Papers by Meng Cao

Argue with Me Tersely: Towards Sentence-Level Counter-Argument Generation (2023.emnlp-main)

Challenge:	Existing REG systems rely on entity-specific supervised training, which means they cannot handle entities not seen during training.
Approach:	They propose a deep neural network model that encodes both the local context and an external profile of the entity to generate reference realizations.
Outcome:	The proposed model outperforms baselines on three different splits of the WebNLG dataset according to automatic and human evaluations.

Copied to clipboard

Jiayu Lin, Rong Ye, Meng Han, Qi Zhang, Ruofei Lai, Xinyu Zhang, Zhao Cao, Xuanjing Huang, Zhongyu Wei

Beyond Polarity: Continuous Affect-Enhanced Multimodal Aspect-Based Sentiment Classification (2026.findings-acl)

Challenge:	Existing work describes paragraph-level counter-argument generation task as paragraph-based . however, sentence-level generation can be quite different due to its unique constraints and brevity-focused challenges.
Approach:	They propose a benchmark framework for sentence-level counter-argument generation . they use an annotated debate forum dataset to generate high-quality counter-argments .
Outcome:	The proposed framework and evaluator are competitive in counter-argument generation tasks.

Copied to clipboard

Ling-Ang Meng, Tianyu Zhao, Dawei Song, Jingxu Cao, Youhui Zuo

Information Retrieval

Challenge:	Existing methods for multimodal aspect-based sentiment classification exploit discrete polarity patterns and generic visual embeddings.
Approach:	They propose a Valence–Arousal–Dominance(VAD)-Enhanced MABSC framework that integrates VAD signals into multimodal sentiment reasoning and learns emotion-sensitive image representations.
Outcome:	The proposed framework brings VAD signals into multimodal sentiment reasoning and learns emotion-sensitive image representations.

Mitigating Lost in Multi-turn Conversation via Curriculum RL with Verifiable Accuracy and Abstention Rewards (2026.acl-long)

Copied to clipboard

Ming Li, Pei Chen, Zhenhao Zhang, Tao Yang, Xinyang Zhang, Han Li, Tianyu Cao, Ming Zeng, Zhuofeng Wu, Meng Jiang, Huasheng Li, Lihong Li, Bing Yin

Hence, Socrates is mortal: A Benchmark for Natural Language Syllogistic Reasoning (2023.findings-acl)

Challenge:	Large Language Models exhibit strong capabilities in single-turn instruction following but suffer from Lost-in-Conversation (LiC) when instructions are revealed progressively in multi-turn settings, models get "Lost in Conversation"
Approach:	They propose a framework that encourages models to generate correct answers and judge solvability in multi-turn conversations.
Outcome:	The proposed framework improves models' ability to balance problem-solving with abstention . it reduces premature answering behaviors that cause lost-in-conversation (LiC)

Copied to clipboard

Yongkang Wu, Meng Han, Yutao Zhu, Lei Li, Xinyu Zhang, Ruofei Lai, Xiaoguang Li, Yuanhang Ren, Zhicheng Dou, Zhao Cao

Factual Error Correction for Abstractive Summarization Models (2020.emnlp-main)

Challenge:	SylloBase is a benchmark for syllogistic reasoning, a critical capability widely required in natural language understanding tasks, such as text entailment and question answering.
Approach:	They propose to use a benchmark to learn syllogistic reasoning on a set of templates and to use them to generate and understand slogisms.
Outcome:	The proposed benchmark covers a complete taxonomy of syllogism reasoning patterns, and contains both automatically and manually constructed samples.

Copied to clipboard

Meng Cao, Yue Dong, Jiapeng Wu, Jackie Chi Kit Cheung

Summarization

Challenge:	Existing methods for abstractive summarization are unable to ensure factual consistency of generated summaries.
Approach:	They propose a post-editing corrector module to identify and correct factual errors in generated summaries.
Outcome:	The proposed model outperforms existing models on CNN/DailyMail dataset on factual consistency evaluation.

Putting Captions to the Test: Evaluating Video Caption Quality through Multiple-Choice Question Answering (2026.acl-long)

Copied to clipboard

Zizhen Wang, Bo Feng, Zhengfeng Lai, Shiyu Li, Yang Lu, Meng Cao, Ping Huang, Xiaoming Simon Wang

Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations (2024.findings-emnlp)

Challenge:	Existing metrics for video captioning are based on text-based comparisons with ground-truth references.
Approach:	They propose a reference-free benchmark that assesses video captions based on their utility . they will release the benchmark to facilitate reproducible research .
Outcome:	The proposed benchmark improves on human-verified, fine-grained questions . it correlates significantly better with human judgments than existing metrics .

Copied to clipboard

Lei Yu, Meng Cao, Jackie Cheung, Yue Dong

TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack (2022.emnlp-main)

Challenge:	State-of-the-art language models (LMs) sometimes generate that misalign with world knowledge.
Approach:	They propose a method to mitigate hallucinations by restoring the LM's internal fact recall pipeline by a targeted restoration of its internal fact-recall pipeline.
Outcome:	The proposed method shows superior performance compared to baselines.

Copied to clipboard

Yu Cao, Dianqi Li, Meng Fang, Tianyi Zhou, Jun Gao, Yibing Zhan, Dacheng Tao

Token Preference Optimization with Self-Calibrated Visual-Anchored Rewards for Hallucination Mitigation (2025.findings-emnlp)

Challenge:	Existing adversarial models rely on keyword matching and ignore relevant contextual relations for answer prediction.
Approach:	They propose to use keyword matching to attack model with two biases that rely on a perturbed answer sentence and a distracting answer sentence to misguide model.
Outcome:	The proposed method produces fluent and grammatical adversarial contexts while maintaining gold answers.

Copied to clipboard

Jihao Gu, Yingyao Wang, Meng Cao, Pi Bu, Jun Song, Bo Zheng, Yancheng He, Shilong Li

Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases (2021.acl-long)

Challenge:	Existing methods for predicting hallucinations suffer from two drawbacks: Lack of scalable token-level rewards and Neglect of visual-anchored tokens.
Approach:	They propose a Token Preference Optimization model with self-calibrated rewards . they propose based on visual-anchored tokens and visual-aware training objective .
Outcome:	The proposed model improves hallucination performance by focusing on visual-anchored tokens without fine-grained annotations.

Copied to clipboard

Boxi Cao, Hongyu Lin, Xianpei Han, Le Sun, Lingyong Yan, Meng Liao, Tong Xue, Jin Xu

DialogUSR: Complex Dialogue Utterance Splitting and Reformulation for Multiple Intent Detection (2022.findings-emnlp)

Challenge:	Recent studies show that pre-trained masked language models can be factual knowledge bases.
Approach:	They conduct a rigorous study to explore the underlying predicting mechanisms of MLMs . they find that previous decent performance mainly owes to the biased prompts which overfit dataset artifacts a .
Outcome:	The proposed model improves on illustrative cases and external contexts . the results question the previous findings that MLMs can be reliable factual knowledge bases .

Copied to clipboard

Haoran Meng, Zheng Xin, Tianyu Liu, Zizhen Wang, He Feng, Binghuai Lin, Xuemin Zhao, Yunbo Cao, Zhifang Sui

Natural Language Interfaces

Challenge:	DialogUSR is a plug-in and domain-agnostic module that empowers multi-intent detection for chatbots . a single user query triggers inquiries on highspeed train ticket price and weather of destination.
Approach:	They propose a dialog utterance splitting and reformulation task that splits multi-intent user query into multiple single-intention sub-queries and recovers all coreferred and omitted information in the sub-questions.
Outcome:	The proposed model can be used to split multi-intent user queries into multiple sub-queries . it can be trained in two stages and perform in-depth analyses on the proposed models .

Cross-Lingual Knowledge Editing in Large Language Models (2024.acl-long)

Copied to clipboard

Jiaan Wang, Yunlong Liang, Zengkui Sun, Yuxuan Cao, Jiarong Xu, Fandong Meng

See the World, Discover Knowledge: A Chinese Factuality Evaluation for Large Vision Language Models (2025.findings-acl)

Challenge:	Knowledge editing is a promising technique to adapt large language models to new knowledge without retraining from scratch.
Approach:	They propose to use a multilingual dataset to translate a large-scale cross-lingual synthetic dataset from English to Chinese and then to evaluate their performance in Chinese.
Outcome:	The proposed method can change model performance on several special cases without retraining from scratch.

Copied to clipboard

Jihao Gu, Yingyao Wang, Pi Bu, Chen Wang, Ziming Wang, Tengtao Song, Donglai Wei, Jiale Yuan, Yingxiu Zhao, Yancheng He, Shilong Li, Jiaheng Liu, Meng Cao, Jun Song, Yingshui Tan, Xiang Li, Wenbo Su, Xiaoyong Zhu, Bo Zheng

Balanced Joint Adversarial Training for Robust Intent Detection and Slot Filling (2020.coling-main)

Challenge:	Existing models for large vision language models do not fully reflect their knowledge capacity and reliability, resulting in erroneous outputs that do not align with the image content or provide answers lacking knowledge evidence.
Approach:	They propose a Chinese-based benchmark for visual factuality across 8 major topics and 56 subtopics and a multi-hop question construction.
Outcome:	The proposed model decouples visual factuality into two parts: seeing the world and discovering knowledge.

Copied to clipboard

Xu Cao, Deyi Xiong, Chongyang Shi, Chao Wang, Yao Meng, Changjian Hu

Semantic Parsing

Challenge:	Existing joint models for intent detection and slot filling show insufficient robustness . however, some small changes of inputs can fool the models to produce wrong predictions .
Approach:	They propose a joint adversarial training model that generates adversarials to attack the joint model and trains the model to defend against the adversarial examples.
Outcome:	The proposed model achieves significantly higher scores and improves robustness on two datasets.

DAGN: Discourse-Aware Graph Network for Logical Reasoning (2021.naacl-main)

Copied to clipboard

Yinya Huang, Meng Fang, Yu Cao, Liwei Wang, Xiaodan Liang

Structured Data in NLP

Challenge:	Recent QA with logical reasoning questions requires passage-level relations among the sentences.
Approach:	They propose a discourse-aware graph network that aggregates passage-level clues for QA by using discourse-based information.
Outcome:	The proposed model achieves competitive results on two logical reasoning QA datasets.

IAG: Induction-Augmented Generation Framework for Answering Reasoning Questions (2023.emnlp-main)

Copied to clipboard

Zhebin Zhang, Xinyu Zhang, Yuanhang Ren, Saijiang Shi, Meng Han, Yongkang Wu, Ruofei Lai, Zhao Cao

TIU-Bench: A Benchmark for Evaluating Large Multimodal Models on Text-rich Image Understanding (2025.findings-emnlp)

Challenge:	Existing approaches to QA using retrieval-augmented knowledge are limited by limited coverage and noisy information.
Approach:	They propose an induction-augmented generation framework that utilizes inductive knowledge along with retrieved documents for implicit reasoning.
Outcome:	The proposed framework outperforms RAG and ChatGPT on two Open-Domain QA tasks.

Copied to clipboard

Kun Zhang, Liqiang Niu, Zhen Cao, Fandong Meng, Jie Zhou

Pretrained Language Models for Dialogue Generation with Multiple Input Sources (2020.findings-emnlp)

Challenge:	Existing text-rich image understanding benchmarks lack scale and fragmented scenarios . a new full-image structured output format is proposed to enable fine-grained evaluation of perception and reasoning capabilities.
Approach:	They propose a large-scale, multilingual benchmark that includes over 100,000 annotations and 22,000 question-answer pairs.
Outcome:	The proposed framework provides a comprehensive platform for developing and evaluating next-generation multimodal AI systems.

Copied to clipboard

Yu Cao, Wei Bi, Meng Fang, Dacheng Tao

On Pursuit of Designing Multi-modal Transformer for Video Grounding (2021.emnlp-main)

Challenge:	Large-scale pretrained language models have achieved outstanding performance on natural language understanding tasks.
Approach:	They propose to fuse attention information from multiple input sources to achieve better relevance with dialogue history than simple fusion baselines.
Outcome:	The proposed models deliver higher relevance with dialogue history than baselines.

Copied to clipboard

Meng Cao, Long Chen, Mike Zheng Shou, Can Zhang, Yuexian Zou

Can LLMs Reason Abstractly Over Math Word Problems Without CoT? Disentangling Abstract Formulation From Arithmetic Computation (2025.emnlp-main)

Challenge:	Existing methods for video grounding are not end-to-end, i.e., they rely on time-consuming post-processing steps to refine predictions.
Approach:	They propose an end-to-end multi-modal Transformer model that uses two encoders and a cross-modal decoder for grounding prediction.
Outcome:	The proposed model is 4.9% faster than existing models and is based on a set of encodings and decoders.

Copied to clipboard

Ziling Cheng, Meng Cao, Leila Pishdad, Yanshuai Cao, Jackie CK Cheung

BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering (N19-1)

Challenge:	Large language models (LLMs) are often evaluated on math word problems . however, such metrics conflate two distinct sub-skills: abstract formulation and arithmetic computation.
Approach:	They propose to use Final-answer-based metrics to evaluate large language models on math word problems to conflate two distinct sub-skills: abstract formulation and arithmetic computation.
Outcome:	The proposed model performance is bottlenecked by arithmetic computation and not abstract formulation, the study shows.

Copied to clipboard

Yu Cao, Meng Fang, Dacheng Tao

Structured Data in NLP

Challenge:	Existing datasets for question answering and machine comprehension (MC) are limited to a single paragraph, or even part of it.
Approach:	They propose a bi-directional Attention Entity Graph Convolutional Network (BAG) that leverages relationships between nodes in an entity graph and attention information between a query and the entity graph to generate a prediction.
Outcome:	Experimental results show that the proposed network achieves state-of-the-art accuracy on the QAngaroo WIKIHOP dataset.

The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction (2025.findings-acl)

Copied to clipboard

Yihuai Hong, Meng Cao, Dian Zhou, Lei Yu, Zhijing Jin

MR. Judge: Multimodal Reasoner as a Judge (2025.emnlp-main)

Challenge:	Large language models excel on a variety of reasoning benchmarks, but struggle to generalize to unseen questions due to over-reliance on memorized training examples.
Approach:	They propose to identify a set of linear features in the model’s residual stream that govern the balance between genuine reasoning and memory recall.
Outcome:	The proposed model can be manipulated to activate the most relevant problem-solving capabilities during answer generation.

Copied to clipboard

Renjie Pi, Haoping Bai, Qibin Chen, Xiaoming Simon Wang, Jiulong Shan, Xiaojiang Liu, Meng Cao

MMAU: A Holistic Benchmark of Agent Capabilities Across Diverse Domains (2025.findings-naacl)

Challenge:	Effective reward modeling is especially valuable in reinforcement learning (RLHF) .
Approach:	They propose a paradigm for empowering general-purpose MLLMs judges with strong reasoning capabilities by using multiple-choice problem models instead of directly assigning scores.
Outcome:	The proposed model surpasses GPT-4o on VL-RewardBench and improves performance on MM-Vet by up to 7.7%.

Copied to clipboard

Guoli Yin, Haoping Bai, Shuang Ma, Feng Nan, Yanchao Sun, Zhaoyang Xu, Shen Ma, Jiarui Lu, Xiang Kong, Aonan Zhang, Dian Ang Yap, Yizhe Zhang, Karsten Ahnert, Vik Kamath, Mathias Berglund, Dominic Walsh, Tobias Gindele, Juergen Wiest, Zhengfeng Lai, Xiaoming Simon Wang, Jiulong Shan, Meng Cao, Ruoming Pang, Zirui Wang

Challenge:	Existing benchmarks focus on specific application scenarios, emphasizing task completion but failing to dissect the underlying skills that drive these outcomes.
Approach:	They propose a Massive Multitask Agent Understanding benchmark that evaluates LLMs across five domains and offline tasks.
Outcome:	The Massive Multitask Agent Understanding (MMAU) benchmark evaluates models across five domains including Tool-use, Directed Acyclic Graph (DAG) QA, Data Science and Machine Learning coding, Contest-level programming and Mathematics.

Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation (2024.acl-long)

Copied to clipboard

Aiwei Liu, Haoping Bai, Zhiyun Lu, Xiang Kong, Xiaoming Wang, Jiulong Shan, Meng Cao, Lijie Wen

Responsible & Trustworthy NLP

Challenge:	Existing methods to evaluate preference data without human annotations are difficult . et al., 2022b) is effective for aligning large language models with human expectations .
Approach:	They propose a method to evaluate the response preference using output probabilities under contrastive prompts.
Outcome:	The proposed method could surpass the RLHF method without human-annotated preference data.

DiffusEmp: A Diffusion Model-Based Framework with Multi-Grained Control for Empathetic Response Generation (2023.acl-long)

Copied to clipboard

Guanqun Bi, Lei Shen, Yanan Cao, Meng Chen, Yuqiang Xie, Zheng Lin, Xiaodong He

Hi-ArG: Exploring the Integration of Hierarchical Argumentation Graphs in Language Pretraining (2023.emnlp-main)

Challenge:	Existing methods to generate empathetic responses are monotonous and generic, resulting in shallow empathy and few connections to the context.
Approach:	They propose to use explicit control to guide the empathy expression and a framework DiffusEmp to unify the utilization of dialogue context and attribute-oriented control signals.
Outcome:	The proposed framework outperforms baselines on EmpatheticDialogue in terms of controllability, informativeness, diversity, and diversity without the loss of context-relatedness.

Copied to clipboard

Jingcong Liang, Rong Ye, Meng Han, Qi Zhang, Ruofei Lai, Xinyu Zhang, Zhao Cao, Xuanjing Huang, Zhongyu Wei

Where Did That Come From? Sentence-Level Error-Tolerant Attribution (2025.findings-emnlp)

Challenge:	Recent studies have discussed its capability to assist language models for various applications.
Approach:	They propose a structure to organize arguments using the Hierarchical Argumentation Graph (Hi-ArG) and propose two approaches to exploit Hi-AarG, including a text-graph multi-modal model GreaseArR and a framework augmented with graph information.
Outcome:	The proposed structure supersedes existing language models on two argumentation tasks while incorporating graph information during further training improves vanilla language models.

Copied to clipboard

Ori Ernst, Aviv Slobodkin, Meng Cao, Sihui Wei, Jackie CK Cheung

Interleaved Tool-Call Reasoning for Protein Function Understanding (2026.acl-long)

Challenge:	Existing task definitions exclude unsupported or hallucinated content leaving them unattributed . authors propose a new definition for sentence-level error-tolerant attribution .
Approach:	They propose a new definition for sentence-level error-tolerant attribution that extends attribution to include incorrect or hallucinated content.
Outcome:	The proposed approach reduces annotation time and facilitates hallucination fixing.

Copied to clipboard

Chuanliu Fan, Zicheng Ma, Huanran Meng, Aijia Zhang, Wenjie Du, Jun Zhang, Ziqiang Cao, Guohong Fu

Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers (2024.findings-acl)

Challenge:	Recent advances in large language models have highlighted the effectiveness of chain-of-thought reasoning in symbolic domains such as mathematics and programming.
Approach:	They propose a tool-augmented protein reasoning agent that unifies problem decomposition, tool invocation, and grounded answer generation.
Outcome:	The proposed protein function understanding agent outperforms text-only reasoning models with an average performance improvement of 103%.

Copied to clipboard

Haowen Pan, Yixin Cao, Xiaozhi Wang, Xun Yang, Meng Wang

Towards Robust Visual Question Answering: Making the Most of Biased Samples via Contrastive Learning (2022.findings-emnlp)

Challenge:	Existing methods to identify key neurons for interpretability of multi-modal large language models are unclear.
Approach:	They propose a method to identify key neurons for interpretability by multi-modal large language models.
Outcome:	The proposed method improves conventional works upon efficiency and applied range by removing needs of costly gradient computation.

Copied to clipboard

Qingyi Si, Yuanxin Liu, Fandong Meng, Zheng Lin, Peng Fu, Yanan Cao, Weiping Wang, Jie Zhou

An Empirical Study of Many-to-Many Summarization with Large Language Models (2025.acl-long)

Challenge:	Recent studies have shown that biased samples can be brittle for VQA models . however, the improvements on OOD data severely sacrifice the performance on the in-distribution (ID) data.
Approach:	They propose a contrastive learning approach that exploits biased samples for unbiased information that contributes to reasoning.
Outcome:	The proposed method achieves competitive performance on the OOD dataset while maintaining robustness on the ID dataset.

Copied to clipboard

Jiaan Wang, Fandong Meng, Zengkui Sun, Yunlong Liang, Yuxuan Cao, Jiarong Xu, Haoxiang Shi, Jie Zhou

RedOne 2.0: Rethinking Domain-specific LLM Post-Training in Social Networking Services (2026.acl-industry)

Challenge:	Recent studies have shown that large language models (LLMs) have strong multilingual abilities, giving them the potential to perform M2MS in real applications.
Approach:	They propose to use many-to-many summarization (M2MS) to generate a brief summary in any language given a document also in any other language.
Outcome:	The proposed model outperforms zero-shot LLMs in terms of automatic evaluations.

Copied to clipboard

Fei zhao, Chonggang Lu, Haofu Qian, Fangcheng Shi, Zijie Meng, Jianzhao Huang, Zheyong Xie, Shaosheng Cao

TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion (2020.emnlp-main)

Challenge:	Social networking services (SNS) are critical infrastructure for global interaction . supervised fine-tuning (SFT) can improve in-domain performance, but it often induces a ”seesaw” trade-off with out-of-domain robustness .
Approach:	They propose an SNS-oriented LLM with a progressive, RL-prioritized post-training paradigm for fast and stable adaptation.
Outcome:	The proposed model improves over the previous 7B model by 2.41 on average . it also yields an 8.74 average gain over its Qwen3-4B base .

Copied to clipboard

Jiapeng Wu, Meng Cao, Jackie Chi Kit Cheung, William L. Hamilton

Responsible AI Considerations in Text Summarization Research: A Review of Current Practices (2023.findings-emnlp)

Challenge:	Existing methods for static knowledge graphs do not explicitly leverage multi-hop structural information and temporal facts from recent time steps to enhance their predictions.
Approach:	They propose a framework to leverage time-dependent temporal information to infer missing facts in temporal knowledge graphs.
Outcome:	The proposed framework achieves 10.7% improvement in Hits@10 across three standard benchmarks.

Copied to clipboard

Yu Lu Liu, Meng Cao, Su Lin Blodgett, Jackie Chi Kit Cheung, Alexandra Olteanu, Adam Trischler

Information Extraction & Text Mining

Challenge:	a recent study examines research and reporting practices for text summarization tasks . text summaries are often overlooked by the responsible AI community .
Approach:	They examine research and reporting practices in the context of text summarization . they find that relatively few papers engage with possible stakeholders .
Outcome:	The findings highlight current research practices and provide recommendations on research directions.

A Model-agnostic Data Manipulation Method for Persona-based Dialogue Generation (2022.acl-long)

Copied to clipboard

Yu Cao, Wei Bi, Meng Fang, Shuming Shi, Dacheng Tao

Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training (2022.naacl-main)

Challenge:	Existing models for introducing explicit personas are expensive due to their expensive collection costs.
Approach:	They propose a data manipulation method which is model-agnostic to be packed with any persona-based dialogue generation model to improve their performance.
Outcome:	The proposed method is model-agnostic to be packed with any persona-based dialogue generation model to improve their performance.

Copied to clipboard

Yuanxin Liu, Fandong Meng, Zheng Lin, Peng Fu, Yanan Cao, Weiping Wang, Jie Zhou

Learning with Rejection for Abstractive Text Summarization (2022.emnlp-main)

Challenge:	Recent studies show pre-trained language models contain matching subnetworks that have similar transfer learning performance as the original PLM.
Approach:	They propose to prune matching subnetworks using magnitude-based pruning . they propose to optimize the subnetwork structure towards the pre-training objectives .
Outcome:	The proposed method is more efficient in searching subnetworks and advantageous when fine-tuning within a range of data scarcity.

Copied to clipboard

Meng Cao, Yue Dong, Jingyi He, Jackie Chi Kit Cheung

A Survey for Efficient Open Domain Question Answering (2023.acl-long)

Challenge:	Existing abstractive summarization systems produce non-factual summaries due to noise in the training dataset.
Approach:	They propose a training objective for abstractive summarization based on rejection learning that learns whether or not to reject potentially noisy tokens.
Outcome:	The proposed method significantly improves the factuality of generated summaries in automatic and human evaluations when compared to baseline models.

Copied to clipboard

Qin Zhang, Shangsi Chen, Dongkuan Xu, Qingqing Cao, Xiaojun Chen, Trevor Cohn, Meng Fang

Natural Language Interfaces

Challenge:	Open domain question answering (ODQA) is a longstanding task that can answer factoid questions without explicit evidence in natural language processing (NLP).
Approach:	They propose to use open domain question answering to answer factual questions from a large knowledge corpus without explicit evidence.
Outcome:	The proposed models can answer factoid questions from a large knowledge corpus without explicit evidence.

CROSSAGENTIE: Cross-Type and Cross-Task Multi-Agent LLM Collaboration for Zero-Shot Information Extraction (2025.findings-acl)

Copied to clipboard

Meng Lu, Yuzhang Xie, Zhenyu Bi, Shuxiang Cao, Xuan Wang

Low-Resource NLP

Challenge:	Large language models struggle with producing structured output while maintaining accuracy in zero-shot information extraction (IE)
Approach:	They propose a multi-agent framework that enhances zero-shot IE through multi-task collaboration.
Outcome:	CROSSAGENTIE outperforms state-of-the-art models in structured prediction . the framework significantly reduces inference cost while preserving accuracy .

Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMs (2025.acl-long)

Copied to clipboard

Ziling Cheng, Meng Cao, Marc-Antoine Rondeau, Jackie CK Cheung

GenKIE: Robust Generative Multimodal Document Key Information Extraction (2023.findings-emnlp)

Challenge:	Existing studies have shown that LLMs reproduce training artifacts, exploit spurious correlations, and fail when faced with distribution shifts.
Approach:	They examine irrelevant context hallucinations in which models integrate misleading contextual cues into their predictions.
Outcome:	The proposed model errors are reflected in the model's internal computations, and they are consistent with previous studies.

Copied to clipboard

Panfeng Cao, Ye Wang, Qiang Zhang, Zaiqiao Meng

RedOne: Revealing Domain-specific LLM Post-Training in Social Networking Services (2025.emnlp-industry)

Challenge:	Key information extraction (KIE) is a key application for information retrieval and text mining.
Approach:	They propose a novel generative end-to-end model, named GenKIE, to address the KIE task.
Outcome:	The proposed model generalizes over different types of documents and achieves state-of-the-art results.

Copied to clipboard

Fei Zhao, Chonggang Lu, null Wangyue, Zheyong Xie, Ziyan Liu, Haofu Qian, Jianzhao Huang, Fangcheng Shi, Zijie Meng, Hongcheng Guo, Mingqian He, Xinze Lyu, Zheyu Ye, Weiting Liu, Boyang Wang, Shaosheng Cao

Phrase-level Textual Adversarial Attack with Label Preservation (2022.findings-naacl)

Challenge:	Social networking services (SNS) have experienced rapid growth, which has proposed significant challenges for platform content management and interaction quality improvement.
Approach:	They propose a domain-specific LLM to break the performance bottleneck of single-task baselines and establish a comprehensive foundation for social networking services.
Outcome:	The proposed model achieves an average improvement of 14.02% across 8 major tasks and 7.56% in bilingual evaluation benchmark, compared with baseline models.

Copied to clipboard

Yibin Lei, Yu Cao, Dianqi Li, Tianyi Zhou, Meng Fang, Mykola Pechenizkiy

Enhancing Reinforcement Learning with Dense Rewards from Language Model Critic (2024.emnlp-main)

Challenge:	Existing adversarial attacks are usually realized through word-level or sentence-level perturbations, which either limit the perturbation space or sacrifice fluency and textual quality.
Approach:	They propose a phrase-level perturbation-based adversarial ATtack that generates adversarials through phrase- level perturbations.
Outcome:	The proposed approach improves the performance of natural language processing models by reducing the need for word-level perturbations and preserving the fluency and grammaticality of the samples.

Copied to clipboard

Meng Cao, Lei Shu, Lei Yu, Yun Zhu, Nevan Wichers, Yinxiao Liu, Lei Meng

Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA (2022.findings-emnlp)

Challenge:	Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences, but the sparsity of these signals can lead to inefficient and unstable learning.
Approach:	They propose a framework that utilizes the critique capability of Large Language Models to produce intermediate-step rewards during RL training.
Outcome:	The proposed framework improves sample efficiency and the overall performance of the policy model, supported by both automatic and human evaluation.

Copied to clipboard

Qingyi Si, Fandong Meng, Mingyu Zheng, Zheng Lin, Yuanxin Liu, Peng Fu, Yanan Cao, Weiping Wang, Jie Zhou

Question Answering

Challenge:	Visual Question Answering (VQA) models are prone to learn the shortcut solution formed by dataset biases rather than the intended solution.
Approach:	They propose a dataset that considers varying types of shortcuts by constructing different distribution shifts in multiple OOD test sets.
Outcome:	The proposed dataset considers varying types of shortcuts by constructing different distribution shifts in multiple OOD test sets.

DialogVCS: Robust Natural Language Understanding in Dialogue System Upgrade (2024.naacl-long)

Copied to clipboard

Zefan Cai, Xin Zheng, Tianyu Liu, Haoran Meng, Jiaqi Han, Gang Yuan, Binghuai Lin, Baobao Chang, Yunbo Cao

RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter (2024.findings-acl)

Challenge:	Existing models for natural language understanding are based on a well-defined intent 1 ontology.
Approach:	They propose to retrain the natural language understanding model as new data from real users are merged into existing data.
Outcome:	The proposed model shows that the semantically entangled intents can be recognized with an automatic workflow.

Copied to clipboard

Meng Cao, Haoran Tang, Jinfa Huang, Peng Jin, Can Zhang, Ruyang Liu, Long Chen, Xiaodan Liang, Li Yuan, Ge Li

Green & Sustainable NLP

Challenge:	Text-Video Retrieval (TVR) aims to align relevant video content with natural language queries.
Approach:	They propose to conduct efficient text-video Retrieval with a salient-and-correlated AdaPter . they propose a low-rank modulation module to refine per-image features from frozen CLIP backbone .
Outcome:	Experiments on four TVR datasets show that the proposed method performs better than other methods.

Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization (2022.acl-long)

Copied to clipboard

Meng Cao, Yue Dong, Jackie Cheung