao Ding, Yixuan Ma, Yang Zhao, Kaitao Qiu, Ting Liu, Bing Qin

Although achieving promising performance, recent analyses show that current generative large language models (LLMs) may still capture dataset biases and utilize them for generation, leading to poor generalizability and harmfulness of LLMs. However, due to the diversity of dataset biases and the over-optimization problem, previous prior-knowledge-based debiasing methods and fine-tuning-based debiasing methods may not be suitable for current LLMs.To address this issue, we explore combining active learning with the causal mechanisms and propose a casual-guided active learning (CAL) framework, which utilizes LLMs itself to automatically and autonomously identify informative biased samples and induce the bias patterns. Then a cost-effective and efficient in-context learning based method is employed to prevent LLMs from utilizing dataset biases during generation.Experimental results show that CAL can effectively recognize typical biased instances and induce various bias patterns for debiasing LLMs.

Fahim Faisal, Orevaoghene Ahia, Aarohi Srivastava, Kabir Ahuja, David Chiang, Yulia Tsvetkov, Antonios Anastasopoulos

Language technologies should be judged on their usefulness in real-world use cases. An often overlooked aspect in natural language processing (NLP) research and evaluation is language variation in the form of non-standard dialects or language varieties (hereafter, varieties). Most NLP benchmarks are limited to standard language varieties. To fill this gap, we propose DIALECTBENCH, the first-ever large-scale benchmark for NLP on varieties, which aggregates an extensive set of task-varied varieties datasets (10 text-level tasks covering 281 varieties). This allows for a comprehensive evaluation of NLP system performance on different varieties. We provide substantial proof of performance disparities between standard and non-standard language varieties, and we also identify language clusters with larger performance divergence across tasks.We believe DIALECTBENCH provides a comprehensive view of the current state of NLP for varieties and one step towards advancing it further.

Chenxin An, Shansan Gong, Ming Zhong, Xingjian Zhao, Mukai Li, Jun Zhang, Lingpeng Kong, Xipeng Qiu

Recently, there has been growing interest in long-context scaling of large language models (LLMs). To facilitate research in this field, we propose L-Eval to institute a more standardized evaluation for Long-Context Language Models (LCLMs) addressing two key aspects: dataset construction and evaluation metrics. On the one hand, we build a new evaluation suite containing 20 sub-tasks, 508 long documents, and more than 2,000 human-labeled query-response pairs including diverse task types, domains, and input length (3k~200k tokens). On the other hand, we investigate the effectiveness of evaluation metrics for LCLMs and we show that Length-instruction-enhanced (LIE) evaluation and LLM judges can better correlate with human judgments. We conducted a comprehensive study of 4 popular commercial LLMs and 12 open-source counterparts using the L-Eval benchmark. Our empirical findings offer useful insights into the study of LCLMs and lay the groundwork for the development of a more principled evaluation of these models.