Papers by Meng Li

Autoregressive Speech Synthesis without Vector Quantization (2025.acl-long)

Challenge:	Recent advances in large language models (LLMs) have expanded their scope to encompass multimodal functions.
Approach:	They propose a robust and adaptive speech large language model with dual encoders . they validate the model on universal speech benchmarks and apply it to specialized speech-question-answer datasets based on a CoT approach .
Outcome:	The proposed model achieves state-of-the-art performance across a range of speech tasks on the same model size.

Copied to clipboard

Lingwei Meng, Long Zhou, Shujie Liu, Sanyuan Chen, Bing Han, Shujie Hu, Yanqing Liu, Jinyu Li, Sheng Zhao, Xixin Wu, Helen M. Meng, Furu Wei

Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage (2026.findings-acl)

Challenge:	MELLE is a novel language modeling approach for text-to-speech synthesis that generates continuous tokens from text . authors demonstrate that it reduces the need for vector quantization and improves model robustness .
Approach:	They propose to autoregressively generate continuous mel-spectrogram frames directly from text condition, bypassing vector quantization.
Outcome:	The proposed model achieves superior performance across multiple metrics and is more streamlined.

Copied to clipboard

Junhao Hu, Fangze Li, Mingtao Xu, Feifan Meng, Shiju Zhao, Tiancheng Hu, Ting Peng, Anmin Liu, Wenrui Huang, Chenxu Liu, Ziyue Hua, Tao Xie

Challenge:	Prior work typically decomposes inference into prefill and decode stages, with the decode stage dominating total latency.
Approach:	They propose an algorithm that detects threshold where information loss exceeds information gain during sparse decoding to reduce token consumption by up to 90% and a marginal accuracy degradation of less than 2%.
Outcome:	The proposed algorithm reduces token consumption by 90% with a marginal accuracy degradation of less than 2% across reasoning-intensive benchmarks.

Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts (2024.findings-acl)

Copied to clipboard

Ganesh Jawahar, Haichuan Yang, Yunyang Xiong, Zechun Liu, Dilin Wang, Fei Sun, Meng Li, Aasish Pappu, Barlas Oguz, Muhammad Abdul-Mageed, Laks Lakshmanan, Raghuraman Krishnamoorthi, Vikas Chandra

Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training (2021.emnlp-main)

Challenge:	Neural architecture search (NAS) uses weight-sharing supernets to generate diverse subnetworks without retraining.
Approach:	They propose a weight-sharing supernet that leverages mixture-of-experts to enhance supernet model expressiveness with minimal training overhead.
Outcome:	The proposed method achieves state-of-the-art (SoTA) performance in NAS for fast machine translation models, surpassing NAS-BERT and AutoDistil across various model sizes.

Copied to clipboard

Minghao Wu, Yitong Li, Meng Zhang, Liangyou Li, Gholamreza Haffari, Qun Liu

Multilinguality

Challenge:	MultiUAT dynamically adjusts training data usage based on model’s uncertainty on a small set of trusted clean data for multi-corpus machine translation.
Approach:	They propose an approach that dynamically adjusts the training data usage based on the model’s uncertainty on a small set of trusted clean data for multi-corpus machine translation.
Outcome:	The proposed approach outperforms baselines on 16 languages and 2 domains on English-German translation.

LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing (2024.emnlp-main)

Copied to clipboard

Jiangshu Du, Yibo Wang, Wenting Zhao, Zhongfen Deng, Shuaiqi Liu, Renze Lou, Henry Zou, Pranav Narayanan Venkit, Nan Zhang, Mukund Srinath, Haoran Zhang, Vipul Gupta, Yinghui Li, Tao Li, Fei Wang, Qin Liu, Tianlin Liu, Pengzhi Gao, Congying Xia, Chen Xing, Cheng Jiayang, Zhaowei Wang, Ying Su, Raj Shah, Ruohao Guo, Jing Gu, Haoran Li, Kangda Wei, Zihao Wang, Lu Cheng, Surangika Ranathunga, Meng Fang, Jie Fu, Fei Liu, Ruihong Huang, Eduardo Blanco, Yixin Cao, Rui Zhang, Philip Yu, Wenpeng Yin

Challenge:	a comparative analysis of paper (meta-)reviews by large language models (LLMs) aims to identify and distinguish LLMs from human activities .
Approach:	They present a comparative analysis to identify and distinguish LLM activities from human activities.
Outcome:	The proposed analysis aims to improve recognition of instances when someone implicitly uses LLMs for reviewing activities.

Rethinking Machine Ethics – Can LLMs Perform Moral Reasoning through the Lens of Moral Theories? (2024.findings-naacl)

Copied to clipboard

Jingyan Zhou, Minda Hu, Junan Li, Xiaoying Zhang, Xixin Wu, Irwin King, Helen Meng

Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs (2026.acl-long)

Challenge:	Existing approaches to making moral judgments are mostly bottom-up and lack explainability.
Approach:	They propose a top-down framework to steer Large Language Models to perform moral reasoning with well-established moral theories.
Outcome:	The proposed framework can integrate various moral theories on moral datasets.

Copied to clipboard

Zhenyu Liu, Xuanyu Zhang, Yunxin li, Qixun Teng, Shenyuan Jiang, Haolan Chen, Mingjun Zhao, Fanbo Meng, Yu Xu, Yancheng He, Baotian Hu, Haizhou Li, Min Zhang

GNN-SL: Sequence Labeling Based on Nearest Examples via GNN (2023.findings-acl)

Challenge:	despite significant progress, full-duplex SLMs are constrained by severe modality interference, authors say . modality interferes with acoustic and semantic modeling, making them unintelligent and unnatural . authors propose a hierarchical parameter separation strategy that decouples conflicting modalities in deep layers .
Approach:	They propose a hierarchical parameter separation strategy that decouples conflicting modalities in deep layers while preserving cross-modality coherence via a dedicated semantic alignment channel.
Outcome:	The proposed method significantly advances the state of the art on full-duplex benchmarks . it decouples conflicting modalities in deep layers while preserving cross-modality coherence .

Copied to clipboard

Shuhe Wang, Yuxian Meng, Rongbin Ouyang, Jiwei Li, Tianwei Zhang, Lingjuan Lyu, Guoyin Wang

ReFreeKV: Towards Threshold-Free KV Cache Compression (2026.findings-acl)

Challenge:	Existing sequence labeling algorithms can be decomposed into two parts .
Approach:	They propose a graph neural networks sequence labeling (GNN-SL) that augments the vanilla SL model output with similar tagging examples retrieved from the whole training set.
Outcome:	The proposed model performs well on three sequence labeling tasks.

Copied to clipboard

Xuanfan Ni, Liyan Xu, Chenyang Lyu, Longyue Wang, Mo Yu, Lemao Liu, Fandong Meng, Jie Zhou, Piji Li

Do LLMs Catch Their Own Mistakes? A Comprehensive Benchmark for Reflective Tool Use LLMs (2026.findings-acl)

Challenge:	Towards the KV cache efficiency, we propose a new objective that lifts the threshold constraints for robust KV compression.
Approach:	They propose a method that adjusts KV cache budgets while preserving full-cache performance.
Outcome:	The proposed method can reduce memory consumption while preserving full-cache performance.

Copied to clipboard

Zheyuan Liu, Liqiang Xiao, Yang Li, Hyokun Yun, Lihong Li, Chao Zhang, Meng Jiang

Enhancing Conversational Search: Large Language Model-Aided Informative Query Rewriting (2023.findings-emnlp)

Challenge:	Existing benchmarks primarily evaluate planning and execution success, overlooking the self-reflective dimension of tool use.
Approach:	They propose a benchmark to assess LLMs’ self-reflective reasoning in tool-augmented multi-turn dialogues.
Outcome:	The proposed benchmark covers 10 domains with 88 distinct APIs and 968 annotated dialogues, systematically injecting diverse error types arising from both user and assistant behavior.

Copied to clipboard

Fanghua Ye, Meng Fang, Shenghui Li, Emine Yilmaz

Is Word Segmentation Necessary for Deep Learning of Chinese Representations? (P19-1)

Challenge:	Existing approaches to rewrite context-dependent queries lack sufficient information for optimal retrieval performance.
Approach:	They propose to use large language models (LLMs) as query rewriters to generate informative queries through well-designed instructions.
Outcome:	The proposed approach improves performance on the QReCC dataset compared to human rewrites .

Copied to clipboard

Xiaoya Li, Yuxian Meng, Xiaofei Sun, Qinghong Han, Arianna Yuan, Jiwei Li

Representation Learning

Challenge:	Using word-based models, we compare word-oriented models with char-based ones . word-driven models are more vulnerable to data sparsity and the presence of out-of-vocabulary words .
Approach:	They benchmark word-based models with char-based model which does not involve word segmentation in four NLP benchmark tasks.
Outcome:	The proposed model outperforms char-based models in four NLP benchmark tasks.

One QuantLLM for ALL: Fine-tuning Quantized LLMs Once for Efficient Deployments (2025.acl-long)

Copied to clipboard

Ke Yi, Yuhui Xu, Heng Chang, Yuan Meng, Tong Zhang, Jia Li

Dependency Parsing as MRC-based Span-Span Prediction (2022.acl-long)

Challenge:	Quantization has shown promise for Large Language Models, but current methods require lengthy training to alleviate quantization loss.
Approach:	They propose to decouple weights and incorporate Low-Rank adapters to reduce weight sharing . they validate the approach on LLaMA2 families and Mistral on downstream evaluation .
Outcome:	The proposed approach shows high performance while reducing deployment time faced with multiple scenarios.

Copied to clipboard

Leilei Gan, Yuxian Meng, Kun Kuang, Xiaofei Sun, Chun Fan, Fei Wu, Jiwei Li

Syntactic Text Processing

Challenge:	Existing methods for dependency parsing address the issue that edges should be constructed at the text span/subtree level rather than word level.
Approach:	They propose a method that constructs dependency trees by directly modeling span-span relations by modeling subtree-subtree relationships.
Outcome:	The proposed method constructs dependency trees by modeling span-span relations . it can retrieve missing spans in the span proposal stage, which leads to higher recall .

MalURLBench: A Benchmark Evaluating Agents’ Vulnerabilities When Processing Web URLs (2026.findings-acl)

Copied to clipboard

Dezhang Kong, Zhuxi Wu, Shiqi Liu, ZhiCheng Tan, Kuichen Lu, Minghao Li, Qichen Liu, Shengyu Chu, Zhenhua Xu, Xuan Liu, Meng Han

The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit (2025.acl-long)

Challenge:	Existing models struggle to detect elaborately disguised malicious URLs, despite their ability to process malicious URL's.
Approach:	They propose a benchmark to evaluate LLMs’ vulnerabilities to malicious URLs and a lightweight defense module to mitigate the vulnerability.
Outcome:	The proposed framework analyzes 61,845 attack instances spanning 10 real-world scenarios and 7 categories of real malicious websites.

Copied to clipboard

Huixue Zhou, Hengrui Gu, Zaifu Zhan, Xi Liu, Kaixiong Zhou, Yongkang Xiao, Mingfu Liang, Srinivas Prasad Govindan, Piyush Chawla, Jiyan Yang, Xiangfei Meng, Huayu Li, Buyun Zhang, Liang Luo, Wen-Yen Chen, Yiping Han, Bo Long, Rui Zhang, Tianlong Chen

Aligning Large Language Models with Implicit Preferences from User-Generated Content (2025.acl-long)

Challenge:	Existing frameworks for Large Language Models (LLMs) for Click-Through Rate prediction require a careful balance between computational efficiency and predictive accuracy.
Approach:	They propose a framework that integrates Retrieval-Augmented Generation with a novel multi-head early exit architecture to address both challenges.
Outcome:	The proposed framework reduces retrieval time while maintaining high model performance.

Copied to clipboard

Zhaoxuan Tan, Zheng Li, Tianyi Liu, Haodong Wang, Hyokun Yun, Ming Zeng, Pei Chen, Zhihan Zhang, Yifan Gao, Ruijie Wang, Priyanka Nigam, Bing Yin, Meng Jiang

AdaTooler-V: Adaptive Tool-Use for Images and Videos (2026.findings-acl)

Challenge:	Existing preference learning methods rely heavily on curated data from humans or advanced LLMs, which is costly and difficult to scale.
Approach:	They propose a framework that leverages implicit preferences in unlabeled user-generated content to generate preference data.
Outcome:	The proposed framework transforms user-generated content into user queries and generates responses from the policy model.

Copied to clipboard

Chaoyang Wang, Kaituo Feng, Dongyang Chen, Zhongyu Wang, Zhixun Li, Sicheng Gao, Meng Meng, Xu Zhou, Manyuan Zhang, Yuzhang Shang, Xiangyu Yue

Cross-layer Attention Sharing for Pre-trained Large Language Models (2026.tacl-1)

Challenge:	Existing models exhibit blind tool-use reasoning patterns, which significantly increases inference overhead and degrades model performance.
Approach:	They propose an MLLM that performs adaptive tool-use by determining whether a visual problem truly requires tools.
Outcome:	The proposed model outperforms existing methods in visual reasoning tasks.

Copied to clipboard

Yongyu Mu, Yuzhang Wu, Yuchun Fan, Chenglong Wang, Hengyu Li, Jiali Zeng, Qiaozhi He, Murun Yang, Fandong Meng, Jie Zhou, Tong Xiao, Jingbo Zhu

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

Challenge:	Existing studies focus on compressing the Key-Value cache or grouping attention heads, while overlooking redundancy between layers.
Approach:	They propose a lightweight substitute for self-attention in well-trained LLMs that uses feed-forward networks to align attention heads between adjacent layers and low-rank matrices to approximate differences in layer-wise attention weights.
Outcome:	The proposed model reduces redundancy by sharing weights across layers while maintaining high response quality while reducing redundant calculations within 53% 84% of the total layers.

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

MEMD: A Diversity-Promoting Learning Framework for Short-Text Conversation (C18-1)

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

Meng Zou, Xihan Li, Haokun Liu, Zhihong Deng

CofeNet: Context and Former-Label Enhanced Net for Complicated Quotation Extraction (2022.coling-1)

Challenge:	Neural encoder-decoder models tend to generate meaningless and generic responses regardless of what the input text is.
Approach:	They propose an easy-to-extend learning framework based on latent vectors to provide training guidance without resorting to extra data or complicating network’s inner structure.
Outcome:	The proposed framework improves the quality of generated responses according to automatic metrics and human evaluations, yielding more diverse and smooth replies.

Copied to clipboard

Yequan Wang, Xiang Li, Aixin Sun, Xuying Meng, Huaming Liao, Jiafeng Guo

VCB Bench: An Evaluation Benchmark for Audio-Grounded Large Language Model Conversational Agents (2026.findings-acl)

Challenge:	Existing solutions for quotation extraction use rule-based approaches and sequence labeling models.
Approach:	They propose a Context and Former-Label Enhanced Net for quotation extraction.
Outcome:	The proposed method achieves state-of-the-art performance on complicated quotation extraction on two public datasets and one proprietary dataset.

Copied to clipboard

Jiliang Hu, Wenfu Wang, Zuchao Li, Chenxing Li, Yiyang Zhao, Hanzhao Li, Liqiang Zhang, Meng Yu, Dong Yu

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

Challenge:	despite advances in multimodal conversational systems, current benchmarks lack comprehensive evaluation across key dimensions.
Approach:	They propose a Chinese benchmark built exclusively on real human speech to fill this gap . they assess LALMs across three complementary axes: instruction following, knowledge understanding, robustness .
Outcome:	VCB Bench assesses LALMs across three complementary axes: instruction following, knowledge understanding, and robustness . VCBM Bench provides reproducible and fine-grained framework for Chinese voice chat bots . results show significant performance disparities and offer tangible insights for future improvements .

Copied to clipboard

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

Self-supervised Regularization for Text Classification (2021.tacl-1)

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 Zhou, Zechen Li, Pengtao Xie

Adaptive Query Rewriting: Aligning Rewriters through Marginal Probability of Conversational Answers (2024.emnlp-main)

Challenge:	Text classification models are prone to overfitting when limited texts are available for training.
Approach:	They propose a data-dependent regularization approach based on self-supervised learning . they define auxiliary tasks on input data without using human-provided labels .
Outcome:	Experiments on 17 text classification datasets demonstrate the effectiveness of the proposed method.

Copied to clipboard

Tianhua Zhang, Kun Li, Hongyin Luo, Xixin Wu, James Glass, Helen Meng

E-ConvRec: A Large-Scale Conversational Recommendation Dataset for E-Commerce Customer Service (2022.lrec-1)

Challenge:	Existing methods to incorporate retriever’s preference during the training of query rewriting models rely on extensive annotations such as in-domain rewrites and/or relevant passage labels, limiting their generalization and adaptation capabilities.
Approach:	They propose a framework for training query rewriting models with limited rewrite annotations from seed datasets and completely no passage label.
Outcome:	The proposed approach decontexualizes conversational queries into self-contained questions suitable for off-the-shelf retrievers.

Copied to clipboard

Meihuizi Jia, Ruixue Liu, Peiying Wang, Yang Song, Zexi Xi, Haobin Li, Xin Shen, Meng Chen, Jinhui Pang, Xiaodong He

Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoders (2025.emnlp-main)

Challenge:	Recent research has focused on developing conversational recommendation system (CRS), which provides valuable recommendations to users through conversations.
Approach:	They construct an authentic Chinese dialogue dataset consisting of over 25k dialogues and 770k utterances, which contains user profile, product knowledge base, and multiple sequential real conversations between users and recommenders.
Outcome:	The proposed dataset contains user profile, product knowledge base, and multiple sequential real conversations between users and recommenders.

Copied to clipboard

Weiqiao Shan, Yuang Li, Yuhao Zhang, Yingfeng Luo, Chen Xu, Xiaofeng Zhao, Long Meng, Yunfei Lu, Min Zhang, Hao Yang, Tong Xiao, JingBo Zhu

Infinity-Parser: Layout-Aware Reinforcement Learning with High-quality Document Parsing Dataset (2026.findings-acl)

Challenge:	Existing work on integrating audio encoders with large language models (LLMs) has focused on semantic understanding tasks, but different tasks may require distinct features that emphasize either semantic or acoustic aspects.
Approach:	They propose to use a prompt-aware mixture to enhance the Speech LLM that uses multiple audio encoders to extract different features based on the prompt.
Outcome:	The proposed approach outperforms all single-encoder Speech LLMs on ASR, speaker number verification, and AC tasks.

Copied to clipboard

Baode Wang, Biao Wu, Weizhen Li, Meng Fang, Zuming Huang, Jun Huang, Yanjie Liang, Haozhe Wang, Ling Chen, Wei Chu, Yuan Qi

DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation (2026.acl-long)

Challenge:	Existing supervised fine-tuning methods struggle to generalize across document types, leading to poor performance.
Approach:	They propose layoutRL, a reinforcement learning framework that optimizes layout understanding through composite rewards integrating normalized edit distance, paragraph count accuracy, and reading order preservation.
Outcome:	The proposed model outperforms specialized document parsing systems and general-purpose vision-language models on a broad range of document types, languages, and structural complexities.

Copied to clipboard

Li Huang, Zhongxin Liu, Yifan Wu, Tao Yin, Dong li, Jichao Bi, Nankun Mu, Hongyu Zhang, Meng Yan

Programming Languages in NLP

Challenge:	Large Language Models (LLMs) can replicate insecure patterns from training data.
Approach:	They propose a framework that leverages distributed security-relevant cues by aggregating representations from multiple upper layers via an attention-based module.
Outcome:	Experiments show that the framework improves the secure-and-correct generation rate by 11.9% over baselines.

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

Harvesting Events from Multiple Sources: Towards a Cross-Document Event Extraction Paradigm (2024.findings-acl)

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

Qiang Gao, Zixiang Meng, Bobo Li, Jun Zhou, Fei Li, Chong Teng, Donghong Ji

The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool Hallucination (2026.acl-long)

Challenge:	Document-level event extraction aims to extract structured information from unstructured text.
Approach:	They propose a cross-document event extraction pipeline that integrates event information from multiple documents and provides a comprehensive perspective on events.
Outcome:	The proposed pipeline achieves about 72% F1 in end-to-end cross-document event extraction, setting up a benchmark for future research.

Copied to clipboard

Chenlong Yin, Zeyang Sha, Shiwen Cui, Changhua Meng, Zechao Li

ResoFilter: Fine-grained Synthetic Data Filtering for Large Language Models through Data-Parameter Resonance Analysis (2025.findings-naacl)

Challenge:	Recent studies suggest that strengthening reasoning often coincides with increased hallucination . however, no prior work has examined whether reasoning enhancement itself causes tool hallucinism .
Approach:	They propose a diagnostic benchmark measuring tool hallucination in two failure modes . they demonstrate a causal relationship between enhancing reasoning and tool hallubulation .
Outcome:	The proposed benchmark measures tool hallucination in two failure modes: no tool available, and (ii) only distractor tools available.

Copied to clipboard

Zeao Tu, Xiangdi Meng, Yu He, Zihan Yao, Tianyu Qi, Jun Liu, Ming Li

Leveraging the Power of Large Language Models in Entity Linking via Adaptive Routing and Targeted Reasoning (2025.emnlp-industry)

Challenge:	Existing methods for enhancing large language models lack clear metrics for evaluating data characteristics.
Approach:	They propose a method that integrates models, data, and tasks to refine datasets.
Outcome:	The proposed method achieves comparable results to full-scale fine-tuning using only half the data in mathematical tasks and exhibits strong generalization across different models and domains.

Copied to clipboard

Yajie Li, Albert Galimov, Mitra Datta Ganapaneni, Pujitha Thejaswi, De Meng, Priyanshu Kumar, Saloni Potdar

Control Large Language Models via Divide and Conquer (2024.emnlp-main)

Challenge:	Entity Linking (EL) relies on large labeled datasets and extensive fine-tuning . lexical ambiguity, knowledge-intensive cases and low-context mentions are some of the challenges.
Approach:	Entity Linking (EL) relies on large annotated datasets and extensive fine-tuning . authors propose a pipeline that integrates candidate generation, context-based scoring, adaptive routing, and selective reasoning .
Outcome:	ARTER outperforms ReFinED and LLM-based pipelines on standard benchmarks . it performs twice as efficiently on 5 out of 6 datasets and doubles the number of tokens compared to pipelines using LLM .

Copied to clipboard

Bingxuan Li, Yiwei Wang, Tao Meng, Kai-Wei Chang, Nanyun Peng

IHEval: Evaluating Language Models on Following the Instruction Hierarchy (2025.naacl-long)

Challenge:	Lexically Constrained Generation (LCG) is a crucial task of text generation.
Approach:	They propose a Divide and Conquer Generation strategy to enhance LLMs' performance in Lexically Constrained Generation with prompt-based controlling.
Outcome:	The proposed strategy shows 90% improvement on the most challenging LCG task.

Copied to clipboard

Zhihan Zhang, Shiyang Li, Zixuan Zhang, Xin Liu, Haoming Jiang, Xianfeng Tang, Yifan Gao, Zheng Li, Haodong Wang, Zhaoxuan Tan, Yichuan Li, Qingyu Yin, Bing Yin, Meng Jiang

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

Challenge:	Instruction-tuned language models (LMs) are increasingly deployed as interactive services across various applications.
Approach:	They propose a benchmark to evaluate models' ability to follow the instruction hierarchy by comparing their models to a set of benchmarks.
Outcome:	The proposed benchmark covers 3,538 examples across nine tasks covering cases where instructions in different priorities either align or conflict.

Copied to clipboard

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

Revisiting Catastrophic Forgetting in Large Language Model Tuning (2024.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

Hongyu Li, Liang Ding, Meng Fang, Dacheng Tao

Instant Personalized Large Language Model Adaptation via Hypernetwork (2026.acl-long)

Challenge:	Catastrophic Forgetting (CF) compromises the effectiveness of large language models during fine-tuning, yet the underlying causes of CF remain largely unexplored.
Approach:	They propose a method to flatten the model loss landscape to mitigate CF by flattening the loss landscape.
Outcome:	The proposed method complements existing anti-forgetting strategies, further enhancing the resistance of LLMs to CF.

Copied to clipboard

Zhaoxuan Tan, Zixuan Zhang, Haoyang Wen, Zheng Li, Rongzhi Zhang, Pei Chen, Fengran Mo, Zheyuan Liu, Qingkai Zeng, Qingyu Yin, Meng Jiang

AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-Playing (2026.findings-acl)

Challenge:	Existing parameter-efficient fine-tuning methods require training a separate adapter for each user, making them computationally expensive and impractical for real-time updates.
Approach:	They propose a scalable framework that maps a user's profile directly to a full set of adapter parameters.
Outcome:	The proposed framework outperforms prompt-based personalization and OPPU while using substantially fewer computational resources at deployment.

Copied to clipboard

Zhenhua Xu, Dongsheng Chen, Shuo Wang, Jian Li, Chengjie Wang, Meng Han, Yabiao Wang

Challenge:	Existing LLMs lack immersion and adaptability, resulting in limited character orchestration and on-the-fly character introduction.
Approach:	They propose an LLM-based framework that allows actors to interact with users in an ongoing narrative.
Outcome:	The proposed framework outperforms commercial LLMs in character consistency, environment grounding, and narrative coherence.

UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations (2025.acl-long)

Copied to clipboard

Fengran Mo, Yifan Gao, Chuan Meng, Xin Liu, Zhuofeng Wu, Kelong Mao, Zhengyang Wang, Pei Chen, Zheng Li, Xian Li, Bing Yin, Meng Jiang

Exploring Conditional Variational Mechanism to Pinyin Input Method for Addressing One-to-Many Mappings in Low-Resource Scenarios (2024.acl-short)

Challenge:	Existing conversational search systems are usually built with two different models . this separation restricts the system from leveraging the model's intrinsic knowledge simultaneously . Existing studies for developing unified models cannot fully address the aspects of understanding conversational context, managing retrieval independently, and generating responses.
Approach:	They propose to unify dense retrieval and response generation for large language models in conversation by fine-tuning and mitigating data discrepancy.
Outcome:	The proposed model can outperform existing models on five conversational search datasets and reduce inconsistency risks while mitigating data discrepancy.

Copied to clipboard

Bin Sun, Jianfeng Li, Hao Zhou, Fandong Meng, Kan Li, Jie Zhou

A Dashboard for Mitigating the COVID-19 Misinfodemic (2021.eacl-demos)

Challenge:	Experimental results demonstrate the superior performance of our method.
Approach:	They propose to leverage conditional variational mechanism to simplify pinyin IME . they employ a strategy that facilitates interaction between pinyan and Chinese character information .
Outcome:	The proposed method improves the performance of pinyin input method engine (IME) under low-resource conditions.

Copied to clipboard

Zhengyuan Zhu, Kevin Meng, Josue Caraballo, Israa Jaradat, Xiao Shi, Zeyu Zhang, Farahnaz Akrami, Haojin Liao, Fatma Arslan, Damian Jimenez, Mohanmmed Samiul Saeef, Paras Pathak, Chengkai Li

Incremental Transformer with Deliberation Decoder for Document Grounded Conversations (P19-1)

Challenge:	a new public dashboard aims to understand the impact of the COVID-19 misinfodemic on Twitter . the dashboard uses a curated catalog of COVId-19 related facts and debunks of misinformation .
Approach:	They propose a public dashboard that matches tweets with COVID-19 misinformation . they also propose experiments to analyze the spread of misinformation on twitter .
Outcome:	The proposed dashboard uses a curated catalog of COVID-19 related facts and debunks misinformation . it shows the most prevalent information from the catalog among Twitter users in user-selected geographic regions .

Copied to clipboard

Zekang Li, Cheng Niu, Fandong Meng, Yang Feng, Qian Li, Jie Zhou

ConRPG: Paraphrase Generation using Contexts as Regularizer (2021.emnlp-main)

Challenge:	Existing dialogue systems do not exploit document knowledge effectively enough.
Approach:	They propose a Transformer-based architecture for document grounded conversations that incorporates document knowledge into a two-pass decoder to improve context coherence and knowledge correctness.
Outcome:	The proposed model outperforms baselines on context coherence and knowledge relevance on a real-world document grounded dataset.

Copied to clipboard

Yuxian Meng, Xiang Ao, Qing He, Xiaofei Sun, Qinghong Han, Fei Wu, Chun Fan, Jiwei Li

Evaluating Readability and Faithfulness of Concept-based Explanations (2024.emnlp-main)

Challenge:	Existing methods for paraphrase generation lack reliable supervision signals.
Approach:	They propose an unsupervised paradigm for paraphrase generation based on contextual language models, candidate filtering and paraphrase model training based upon the selected candidates.
Outcome:	The proposed paradigm outperforms existing paraphrase generation methods in supervised and unsupervised setups.

Copied to clipboard

Meng Li, Haoran Jin, Ruixuan Huang, Zhihao Xu, Defu Lian, Zijia Lin, Di Zhang, Xiting Wang

Explainability & Interpretability in NLP

Challenge:	Existing methods for evaluating concepts from different perspectives lack a unified formalization.
Approach:	They propose a formal definition of concepts generalizing to diverse concept-based explanations’ settings and apply it to other types of explanations or tasks.
Outcome:	Extensive experimental analysis was carried out to determine the evaluation measures for explanation evaluation measures.

MentalGLM Series: Explainable Large Language Models for Mental Health Analysis on Chinese Social Media (2025.emnlp-main)

Copied to clipboard

Wei Zhai, Nan Bai, Qing Zhao, Jianqiang Li, Fan Wang, Hongzhi Qi, Meng Jiang, Xiaoqin Wang, Bing Xiang Yang, Guanghui Fu

Two Parents, One Child: Dual Transfer for Low-Resource Neural Machine Translation (2021.findings-acl)

Challenge:	Social media is a key platform for emotional expression, yet deep learning lacks flexibility and interpretability.
Approach:	They propose to use Chinese social media to train interpretable mental health instruction datasets to test models' ability to explain their decisions.
Outcome:	The proposed models outperform deep learning and LLMs on three mental health downstream tasks and demonstrate their potential for clinical applications.

Copied to clipboard

Meng Zhang, Liangyou Li, Qun Liu

PunchBench: Benchmarking MLLMs in Multimodal Punchline Comprehension (2025.acl-long)

Challenge:	Neural machine translation suffers when parallel data is scarce for training . a new framework to transfer multiple sources of auxiliary data is proposed .
Approach:	They propose a framework to transfer multiple sources of auxiliary data from high-resource parallel data to low-resourced translation models using pretrained language models.
Outcome:	The proposed approach yields consistent improvements over strong competitors for multiple translation directions.

Copied to clipboard

Kun Ouyang, Yuanxin Liu, Shicheng Li, Yi Liu, Hao Zhou, Fandong Meng, Jie Zhou, Xu Sun

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

Challenge:	Existing benchmarks on punchline comprehension suffer from language shortcuts that allow models to rely on text, lack of question diversity, and narrow focus on a specific domain of multimodal content.
Approach:	They propose a multimodal punchline comprehension benchmark to assess models' ability to comprehend punchlines.
Outcome:	The proposed model surpasses in-context learning and chain-of-thought in punchline comprehension.

Copied to clipboard

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

AVG-LLaVA: An Efficient Large Multimodal Model with Adaptive Visual Granularity (2025.findings-acl)

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

Zhibin Lan, Liqiang Niu, Fandong Meng, Wenbo Li, Jie Zhou, Jinsong Su

CHBias: Bias Evaluation and Mitigation of Chinese Conversational Language Models (2023.acl-long)

Challenge:	Existing large multimodal models typically divide high-resolution images into multiple local images and a global image, leading to a large number of visual tokens.
Approach:	They propose an LMM that can adaptively select the appropriate visual granularity based on the input image and instruction.
Outcome:	The proposed model significantly reduces visual tokens and speeds up inference on 11 benchmarks.

Copied to clipboard

Jiaxu Zhao, Meng Fang, Zijing Shi, Yitong Li, Ling Chen, Mykola Pechenizkiy

Beyond Single Frames: Can LMMs Comprehend Implicit Narratives in Comic Strip? (2025.findings-emnlp)

Challenge:	Existing studies on social biases in language models have focused on only English.
Approach:	They propose to use a Chinese dataset for bias evaluation and mitigation of Chinese conversational language models.
Outcome:	The proposed dataset includes under-explored bias categories, such as ageism and appearance biases, which received less attention in previous studies.

Copied to clipboard

Xiaochen Wang, Heming Xia, Jialin Song, Longyu Guan, Qingxiu Dong, Rui Li, Yixin Yang, Yifan Pu, Weiyao Luo, Yiru Wang, Xiangdi Meng, Wenjie Li, Zhifang Sui

Enhancing Cross-lingual Prompting with Dual Prompt Augmentation (2023.findings-acl)

Challenge:	Large Multimodal Models have demonstrated strong performance on vision-language benchmarks, yet current evaluations focus on single-image reasoning.
Approach:	STRIPCIPHER is a benchmark designed to evaluate model ability on understanding implicit narratives in silent comics.
Outcome:	STRIPCIPHER is a high-quality, human-annotated dataset featuring fine-grained annotations and comprehensive coverage of varying difficulty levels.

Copied to clipboard

Meng Zhou, Xin Li, Yue Jiang, Lidong Bing

Turn-PPO: Turn-Level Advantage Estimation with PPO for Improved Multi-Turn RL in Agentic LLMs (2026.findings-eacl)

Challenge:	a recent study shows that prompting is superior for multilingual/cross-lingual problems . despite its effectiveness on English tasks, its potential for cross-lingual problem is under-explored .
Approach:	They propose a framework for prompting that can be used to augment cross-lingual prompts.
Outcome:	The proposed framework achieves 46.54% with only 16 English training examples per class, significantly better than fine-tuning.

Copied to clipboard

Junbo Li, Peng Zhou, Rui Meng, Meet P. Vadera, Lihong Li, Yang Li

Tackling Modality Heterogeneity with Multi-View Calibration Network for Multimodal Sentiment Detection (2023.acl-long)

Challenge:	Reinforcement learning (RL) has re-emerged as a natural approach for training interactive LLM agents in real-world environments.
Approach:	They propose a variant that operates on a turn-level MDP formulation, instead of the commonly used token-level one.
Outcome:	The proposed method is more robust than the widely used GRPO algorithm and more efficient than token-level MDPs.

Copied to clipboard

Yiwei Wei, Shaozu Yuan, Ruosong Yang, Lei Shen, Zhangmeizhi Li, Longbiao Wang, Meng Chen

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

Challenge:	Existing studies focus on fusing different features but ignore the challenge of modality heterogeneity.
Approach:	They propose a text-guided fusion module with novel Sparse-Attention to reduce the negative impacts of redundant visual elements and a sentiment-based congruity constraint task to calibrate the feature shift in the representation space.
Outcome:	The proposed model is competitive against existing methods and achieves state-of-the-art results on two public benchmark datasets.

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

DocLens: A Tool-Augmented Multi-Agent Framework for Long Visual Document Understanding (2026.acl-long)

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

Dawei Zhu, Rui Meng, Jiefeng Chen, Sujian Li, Tomas Pfister, Jinsung Yoon

Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection (2022.findings-emnlp)

Challenge:	Existing approaches to localizing evidence from long visual documents fail on a fundamental challenge: evidence localization.
Approach:	They propose a tool-augmented multi-agent framework that “zooms in” on evidence like a lens.
Outcome:	The proposed framework achieves state-of-the-art performance on MMLongBench-Doc and FinRAGBench-V, surpassing even human experts.

Copied to clipboard

Lanrui Wang, Jiangnan Li, Zheng Lin, Fandong Meng, Chenxu Yang, Weiping Wang, Jie Zhou

Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates (2025.emnlp-main)

Challenge:	Empathy is a key trait of everyday human conversations.
Approach:	They propose a serial encoding and Emotion-Knowledge interaction method for empathetic dialogue generation which is more sensitive to emotion dynamics in conversations.
Outcome:	The proposed method outperforms baseline evaluations on the utterance-level annotated EMPATHETICDIALOGUES.

Copied to clipboard

Hy Dang, Tianyi Liu, Zhuofeng Wu, Jingfeng Yang, Haoming Jiang, Tao Yang, Pei Chen, Zhengyang Wang, Helen Wang, Huasheng Li, Bing Yin, Meng Jiang

Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding (2023.acl-long)

Challenge:	Large language models (LLMs) have strong reasoning and tool-use capabilities, yet fail in real-world tool-interactions due to incorrect parameterization, poor tool selection, or misinterpretation of user intent.
Approach:	They propose a curriculum-inspired framework that leverages structured reasoning templates to guide LLMs through more deliberate step-by-step instructions for generating function calls.
Outcome:	The proposed framework reduces tool-use errors and improves interpretability and transparency of tool-using agents.

Copied to clipboard

Haoli Bai, Zhiguang Liu, Xiaojun Meng, Li Wentao, Shuang Liu, Yifeng Luo, Nian Xie, Rongfu Zheng, Liangwei Wang, Lu Hou, Jiansheng Wei, Xin Jiang, Qun Liu

Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation (2024.emnlp-main)

Challenge:	Existing solutions for visual document understanding lack granularity of document textlines.
Approach:	They propose a supervised pre-training program to leverage structural knowledge nested in document textlines to achieve fine-grained alignment between visual regions and texts.
Outcome:	The proposed system performs better on various VDU tasks in English and Chinese.

Copied to clipboard

Yuan Ge, Yilun Liu, Chi Hu, Weibin Meng, Shimin Tao, Xiaofeng Zhao, Mahong Xia, Zhang Li, Boxing Chen, Hao Yang, Bei Li, Tong Xiao, JingBo Zhu

RankNAS: Efficient Neural Architecture Search by Pairwise Ranking (2021.emnlp-main)

Challenge:	Existing methods for instruction data selection have limitations such as relying on fragile external APIs, being affected by biases in GPT models, or reducing the diversity of the selected instruction dataset.
Approach:	They propose an industrial-friendly, expert-aligned and diversity-preserved instruction data selection method: Clustering and Ranking (CaR).
Outcome:	The proposed method outperforms Alpaca's existing methods by 32.1% in GPT-4 evaluations.

Copied to clipboard

Chi Hu, Chenglong Wang, Xiangnan Ma, Xia Meng, Yinqiao Li, Tong Xiao, Jingbo Zhu, Changliang Li

What is Stigma Attributed to? A Theory-Grounded, Expert-Annotated Interview Corpus for Demystifying Mental-Health Stigma (2025.acl-long)

Challenge:	Existing methods require training millions of architectures to estimate the accuracy of the search results.
Approach:	They propose a performance ranking method (RankNAS) that uses pairwise ranking and search space pruning to enlarge the search space.
Outcome:	The proposed method significantly accelerates NAS through pairwise ranking and search space pruning.

Copied to clipboard

Han Meng, Yancan Chen, Yunan Li, Yitian Yang, Jungup Lee, Renwen Zhang, Yi-Chieh Lee

Linguistic Theories

Challenge:	Existing resources for training neural models to finely classify mental-health stigma are limited, relying primarily on social media or synthetic data without theoretical underpinnings.
Approach:	They propose to use an expert-annotated corpus of human-chatbot interviews to finely classify mental-health stigma.
Outcome:	The proposed corpus can facilitate research on computationally detecting, neutralizing, and counteracting mental-health stigma.

An MRC Framework for Semantic Role Labeling (2022.coling-1)

Copied to clipboard

Nan Wang, Jiwei Li, Yuxian Meng, Xiaofei Sun, Han Qiu, Ziyao Wang, Guoyin Wang, Jun He

Semantic Parsing

Challenge:	Existing work on semantic role labels ignores the semantic connection between the two tasks . et al. (2010) defined two types of semantic roles: core roles and non-core roles.
Approach:	They propose to use machine reading comprehension to bridge the gap between these two tasks . they formalize predicate disambiguation as multiple-choice machine reading understanding .
Outcome:	The proposed framework achieves state-of-the-art or comparable results to previous work . it uses the descriptions of candidate senses of a given predicate as options to select the correct sense .

From Observation to Understanding: Front-Door Adjustments with Uncertainty Calibration for Enhancing Egocentric Reasoning in LVLMs (2025.findings-acl)

Copied to clipboard

Shenshen Li, Wenxin Meng, Lei Wang, Hao Yang, Chong Peng, Peng Yan, Fumin Shen, Jingkuan Song, Heng Tao Shen, Xing Xu

Optimal Transport-Based Token Weighting scheme for Enhanced Preference Optimization (2025.acl-long)

Challenge:	Existing methods that adapt LVLMs to egocentric tasks overlook critical agent-environment interactions, limiting their ability to perform egoic reasoning.
Approach:	They propose a zero-shot paradigm to enhance egocentric reasoning by simulating human causal reasoning by formalizing ego-centric reasoning using a structural causal model.
Outcome:	The proposed method improves egocentric reasoning abilities on six tasks.

Copied to clipboard

Meng Li, Guangda Huzhang, Haibo Zhang, Xiting Wang, Anxiang Zeng

Challenge:	Existing methods for direct preference optimization assign equal importance to all tokens while humans focus on more meaningful parts.
Approach:	They propose to use a transport-based token weighting scheme to enhance direct preference optimization by emphasizing meaningful token pairs and de-emphasizing less relevant ones to yield a more contrastive reward difference estimate.
Outcome:	Extensive experiments have validated the proposed method in improving instruction-following ability across various settings.

Enhancing Argument Structure Extraction with Efficient Leverage of Contextual Information (2023.findings-emnlp)

Copied to clipboard

Yun Luo, Zhen Yang, Fandong Meng, Yingjie Li, Jie Zhou, Yue Zhang

Self Question-answering: Aspect-based Sentiment Analysis by Role Flipped Machine Reading Comprehension (2021.findings-emnlp)

Challenge:	Argument structure extraction (ASE) aims to identify the discourse structure of arguments within documents.
Approach:	They propose an Efficient Context-aware ASE model that fully exploits contextual information by augmenting modeling capacity and augmenting training data.
Outcome:	The proposed model can extract argumentative discourse structure from documents and reduce reliance on specific words or less informative sentences.

Copied to clipboard

Guoxin Yu, Jiwei Li, Ling Luo, Yuxian Meng, Xiang Ao, Qing He

Learning from Committee: Reasoning Distillation from a Mixture of Teachers with Peer-Review (2025.findings-acl)

Challenge:	unified Aspect-based Sentiment Analysis (ABSA) aims to couple aspect terms with their corresponding opinion terms, which might make it easier to predict sentiment polarities.
Approach:	They propose a new paradigm to pair aspect terms with their corresponding opinion terms . they propose to use a machine learning paradigm to solve the unified ABSA task .
Outcome:	The proposed framework can solve the ABSA task without any additional data annotation or transformation.

Copied to clipboard

Zhuochun Li, Yuelyu Ji, Rui Meng, Daqing He

Towards Unifying Multi-Lingual and Cross-Lingual Summarization (2023.acl-long)

Challenge:	Large language models (LLMs) have proven to be highly effective in addressing a wide range of complex tasks.
Approach:	They propose a method that asks teachers to identify and explain student’s mistakes and then asks them to provide customized instruction learning data.
Outcome:	The proposed method reduces the chance of teachers guessing incorrectly with flawed rationales, improving instructional data quality.

Copied to clipboard

Jiaan Wang, Fandong Meng, Duo Zheng, Yunlong Liang, Zhixu Li, Jianfeng Qu, Jie Zhou

Summarization

Challenge:	Existing work on multilingual summarization and cross-lingual summmarization has been limited due to their different definitions.
Approach:	They propose to unify MLS and CLS into a more general setting, i.e. many-to-many summarization.
Outcome:	The proposed model outperforms the state-of-the-art models in the zero-shot directions.

Generate, Discriminate, Evolve: Enhancing Context Faithfulness via Fine-Grained Sentence-Level Self-Evolution (2025.findings-acl)

Copied to clipboard

Kun Li, Tianhua Zhang, Yunxiang Li, Hongyin Luo, Abdalla Mohamed Salama Sayed Moustafa, Xixin Wu, James R. Glass, Helen M. Meng

Challenge:	Existing methods to improve context faithfulness in large language models are either inadequate or overlook the potential for self-improvement.
Approach:	They propose a framework that enhances context faithfulness through fine-grained sentence-level optimization.
Outcome:	Experiments on ASQA and ConFiQA datasets show that GenDiE surpasses baselines in faithfulness and correctness and exhibits robust performance for domain adaptation.

kFolden: k-Fold Ensemble for Out-Of-Distribution Detection (2021.emnlp-main)

Copied to clipboard

Xiaoya Li, Jiwei Li, Xiaofei Sun, Chun Fan, Tianwei Zhang, Fei Wu, Yuxian Meng, Jun Zhang

Text Classification

Challenge:	Existing studies studying OOD detection in NLP often rely on external data to diversify model predictions.
Approach:	They propose a framework which mimics OOD detection behavior without external data . they take text classification as an archetype and compare them to existing datasets .
Outcome:	The proposed framework can resolve in- and out-distribution examples in a natural way using existing datasets.

Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence (2024.emnlp-main)

Copied to clipboard

Junru Lu, Jiazheng Li, Siyu An, Meng Zhao, Yulan He, Di Yin, Xing Sun

Challenge:	Existing studies attributed verbosity to biased labels, but new research shows that DPO can be effective in mitigating verboses.
Approach:	They propose to use a method to reduce the amount of verbosity in LLMs by using a downsampling approach.
Outcome:	The proposed approach overcomes the problem of verbosity by reducing the length reliance of the proposed algorithm.

APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention (2026.acl-long)

Copied to clipboard

Yuxiang Huang, Mingye Li, Xu Han, Chaojun Xiao, Weilin Zhao, Ao Sun, Ziqi Yuan, Hao Zhou, Fandong Meng, Zhiyuan Liu

XAL: EXplainable Active Learning Makes Classifiers Better Low-resource Learners (2024.naacl-long)

Challenge:	Existing methods for long-video inference use compression or sparse attention . existing methods restrict LMMs from handling longer, more complex videos .
Approach:	They propose a sequence-parallel framework with optimized attention that accelerates long-video inference across multiple GPUs.
Outcome:	The proposed framework delivers speedups of 12.72x, 1.70x, and 1.18x over FlashAttn, ZigZagRing, and APB without significant performance loss.

Copied to clipboard

Yun Luo, Zhen Yang, Fandong Meng, Yingjie Li, Fang Guo, Qinglin Qi, Jie Zhou, Yue Zhang

RIPRAG: Hack a Black-box Retrieval-Augmented Generation Question-Answering System with Reinforcement Learning (2026.findings-acl)

Challenge:	Existing methods for active learning rely on model uncertainty or disagreement to pick unlabeled data, leading to over-confidence in superficial patterns and lack of exploration.
Approach:	They propose to use a bi-directional encoder and a uni-directional decoder to generate and score an explanation for low-resource text classification.
Outcome:	The proposed model improves on 9 strong baselines on six datasets and can generate explanations for its predictions.

Copied to clipboard

Meng Xi, Sihan Lv, Yechen Jin, Guanjie Cheng, Naibo Wang, Ying Li, Jianwei Yin

RAG-Zeval: Enhancing RAG Responses Evaluator through End-to-End Reasoning and Ranking-Based Reinforcement Learning (2025.emnlp-main)

Challenge:	Existing methods to generate RAG documents require knowledge of the target RAG system’s internal composition and implementation details, whereas black-box methods are unable to utilize interactive information.
Approach:	They propose a RIPRAG attack framework that treats the target RAG system as a black box and leverages a Reinforcement Learning from Black-box Feedback (RLBF) method to optimize the generation model for poisoned documents.
Outcome:	The proposed method achieves an attack success rate (ASR) improvement of up to 0.72 compared to baseline methods.

Copied to clipboard

Kun Li, Yunxiang Li, Tianhua Zhang, Hongyin Luo, Xixin Wu, James R. Glass, Helen M. Meng

Language-Coupled Reinforcement Learning for Multilingual Retrieval-Augmented Generation (2026.findings-acl)

Challenge:	Existing evaluation frameworks rely on direct prompting of resource-intensive models with complex multi-stage prompts, introducing significant computational cost and underutilizing models’ reasoning capabilities.
Approach:	They propose a framework that trains evaluators with reinforcement learning to generate comprehensive and sound assessments with detailed explanation in one-pass.
Outcome:	The proposed framework outperforms baseline evaluation frameworks that rely on LLMs with 10-100 more parameters and achieves the strongest correlation with human judgments.

Copied to clipboard

Rui Qi, Fengran Mo, Yufeng Chen, Xue Zhang, Shuo Wang, Hongliang Li, Xu Jinan, Meng Jiang, Jian-Yun Nie, Kaiyu Huang

Multilinguality

Challenge:	Existing approaches to multilingual retrieval-augmented generation (MRAG) use a single-turn retrieval and subsequent optimization to acquire and integrate beneficial external knowledge from multilingual collections.
Approach:	They propose a multilingual search-augmented reinforcement learning framework that integrates a language-coupled Group Relative Policy Optimization into the policy and reward models.
Outcome:	The proposed framework achieves competitive performance and is appropriate for various practical scenarios such as constrained training data and retrieval over collections encompassing a large number of languages.

Fast Nearest Neighbor Machine Translation (2022.findings-acl)

Copied to clipboard

Yuxian Meng, Xiaoya Li, Xiayu Zheng, Fei Wu, Xiaofei Sun, Tianwei Zhang, Jiwei Li

Investigating Cross-Modal Skill Injection: Scenarios, Methods, and Hyperparameters (2026.acl-long)

Challenge:	Fast kNN-MT uses the entire corpus as the datastore for the nearest neighbor search . knn-MT is two-orders slower than vanilla MT models .
Approach:	They propose a fast kNN-MT model that uses the entire corpus as the datastore for nearest neighbor search.
Outcome:	The proposed model is two-orders faster than kNN-MT and is only two times slower than the standard model.

Copied to clipboard

Zhiyu Xu, Lean Wang, Yuanxin Liu, Lei Li, Hao Zhou, Fandong Meng, Jie Zhou, Xu Sun

R.R.: Unveiling LLM Training Privacy through Recollection and Ranking (2025.findings-acl)

Challenge:	Existing research lacks systematic analysis of the applicability and methodology of cross-modal skill injection.
Approach:	They investigate the applicability and methodology of cross-modal skill injection by integrating a domain-expert LLM into a VLM.
Outcome:	The proposed method enables transfer of domain-specific expertise from Large Language Models (LLMs) to VLMs without incurring additional training data requirements or significant computational overhead.

Copied to clipboard

Wenlong Meng, Guo Zhenyuan, Lenan Wu, Chen Gong, Wenyan Liu, Weixian Li, Chengkun Wei, Wenzhi Chen

Let’s Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language Models (2025.findings-acl)

Challenge:	Existing privacy attacks focus on membership inference or data extraction, but reconstructing specific personally identifiable information (PII) in training data remains challenging.
Approach:	They propose a two-step privacy stealing attack that enables attackers to reconstruct PII entities from scrubbed training data where the PI I entities have been masked.
Outcome:	The proposed attack can reconstruct PII entities from scrubbed training data where the PI I entities have been masked.

Copied to clipboard

Kangyang Luo, Zichen Ding, Zhenmin Weng, Lingfeng Qiao, Meng Zhao, Xiang Li, Di Yin, Jinlong Shu

On the Robustness of Document-Level Relation Extraction Models to Entity Name Variations (2024.findings-acl)

Challenge:	Existing efforts to improve CoT prompting have limitations that require extensive human effort or performance needs to be improved.
Approach:	They propose a prompt approach for automatic reasoning called LBS3 inspired by curriculum learning which better reflects human learning habits.
Outcome:	The proposed approach achieves strongly competitive performance compared to baselines in reasoning-intensive tasks with varying open- and closed-source LLMs.

Copied to clipboard

Shiao Meng, Xuming Hu, Aiwei Liu, Fukun Ma, Yawen Yang, Shuang Li, Lijie Wen

Unsupervised Knowledge Selection for Dialogue Generation (2021.findings-acl)

Challenge:	Existing DocRE models which perform well may make more mistakes when merely changing the entity names in the document, hindering the generalization to novel entity names.
Approach:	They propose a pipeline to generate entity-renamed documents by replacing the original entity names with names from Wikidata.
Outcome:	The proposed pipeline generates entity-renamed documents by replacing the original entity names with names from Wikidata.

Copied to clipboard

Xiuyi Chen, Feilong Chen, Fandong Meng, Peng Li, Jie Zhou

C-LLM: Learn to Check Chinese Spelling Errors Character by Character (2024.emnlp-main)

Challenge:	Existing knowledge selection tasks require the preidentified knowledge to generate informative dialogues.
Approach:	They propose a novel method to supervise knowledge selection when the gold knowledge label is unknown by obtaining an oracle knowledge label via distant supervision and leverage knowledge distillation to alleviate the noisy labeling problem of distant supervision.
Outcome:	The proposed method outperforms strong supervised baselines on two knowledge-grounded dialogue datasets and generates more informative responses.

Copied to clipboard

Kunting Li, Yong Hu, Liang He, Fandong Meng, Jie Zhou

Syntactic Text Processing

Challenge:	Chinese Spell Checking (CSC) aims to detect and correct spelling errors in sentences.
Approach:	They propose a Chinese Spell Checking method that learns to check errors Character by Character.
Outcome:	The proposed method achieves a 2.1% enhancement in general scenarios and a significant improvement in vertical domain scenarios compared to existing methods.

MTPChat: A Multimodal Time-Aware Persona Dataset for Conversational Agents (2025.findings-naacl)

Copied to clipboard

Wanqi Yang, Yanda Li, Meng Fang, Ling Chen

Benchmarking Language Model Creativity: A Case Study on Code Generation (2025.naacl-long)

Challenge:	Existing time-aware datasets that focus on persona-grounded conversations focus on temporal dynamics, which narrows their scope and diminishes their complexity.
Approach:	They propose a multimodal, time-aware persona dialogue dataset that integrates linguistic, visual, and temporal elements within dialogue and persona memory.
Outcome:	The proposed framework integrates linguistic, visual, and temporal elements within dialogue and persona memory to assess a model’s ability to understand implicit temporal cues and dynamic interactions.

Copied to clipboard

Yining Lu, Dixuan Wang, Tianjian Li, Dongwei Jiang, Sanjeev Khudanpur, Meng Jiang, Daniel Khashabi

Universal Conditional Masked Language Pre-training for Neural Machine Translation (2022.acl-long)

Challenge:	Recent studies on LLM creativity evaluation focus on open-ended generation tasks . however, the degree to which LLMs possess and utilize creativity for problem-solving remains unclear .
Approach:	They propose a framework for quantifying LLM creativity that incorporates design ingredients . they introduce DENIAL PROMPTING which pushes LLMs to develop more creative solutions .
Outcome:	The proposed framework quantifies creativity in LLMs on Codeforces problems . it also finds that even the most creative model fails to demonstrate human-like creativity .

Copied to clipboard

Pengfei Li, Liangyou Li, Meng Zhang, Minghao Wu, Qun Liu

Multilinguality

Challenge:	Pre-trained sequence-to-sequence models have significantly improved Neural Machine Translation (NMT) this paper demonstrates that pre-training a sequence- to-squence model with a bidirectional decoder can produce notable performance gains for both Autoregressive and Non-autoregressive NMT tasks.
Approach:	They propose a conditional masked language model pre-trained on bilingual and monolingual corpora in many languages.
Outcome:	The proposed model can achieve significant performance improvements on all scenarios from low- to extremely high-resource languages.

Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction (2021.acl-long)

Copied to clipboard

Yaojie Lu, Hongyu Lin, Jin Xu, Xianpei Han, Jialong Tang, Annan Li, Le Sun, Meng Liao, Shaoyi Chen

Internal Value Alignment in Large Language Models through Controlled Value Vector Activation (2025.acl-long)

Challenge:	Existing methods to extract event records from text decompose complex structure prediction task into multiple subtasks.
Approach:	They propose a sequence-to-structure generation paradigm that can extract events from text . they propose unified event extraction, constrained decoding algorithm and curriculum learning algorithm .
Outcome:	The proposed method can achieve competitive performance using record-level annotations in both supervised learning and transfer learning settings.

Copied to clipboard

Haoran Jin, Meng Li, Xiting Wang, Zhihao Xu, Minlie Huang, Yantao Jia, Defu Lian

Premise-based Multimodal Reasoning: Conditional Inference on Joint Textual and Visual Clues (2022.acl-long)

Challenge:	Existing LLMs do not possess consistent values, but many have been developed to align them at the behavioral level, including supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF).
Approach:	They propose a Controlled Value Vector Activation method that directly aligns the internal values of Large Language Models by interpreting how a value is encoded in their latent representations.
Outcome:	The proposed method achieves highest success rate across 10 basic values without hurting model performance and fluency, and ensures target values even with opposite and potentially malicious input prompts.

Copied to clipboard

Qingxiu Dong, Ziwei Qin, Heming Xia, Tian Feng, Shoujie Tong, Haoran Meng, Lin Xu, Zhongyu Wei, Weidong Zhan, Baobao Chang, Sujian Li, Tianyu Liu, Zhifang Sui

On the Word Alignment from Neural Machine Translation (P19-1)

Challenge:	Existing work in vision language cross-modal reasoning uses binary or multi-choice classification based on source image and textual query.
Approach:	They propose a task where a textual premise is the background presumption on each source image.
Outcome:	The proposed task is based on a dataset of 15,360 movie screenshots and human-curated premise templates from 6 pre-defined categories.

Copied to clipboard

Xintong Li, Guanlin Li, Lemao Liu, Max Meng, Shuming Shi

WeTS: A Benchmark for Translation Suggestion (2022.emnlp-main)

Challenge:	Prior researches suggest that neural machine translation (NMT) captures word alignment through its attention mechanism, however, attention may fail to capture word alignment for some NMT models.
Approach:	They propose two methods to induce word alignment which are general and agnostic to specific NMT models.
Outcome:	The proposed methods induce much better word alignment than attention.

Copied to clipboard

Zhen Yang, Fandong Meng, Yingxue Zhang, Ernan Li, Jie Zhou

Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains (2025.acl-long)

Challenge:	Existing studies focus on overall performance of machine translation but ignore TS performance, authors say . if TS is applied into post-editing, it will reduce the time and cost of post-production.
Approach:	They propose to use a golden corpus annotated by experts to generate a translation suggestion model.
Outcome:	The proposed model improves on the golden corpus annotated by translators on four translation directions.

Copied to clipboard

Kun Li, Tianhua Zhang, Xixin Wu, Hongyin Luo, James R. Glass, Helen M. Meng

Structured Data in NLP

Challenge:	Existing research on the utilization of Knowledge Graphs (KGs) for large language models (LLMs) relies on subgraph retriever or iterative prompting, overlooking the potential synergy of LLMs’ step-wise reasoning capabilities and KGs’ structural nature.
Approach:	They propose a graph-aware constrained decoding framework that facilitates a deep synergy between LLMs and KGs by constraint derived from the topology of the KG.
Outcome:	The proposed framework can provide faithful and sound reasoning for KGQA.

Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Fengran Mo, Yifan Gao, Sha Li, Hansi Zeng, Xin Liu, Zhaoxuan Tan, Xian Li, Jianshu Chen, Dakuo Wang, Meng Jiang

UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity Mixture-of-Experts (2026.acl-long)

Challenge:	Existing studies focus on single-turn scenarios, which might lack the ability to handle multi-turn interactions.
Approach:	They propose a conversational agent that interleaves search and reasoning across turns and provides tailored rewards towards evolving user goals.
Outcome:	The proposed agent interleaves search and reasoning across turns, enabling exploratory and adaptive behaviors learned through reinforcement learning (RL) training with tailored rewards towards evolving user goals.

Copied to clipboard

Zhenyu Liu, Yunxin li, Xuanyu Zhang, Qixun Teng, Shenyuan Jiang, Xinyu Chen, Haoyuan Shi, Haolan Chen, Fanbo Meng, Mingjun Zhao, Yu Xu, Yancheng He, Baotian Hu, Haizhou Li, Min Zhang

Advancing SMoE for Continuous Domain Adaptation of MLLMs: Adaptive Router and Domain-Specific Loss (2025.acl-long)

Challenge:	Recent advances in unified multimodal models indicate a clear trend towards comprehensive content generation.
Approach:	They propose a unified speech and music generation model built upon a novel framework . they propose specialized MoE architectures and curated training strategies to tackle data imbalances .
Outcome:	The proposed model achieves state-of-the-art performance on major speech and music generation benchmarks.

Copied to clipboard

Liang Zhang, Ziyao Lu, Fandong Meng, Hui Li, Jie Zhou, Jinsong Su

MASFactory: A Graph-centric Framework for Orchestrating LLM-Based Multi-Agent Systems with Vibe Graphing (2026.acl-demo)

Challenge:	Recent studies have explored Continual Instruction Tuning (CIT) in Multimodal Large Language Models (MLLMs), with a primary focus on Task-incremental CIT, where MLLM are required to continuously acquire new tasks.
Approach:	They propose a Sparse Mixture of Expert (SMoE) based method for domain-incremental CIT in Multimodal Large Language Models (MLLMs) . they equip the SMoA module with a domain-specific autoregressive loss (DSAL) they establish a new benchmark to evaluate the efficacy of their method .
Outcome:	The proposed method outperforms all baselines and is based on a Sparse Mixture of Experts (SMoE) module .

Copied to clipboard

Yang Liu, Jinxuan Cai, Yishen Li, Qi Meng, Zedi Liu, Xin Li, Chen Qian, Chuan Shi, Cheng Yang

Structured Data in NLP

Challenge:	Large language model-based multi-agent systems (MAS) are increasingly used to extend agentic problem solving via role specialization and collaboration.
Approach:	They propose a graph-centric framework for orchestrating large language model-based multi-agent systems . they compile a user's natural-language intent into an editable workflow specification and then into an executable graph .
Outcome:	The proposed framework compiles natural-language intent into an executable graph and then compile and executes it at runtime.

Enhancing Reinforcement Learning with Label-Sensitive Reward for Natural Language Understanding (2024.acl-long)

Copied to clipboard

Kuo Liao, Shuang Li, Meng Zhao, Liqun Liu, Mengge Xue, Zhenyu Hu, Honglin Han, Chengguo Yin

Challenge:	Recent advances in large language models (LLMs) have yielded remarkable performance, but objective mismatch issues hinder RLHF learning.
Approach:	They propose a Reinforcement Learning framework enhanced with Label-sensitive reward to enhance LLMs' alignment and generation capabilities.
Outcome:	The proposed framework improves performance on five diverse models across eight tasks.

ATLAS: Agent Tuning via Learning Critical Steps (2025.findings-acl)

Copied to clipboard

Zhixun Chen, Ming Li, Yuxuan Huang, Yali Du, Meng Fang, Tianyi Zhou

MultiChartQA: Benchmarking Vision-Language Models on Multi-Chart Problems (2025.naacl-long)

Challenge:	Existing agent tuning approaches employ supervised finetuning on entire expert trajectories, but behavior-cloning of full traitories introduces expert bias and weakens generalization to states not covered by the expert data.
Approach:	They propose a method that finetunes LLMs on critical steps in expert trajectories and identifies and finetuns them on these steps with reduced costs.
Outcome:	The proposed method outperforms existing methods and open-source LLM agents on only 30% critical steps in extensive experiments.

Copied to clipboard

Zifeng Zhu, Mengzhao Jia, Zhihan Zhang, Lang Li, Meng Jiang

A Secure and Efficient Federated Learning Framework for NLP (2021.emnlp-main)

Challenge:	Existing chart understanding benchmarks focus on single-chart tasks, neglecting multi-hop reasoning required to extract and integrate information from multiple charts.
Approach:	They propose a benchmark that evaluates MLLMs’ capabilities in four key areas: direct question answering, parallel question answering and comparative reasoning.
Outcome:	The proposed benchmark evaluates MLLMs’ capabilities in four key areas: direct question answering, parallel question answering and comparative reasoning.

Copied to clipboard

Chenghong Wang, Jieren Deng, Xianrui Meng, Yijue Wang, Ji Li, Sheng Lin, Shuo Han, Fei Miao, Sanguthevar Rajasekaran, Caiwen Ding

RAPL: A Relation-Aware Prototype Learning Approach for Few-Shot Document-Level Relation Extraction (2023.emnlp-main)

Challenge:	Existing FL frameworks require a trusted aggregator or require heavy-weight cryptographic primitives, which makes the performance significantly degraded.
Approach:	They propose a framework that is federated and efficient for NLP . they propose to eliminate the need for trusted entities and achieve better model accuracy .
Outcome:	The proposed framework achieves better model accuracy and model accuracy than existing FL frameworks.

Copied to clipboard

Shiao Meng, Xuming Hu, Aiwei Liu, Shuang Li, Fukun Ma, Yawen Yang, Lijie Wen

A Contextual Hierarchical Attention Network with Adaptive Objective for Dialogue State Tracking (2020.acl-main)

Challenge:	Existing methods to identify semantic relations between entities are time-consuming and labor-intensive.
Approach:	They propose a relation-aware prototype learning method for document-level relation extraction (FSDLRE) they propose RAPL, which judiciously leverages relation descriptions and real NOTA instances as guidance .
Outcome:	The proposed method outperforms state-of-the-art approaches by 2.61% F1 . it generates task-specific NOTA prototypes and refines relation prototypes .

Copied to clipboard

Yong Shan, Zekang Li, Jinchao Zhang, Fandong Meng, Yang Feng, Cheng Niu, Jie Zhou

Enhancing Cross-Document Event Coreference Resolution by Discourse Structure and Semantic Information (2024.lrec-main)

Challenge:	Existing methods for dialogue state tracking ignore the slot imbalance problem and treat all slots indiscriminately, which limits the learning of hard slots.
Approach:	They propose to employ a contextual hierarchical attention network to enhance the DST by learning contextual representations.
Outcome:	The proposed approach achieves 52.68% and 58.55% joint accuracy on multiWOZ 2.0 and MultiWOZ 2.1 datasets and significantly improves performance (+1.24% and +5.98%)

Copied to clipboard

Qiang Gao, Bobo Li, Zixiang Meng, Yunlong Li, Jun Zhou, Fei Li, Chong Teng, Donghong Ji

Who Can Withstand Chat-Audio Attacks? An Evaluation Benchmark for Large Audio-Language Models (2025.findings-acl)

Challenge:	Existing cross-document event coreference resolution models lack the ability to capture long-distance dependencies.
Approach:	They propose to construct document-level Rhetorical Structure Theory trees and cross-document Lexical Chains to model structural and semantic information of documents.
Outcome:	The proposed model outperforms baseline models on English and Chinese datasets by large margins.

Copied to clipboard

Wanqi Yang, Yanda Li, Meng Fang, Yunchao Wei, Ling Chen

Triangular Transfer: Freezing the Pivot for Triangular Machine Translation (2022.acl-short)

Challenge:	Existing research focused on model-specific adversarial methods, but real-world applications demand a more generalizable approach to audio adversarials.
Approach:	They propose a Chat-Audio Attacks benchmark to evaluate LALMs' robustness . they propose standard evaluation, GPT-4o-based evaluation and human evaluation .
Outcome:	The proposed benchmark aims to explore the robustness of six state-of-the-art LALMs with voice interaction capabilities.

Copied to clipboard

Meng Zhang, Liangyou Li, Qun Liu

Regularized Context Gates on Transformer for Machine Translation (2020.acl-main)

Challenge:	Existing approaches to triangular machine translation have not fully exploited all types of auxiliary data.
Approach:	They propose a transfer-learning-based approach that utilizes all types of auxiliary data.
Outcome:	The proposed approach outperforms existing approaches with a series of experiments.

Copied to clipboard

Xintong Li, Lemao Liu, Rui Wang, Guoping Huang, Max Meng

Categorizing Semantic Representations for Neural Machine Translation (2022.coling-1)

Challenge:	Context gates are effective to control the contributions from the source and target contexts in the recurrent neural network (RNN) based neural machine translation.
Approach:	They propose a method to identify source and target contexts and introduce a gate mechanism to control the contributions from source and targets in the advanced Transformer architecture.
Outcome:	The proposed model achieves an averaged gain of 1.0 BLEU score over a strong transformer baseline.

Copied to clipboard

Yongjing Yin, Yafu Li, Fandong Meng, Jie Zhou, Yue Zhang

Context Tracking Network: Graph-based Context Modeling for Implicit Discourse Relation Recognition (2021.naacl-main)

Challenge:	Modern neural machine translation models suffer limitation in compositional generalization, resulting in weakened translation performance on unseen compounds.
Approach:	They propose to introduce categorization to the contextualized representations to improve generalization by reducing sparsity and overfitting.
Outcome:	The proposed method reduces compositional generalization error rates by 24% on a dedicated MT dataset.

Copied to clipboard

Yingxue Zhang, Fandong Meng, Peng Li, Ping Jian, Jie Zhou

ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information (2021.acl-long)

Challenge:	Existing models fail to fully utilize contextual information which plays an important role in interpreting sentences.
Approach:	They propose a graph-based Context Tracking Network to model the discourse context for IDRR.
Outcome:	The proposed model can integrate sentence-level and token-level contextual semantics better than existing models.

Copied to clipboard

Zijun Sun, Xiaoya Li, Xiaofei Sun, Yuxian Meng, Xiang Ao, Qing He, Fei Wu, Jiwei Li

MCP-Guard: A Multi-Stage Defense-in-Depth Framework for Securing Model Context Protocol in Agentic AI (2026.findings-acl)

Challenge:	ChineseBERT model incorporates glyph and pinyin information of Chinese characters into pretraining . proposed model achieves new performance boost over baseline models with fewer training steps .
Approach:	They propose a ChineseBERT model that incorporates glyph and pinyin information into pretraining . the glyph embedding is obtained based on different fonts of a character, and the pinyink embeddment characterizes the pronunciation of Chinese characters.
Outcome:	The proposed model achieves new performance boosts over baseline models with fewer training steps.

Copied to clipboard

Wenpeng Xing, Zhonghao Qi, Yupeng Qin, Yilin Li, Caini Chang, Jiahui Yu, Changting Lin, Zhenzhen Xie, Meng Han

PREE: Towards Harmless and Adaptive Fingerprint Editing in Large Language Models via Knowledge Prefix Enhancement (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) are vulnerable to jailbreak, authors say . authors propose a robust, layered defense architecture designed for LLM–tool interactions .
Approach:	They propose a robust, layered defense architecture designed for LLM–tool interactions . they propose XCP-Guard, which employs a three-stage detection pipeline .
Outcome:	The proposed model achieves 96.01% accuracy in identifying adversarial prompts . the model is based on a three-stage detection pipeline that balances efficiency with accuracy .

Copied to clipboard

Xubin Yue, Zhenhua Xu, Wenpeng Xing, Jiahui Yu, Mohan Li, Meng Han

Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs (2024.findings-acl)

Challenge:	Existing black-box fingerprinting techniques rely on overfitting high-perplexity trigger patterns . experimental results show that model editing in the fingerprint domain exhibits unique advantages .
Approach:	They propose a prefix-enhanced fingerprint editing framework that encodes copyright information into parameter offsets through dual-channel knowledge edit to achieve covert embedding of fingerprint features.
Outcome:	The proposed model editing framework achieves 90% trigger precision in mainstream architectures . the proposed model editor achieves the 90% accuracy in mainstream models .

Copied to clipboard

Bowen Jin, Chulin Xie, Jiawei Zhang, Kashob Kumar Roy, Yu Zhang, Zheng Li, Ruirui Li, Xianfeng Tang, Suhang Wang, Yu Meng, Jiawei Han

Structured Data in NLP

Challenge:	Existing studies suggest augmenting LLMs with external text corpora to alleviate hallucination problems.
Approach:	They propose to augment large language models with text units retrieved from external knowledge corpora to alleviate the issue.
Outcome:	The proposed framework outperforms baselines on GRBench with three LLMs and shows that iterative reasoning outperformed the baselines.

Personality Understanding of Fictional Characters during Book Reading (2023.acl-long)

Copied to clipboard

Mo Yu, Jiangnan Li, Shunyu Yao, Wenjie Pang, Xiaochen Zhou, Zhou Xiao, Fandong Meng, Jie Zhou

Challenge:	Existing methods to predict characters' personalities have not been studied in the NLP field due to the lack of appropriate datasets mimicking the process of book reading.
Approach:	They propose a dataset to predict characters' personalities that uses an exhaustive vocabulary of personality traits as targets.
Outcome:	The proposed dataset is efficient and accurate and relies on long-term context to achieve accurate predictions for both machines and humans.

EmoPrompt-ECPE: Emotion Knowledge-aware Prompt-tuning for Emotion-Cause Pair Extraction (2024.lrec-main)

Copied to clipboard

Xue Gu, Zhihan Zhou, Ziyao Meng, Jian Li, Tiago Gomes, Adriano Tavares, Hao Xu

Paraphrase Generation as Unsupervised Machine Translation (2022.coling-1)

Challenge:	Existing methods for Emotion-cause pair extraction (ECPE) do not distinguish between the emotion-caused pairs that belong to different types of emotions, limiting their applicability.
Approach:	They propose an Emotion-cause pair extraction method which integrates the implicit knowledge of cause clauses into a prompt template and extends the emotion labels to categories with an external emotion word base.
Outcome:	The proposed method extracts all potential emotion clauses and corresponding cause clauses from unannotated documents.

Copied to clipboard

Xiaofei Sun, Yufei Tian, Yuxian Meng, Nanyun Peng, Fei Wu, Jiwei Li, Chun Fan

Question-Interlocutor Scope Realized Graph Modeling over Key Utterances for Dialogue Reading Comprehension (2023.findings-acl)

Challenge:	Existing methods for paraphrase generation rely on labeled datasets or are limited in narrow domains.
Approach:	They propose a paradigm for paraphrase generation by treating the task as unsupervised machine translation based on pairs of unlabeled monolingual sentences.
Outcome:	The proposed paradigm can generate paraphrases on a large unlabeled monolingual corpus without relying on bilingual sentence pairs.

Copied to clipboard

Jiangnan Li, Mo Yu, Fandong Meng, Zheng Lin, Peng Fu, Weiping Wang, Jie Zhou

BertGCN: Transductive Text Classification by Combining GNN and BERT (2021.findings-acl)

Challenge:	Compared to standard RC tasks, dialogue reading comprehension (DRC) has raised challenges because of the complex speaker information and noisy dialogue context.
Approach:	They propose a new method for dialogue reading comprehension that extracts answers from dialogues by using key-utterances-extracting methods and a Question-Interlocutor Scope Realized Graph.
Outcome:	The proposed method achieves state-of-the-art performance against previous works.

Copied to clipboard

Yuxiao Lin, Yuxian Meng, Xiaofei Sun, Qinghong Han, Kun Kuang, Jiwei Li, Fei Wu

Information Retrieval

Challenge:	Text classification is a core task in natural language processing (NLP) Graph neural networks (GNNs) serve as an effective approach for transductive learning.
Approach:	They propose a model that combines large scale pretraining and transductive learning for text classification.
Outcome:	The proposed model achieves SOTA performance on a wide range of datasets.

CAP: Controllable Alignment Prompting for Unlearning in LLMs (2026.acl-long)

Copied to clipboard

Zhaokun Wang, Jinyu Guo, Jingwen Pu, Hongli Pu, Meng Yang, Xunlei Chen, Jie Ou, Wenyi Li, Guangchun Luo, Wenhong Tian

On the Generation of Medical Dialogs for COVID-19 (2021.acl-short)

Challenge:	Existing methods for modifying parameters are unsystematic and rely on empirical experience.
Approach:	They propose a controllable alignment prompting for unlearning framework that decouples unlearning into a learnable prompt optimization process via reinforcement learning.
Outcome:	The proposed framework achieves precise, controllable unlearning without updating model parameters.

Copied to clipboard

Meng Zhou, Zechen Li, Bowen Tan, Guangtao Zeng, Wenmian Yang, Xuehai He, Zeqian Ju, Subrato Chakravorty, Shu Chen, Xingyi Yang, Yichen Zhang, Qingyang Wu, Zhou Yu, Kun Xu, Eric Xing, Pengtao Xie

Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning (2023.emnlp-main)

Challenge:	under the pandemic of COVID-19, people experiencing COVI D19-related symptoms have a pressing need to consult doctors.
Approach:	They develop a medical dialog system that can provide COVID19-related consultations . they use two dialog datasets containing conversations between doctors and patients .
Outcome:	The proposed system can provide COVID19-related consultations, but is too small compared with general-domain dialog datasets.

Copied to clipboard

Lean Wang, Lei Li, Damai Dai, Deli Chen, Hao Zhou, Fandong Meng, Jie Zhou, Xu Sun

Beyond the Safety Tax: Mitigating Unsafe Text-to-Image Generation via External Safety Rectification (2026.findings-acl)

Challenge:	In-context learning (ICL) is a promising capability for large language models (LLMs) but its underlying mechanism remains unexplored.
Approach:	They propose a demonstration compression technique to expedite inference and an analysis framework for diagnosing ICL errors in GPT2-XL.
Outcome:	The proposed method improves ICL performance and expedites inference.

Copied to clipboard

Xiangtao Meng, Yingkai Dong, Ning Yu, Li Wang, Zheng Li, Shanqing Guo

BrowseComp-Plus: A Fair and Disentangled Evaluation Benchmark for Deep Search Agents (2026.acl-long)

Challenge:	Existing safety defenses typically intervene internally within the generative model, but suffer from severe concept entanglement, leading to degradation of benign generation quality.
Approach:	They propose a structurally isolated safety module that performs external, interpretable rectification without modifying the base model.
Outcome:	The proposed module performs external, interpretable rectification without modifying the base model.

Copied to clipboard

Zijian Chen, Xueguang Ma, Shengyao Zhuang, Ping Nie, Kai Zou, Sahel Sharifymoghaddam, Andrew Liu, Joshua Green, Kshama Patel, Ruoxi Meng, Mingyi Su, Yanxi Li, Haoran Hong, Xinyu Shi, Xuye Liu, Hosna Oyarhoseini, Nandan Thakur, Crystina Zhang, Luyu Gao, Wenhu Chen, Jimmy Lin

FARSS: Fisher-Optimized Adaptive Low-Rank and Singular-Vector Selection for Knowledge-Preserving Fine-Tuning (2026.findings-acl)

Challenge:	Existing benchmarks for deep search agents rely on blackbox web search APIs . dynamic and opaque web APIs hinder reproducibility and fair comparisons - authors .
Approach:	They propose a benchmark that employs a fixed corpus for controlled retrieval for deep search agents.
Outcome:	The new benchmark shows that agents that combine large language models with retrieval tools excel at complex, reasoning-intensive queries.

Copied to clipboard

Renxing Chen, Ziwei Xiang, Peisong Wang, Hongjian Fang, Meng Li, Fanhu Zeng, Yanan Zhu, Peipei Yang, Xu-Yao Zhang, Jian Cheng

Strengthened Symbol Binding Makes Large Language Models Reliable Multiple-Choice Selectors (2024.acl-long)

Challenge:	Low-rank adaptation methods for large language models have limitations in preserving world knowledge and limiting updates to preserve world knowledge.
Approach:	They propose a Fisher-optimized adaptive low Rank and Singular-VectorSelection framework for knowledge-preserving fine-tuning that allows efficient and task-sensitive updates.
Outcome:	The proposed framework outperforms existing methods for knowledge-preserving fine-tuning.

Copied to clipboard

Mengge Xue, Zhenyu Hu, Liqun Liu, Kuo Liao, Shuang Li, Honglin Han, Meng Zhao, Chengguo Yin

SOAR: Supervision from Observation for Agentic Reinforcement Learning (2026.acl-long)

Challenge:	Multiple-Choice Questions (MCQs) are a critical area of research in the study of Large Language models (LLMs).
Approach:	They propose an efficient SFT algorithm for MCQs, termed Point-wise Intelligent Feedback, which constructs negative instances by randomly combing the incorrect option contents with all candidate symbols.
Outcome:	The proposed algorithm significantly reduces the model’s selection bias by improving its MCSB capability.

Copied to clipboard

Meng Li, Lei Li, Xiting Wang, Yi Yuan, Zheng Wei, null Brucebian, Zang Li

Triggerless Backdoor Attack for NLP Tasks with Clean Labels (2022.naacl-main)

Challenge:	Prior work assigns supervision based on outcome rewards or external reward models, but ignores environment observations, a critical source of learning.
Approach:	They propose a supervision-based agentic reinforcement learning system that integrates environment observations as an explicit supervision signal.
Outcome:	The proposed model improves performance on reasoning and deep research tasks while reducing erroneous and inefficient tool usage.

Copied to clipboard

Leilei Gan, Jiwei Li, Tianwei Zhang, Xiaoya Li, Yuxian Meng, Fei Wu, Yi Yang, Shangwei Guo, Chun Fan

Multimodal Incremental Transformer with Visual Grounding for Visual Dialogue Generation (2021.findings-acl)

Challenge:	Backdoor attacks are a new threat to neural natural language processing models due to the fragility and lack of interpretability of NLP models.
Approach:	They propose a method to perform backdoor attacks without an external trigger . they propose to use clean-labeled examples to generate poisoned clean-labelled examples .
Outcome:	The proposed strategy is effective and hard to defend due to its triggerless nature.

Copied to clipboard

Feilong Chen, Fandong Meng, Xiuyi Chen, Peng Li, Jie Zhou

LexMatcher: Dictionary-centric Data Curation for LLM-based Machine Translation (2024.findings-emnlp)

Challenge:	Existing studies focus on implicit exploration of multimodal coreference but neglect the importance of locating the objects explicitly in the visual content, which is associated with textual entities.
Approach:	They propose a multimodal incremental transformer with visual grounding which aims to explicitly locate related objects in the image guided by textual entities.
Outcome:	The proposed model achieves comparable performance on the VisDial v0.9 and v1.0 datasets.

Copied to clipboard

Yongjing Yin, Jiali Zeng, Yafu Li, Fandong Meng, Yue Zhang

Evaluating the Expressive Appropriateness of Speech in Rich Contexts (2026.acl-long)

Challenge:	emergence of large language models (LLMs) has brought about new opportunities for machine translation.
Approach:	They propose a method for data curation that supplements the infrequent senses of polysemous words.
Outcome:	The proposed method outperforms established baselines on the WMT2022 test sets and is applicable to other pre-trained models.

Copied to clipboard

Tianrui Wang, Ziyang Ma, Yizhou Peng, Haoyu Wang, Zhikang Niu, Zikang Huang, Yihao Wu, Yi-Wen Chao, Yu Jiang, Yuheng Lu, Guanrou Yang, Xuanchen Li, Hexin Liu, Chunyu Qiang, Cheng Gong, Yifan Yang, Tianchi Liu, Junyu Wang, Nana Hou, Meng Ge, Fuming You, Yang Wei, Zhongqian Sun, Hu Haifeng, Xiaobao Wang, Eng Siong Chng, Xie Chen, Longbiao Wang, Jianwu Dang

Speech & Audio in NLP

Challenge:	Existing methods for evaluating expressive speech focus on word accuracy, naturalness, signal quality, or emotional intensity at the utterance level.
Approach:	They propose a framework for Evaluating Expressive Appropriateness in speech that assesses whether a speech sample aligns with the underlying communicative intent implied by its discourse-level narrative context.
Outcome:	The proposed framework outperforms existing speech evaluation and analysis systems on a human-annotated test set.

Seg2Act: Global Context-aware Action Generation for Document Logical Structuring (2024.emnlp-main)

Copied to clipboard

Zichao Li, Shaojie He, Meng Liao, Xuanang Chen, Yaojie Lu, Hongyu Lin, Yanxiong Lu, Xianpei Han, Le Sun

Challenge:	Document logical structuring is crucial for document intelligence due to the complexity of text segment dependencies in the document.
Approach:	They propose an end-to-end, generation-based method for document logical structuring that generates the action sequence via a global context-aware generative model and updates its global context and current logical structure based on the generated actions.
Outcome:	Experiments on ChCatExt and HierDoc datasets show that Seg2Act performs better than previous methods in both supervised and transfer learning settings.

Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs (2025.emnlp-main)

Copied to clipboard

Dingdong Wang, Junan Li, Mingyu Cui, Dongchao Yang, Xueyuan Chen, Helen M. Meng

SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting (2023.findings-emnlp)

Challenge:	Speech Large Language Models (SpeechLLMs) have emerged as dominant speech processing approaches.
Approach:	They compare self-supervised learning-based discrete and continuous features . they compare performance across six spoken language understanding-related tasks .
Outcome:	The proposed models outperform discrete tokens and continuous features in six spoken language understanding-related tasks.

Copied to clipboard

Xiaoying Zhang, Baolin Peng, Kun Li, Jingyan Zhou, Helen Meng

Dynamic Graph Neural ODE Network for Multi-modal Emotion Recognition in Conversation (2025.coling-main)

Challenge:	Experimental results show that SGP-TOD provides state-of-the-art zero-shot performance . prevailing approach for creating task bots is to fine-tune pre-trained language models .
Approach:	They propose a Schema-Guided Prompting for building Task-Oriented Dialog systems . they use predefined task schema and dialog policy to instruct fixed LLMs to generate appropriate responses .
Outcome:	The proposed system outperforms few-shot approaches on multiwoz, RADDLE, and STAR datasets.

Copied to clipboard

Yuntao Shou, Tao Meng, Wei Ai, Keqin Li

Towards Identifying Social Bias in Dialog Systems: Framework, Dataset, and Benchmark (2022.findings-emnlp)

Challenge:	Existing graph-based multimodal emotion recognition methods fail to capture dynamic changes in emotions.
Approach:	They propose a Dynamic Graph Neural Ordinary Differential Equation Network (DGODE) which combines dynamic changes of emotions to capture temporal dependencies of speakers’ emotions.
Outcome:	The proposed model can capture the temporal dependencies caused by dynamic changes in emotions and can improve on two publicly available multimodal emotion recognition datasets.

Copied to clipboard

Jingyan Zhou, Jiawen Deng, Fei Mi, Yitong Li, Yasheng Wang, Minlie Huang, Xin Jiang, Qun Liu, Helen Meng

Consistency Regularization Training for Compositional Generalization (2023.acl-long)

Challenge:	a number of safety concerns hinder the deployment of open-domain dialog systems, such as offensive languages and toxic behaviors, such social bias is difficult to detect.
Approach:	They propose a Dial-Bias Framework for analyzing social bias in conversations . they introduce a Chinese social bias dialog dataset and conduct in-depth ablation studies .
Outcome:	The proposed framework is the first annotated Chinese social bias dialog dataset . the proposed framework also provides a fine-grained dialog bias measurement benchmark .

Copied to clipboard

Yongjing Yin, Jiali Zeng, Yafu Li, Fandong Meng, Jie Zhou, Yue Zhang

MathAgent: Adversarial Evolution of Constraint Graphs for Mathematical Reasoning Data Synthesis (2026.findings-acl)

Challenge:	Existing neural models have difficulty generalizing to unseen combinations of seen components.
Approach:	They propose to improve the capability of Transformer on compositional generalization by consistency regularization training without modifying model architectures.
Outcome:	The proposed model performs well on semantic parsing and machine translation benchmarks.

Copied to clipboard

Zixiong Yu, Jun Rao, Guhan Chen, Songtao Tian, Bohan Li, Jiansheng Wei, Min Zhang, Xiaojun Meng

Dense Retrievers Can Fail on Simple Queries: Revealing The Granularity Dilemma of Embeddings (2025.findings-emnlp)

Challenge:	Current approaches to synthesising high-quality mathematical reasoning data without human priors suffer from mode collapse and limited logical complexity.
Approach:	They propose a hierarchical synthesis framework that formulates data synthesis as an unsupervised optimization problem over a constraint graph followed by semantic instantiation rather than a direct text generation task.
Outcome:	The proposed framework outperforms widely-used datasets on eight mathematical benchmarks.

Copied to clipboard

Liyan Xu, Zhenlin Su, Mo Yu, Jiangnan Li, Fandong Meng, Jie Zhou

TAKE: Topic-shift Aware Knowledge sElection for Dialogue Generation (2022.coling-1)

Challenge:	a limited number of text encoders are able to recognize fine-grained entities or events within encoded semantics.
Approach:	They propose a new evaluation dataset to examine embeddings' ability to recognize fine-grained entities or events within encoded semantics.
Outcome:	The proposed dataset shows embeddings struggle with fine-grained matching . the proposed encoder outperforms the state-of-the-art 7B model in a small sample .

Copied to clipboard

Chenxu Yang, Zheng Lin, Jiangnan Li, Fandong Meng, Weiping Wang, Lanrui Wang, Jie Zhou

A Survey on Cross-Lingual Summarization (2022.tacl-1)

Challenge:	Recent work finds that realizing who holds the initiative can help select knowledge . however, there is a strong semantic transition between two rounds, probably leading to initiative misjudgment .
Approach:	They propose a topic-shift Aware Knowledge sElector(TAKE) model which locates relevant parts from dialogue history to improve knowledge selection.
Outcome:	The proposed model outperforms baseline models on the WoW.

Copied to clipboard

Jiaan Wang, Fandong Meng, Duo Zheng, Yunlong Liang, Zhixu Li, Jianfeng Qu, Jie Zhou

Layer-wise Model Pruning based on Mutual Information (2021.emnlp-main)

Challenge:	Cross-lingual summarization is a task of generating a summary in one language for a given document in a different language.
Approach:	They present a systematic review of the literature on cross-lingual summarization . they summarize previous efforts and compare them with each other .
Outcome:	The proposed approach is compared with previous approaches and summarizes them to provide a deeper analysis.

Copied to clipboard

Chun Fan, Jiwei Li, Tianwei Zhang, Xiang Ao, Fei Wu, Yuxian Meng, Xiaofei Sun

Massive End-to-end Speech Recognition Models with Time Reduction (2024.naacl-long)

Challenge:	In spite of impressive results of neural networks, the huge model size has hindered their applications in cases where computation and memory resources are limited.
Approach:	They propose a method for layer-wise pruning using mutual information based feature selection in SVMs and logistic regression.
Outcome:	The proposed pruning strategy offers greater speedup and higher performance than weight-based pruning methods.

Copied to clipboard

Weiran Wang, Rohit Prabhavalkar, Haozhe Shan, Zhong Meng, Dongseong Hwang, Qiujia Li, Khe Chai Sim, Bo Li, James Qin, Xingyu Cai, Adam Stooke, Chengjian Zheng, Yanzhang He, Tara Sainath, Pedro Moreno Mengibar

Parallel Test-Time Scaling for Latent Reasoning Models (2026.acl-long)

Challenge:	Using the neural architecture of Google’s universal speech model, we reduce the frame rate and speed up training and inference.
Approach:	They propose to use the neural architecture of Google’s universal speech model with additional funnel pooling layers to significantly reduce the frame rate and speed up training and inference.
Outcome:	The proposed methods work with both connectionist temporal classification (CTC) and RNN-Transducer (RNN-T) and over two domains.

Copied to clipboard

Runyang You, Yongqi Li, Meng Liu, Wenjie Wang, Liqiang Nie, Wenjie Li

Enhancing Temporal Sensitivity and Reasoning for Time-Sensitive Question Answering (2024.findings-emnlp)

Challenge:	Parallel test-time scaling is a pivotal approach for enhancing large language models.
Approach:	They propose two uncertainty-inspired stochastic strategies for parallel test-time scaling for latent reasoning models and a Latent Reward Model for aggregation.
Outcome:	The proposed model scales well with compute and enables effective trajectory selection.

Copied to clipboard

Wanqi Yang, Yanda Li, Meng Fang, Ling Chen

Understanding Translationese in Cross-Lingual Summarization (2023.findings-emnlp)

Challenge:	Existing language models have limited sensitivity to temporal information and inadequate temporal reasoning capabilities.
Approach:	They propose a framework that enhances temporal awareness and reasoning . they propose to use Temporal Information-Aware Embedding and Granular Contrastive Reinforcement Learning .
Outcome:	The proposed framework outperforms existing LLMs on time-sensitive question answering tasks.

Copied to clipboard

Jiaan Wang, Fandong Meng, Yunlong Liang, Tingyi Zhang, Jiarong Xu, Zhixu Li, Jie Zhou

The GaoYao Benchmark: A Comprehensive Framework for Evaluating Multilingual and Multicultural Abilities of Large Language Models (2026.acl-long)

Challenge:	Existing datasets involve translation, but translationese is distinguished from original text . previous studies have shown that translationeses in CLS are not a problem in training sets .
Approach:	They propose to use cross-lingual summarization to generate a concise summary in a target language from a document in . existing datasets typically involve translation in their creation, but the translated text is distinguished from the original written in that language.
Outcome:	The proposed method systematically investigates how translationese affects CLS model evaluation and performance when it appears in source documents or target summaries.

Copied to clipboard

Yilun Liu, Chunguang Zhao, Mengyao Piao, Lingqi Miao, Shimin Tao, Minggui HE, Chenxin Liu, Zhang Li, null Mahongxia, Jiaxin Guo, Chen Liu, Liqun Deng, Jiansheng Wei, Xiaojun Meng, Fanyi Du, Daimeng Wei, Yanghua Xiao

Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents (2022.findings-acl)

Challenge:	Existing multilingual evaluation benchmarks neglect cultural nuances and lack language coverage in subjective tasks.
Approach:	They propose a framework that categorizes evaluation tasks into three cultural layers and nine cognitive sub-layers.
Outcome:	The proposed framework surpasses prior coverage by up to 111% on 20+ LLMs.

Copied to clipboard

Yicheng Zou, Hongwei Liu, Tao Gui, Junzhe Wang, Qi Zhang, Meng Tang, Haixiang Li, Daniell Wang

Xiaofei Sun, Yuxian Meng, Xiang Ao, Fei Wu, Tianwei Zhang, Jiwei Li, Chun Fan

Challenge:	Existing text semantic matching models do not provide granularity for text comparison.
Approach:	They propose a simple yet effective training strategy for text semantic matching by disentangling keywords from intents.
Outcome:	The proposed approach achieves stable performance improvements against a wide range of models on three benchmarks.

Copied to clipboard

ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue Summarization (2022.emnlp-main)

Challenge:	Existing methods to measure sentence similarity face limited dataset size and training-test gap . existing methods lack large-scale labeled datasets with labeles that are labor-intensive and expensive .
Approach:	They propose a framework that measures sentence similarity by comparing probabilities of generating two sentences given the same context.
Outcome:	The proposed framework achieves significant performance boosts over baselines under supervised and unsupervised settings.

Copied to clipboard

Jiaan Wang, Fandong Meng, Ziyao Lu, Duo Zheng, Zhixu Li, Jianfeng Qu, Jie Zhou

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

Challenge:	Existing approaches to building cross-lingual summarization systems on dialogue documents are limited.
Approach:	They propose a benchmark dataset for building cross-lingual summarization systems on dialogue documents.
Outcome:	The proposed model outperforms pipeline models on ClidSum and mDialBART.

Copied to clipboard

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

Plot Retrieval as an Assessment of Abstract Semantic Association (2024.acl-srw)

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

Shicheng Xu, Liang Pang, Jiangnan Li, Mo Yu, Fandong Meng, Huawei Shen, Xueqi Cheng, Jie Zhou

Information Retrieval

Challenge:	Existing information retrieval datasets cannot capture abstract semantic associations well.
Approach:	They propose a task that retrieves relevant plots from the book for a query using a labeled dataset.
Outcome:	The proposed task can be used to evaluate the performance of IR models on the novel task Plot Retrieval.

Mastering the Craft of Data Synthesis for CodeLLMs (2025.naacl-long)

Copied to clipboard

Meng Chen, Philip Arthur, Qianyu Feng, Cong Duy Vu Hoang, Yu-Heng Hong, Mahdi Kazemi Moghaddam, Omid Nezami, Duc Thien Nguyen, Gioacchino Tangari, Duy Vu, Thanh Vu, Mark Johnson, Krishnaram Kenthapadi, Don Dharmasiri, Long Duong, Yuan-Fang Li

Challenge:	Large language models (LLMs) have shown impressive performance in code understanding and generation.
Approach:	They propose a systematic review of large language models and their taxonomy and propose specialized LLMs for code-related tasks.
Outcome:	The proposed models have shown to be highly effective in coding tasks.

GoG: Relation-aware Graph-over-Graph Network for Visual Dialog (2021.findings-acl)

Copied to clipboard

Feilong Chen, Xiuyi Chen, Fandong Meng, Peng Li, Jie Zhou

Bridging the Gap between Prior and Posterior Knowledge Selection for Knowledge-Grounded Dialogue Generation (2020.emnlp-main)

Challenge:	Experimental results show that our model outperforms the strong baseline in both generative and discriminative settings by a significant margin.
Approach:	They propose a relation-aware graph-over-graph network (GoG) for visual dialog . their model outperforms the strong baseline in both generative and discriminative settings .
Outcome:	The proposed model outperforms baseline models in both generative and discriminative settings by a significant margin.

Copied to clipboard

Xiuyi Chen, Fandong Meng, Peng Li, Feilong Chen, Shuang Xu, Bo Xu, Jie Zhou

Dice Loss for Data-imbalanced NLP Tasks (2020.acl-main)

Challenge:	Existing knowledge-grounded dialogue models lack prior and posterior knowledge selection . prior selection module may not learn to select knowledge properly because of lack of posterior information .
Approach:	They propose a knowledge distillation-based training strategy to remove the exposure bias of knowledge selection.
Outcome:	The proposed model improves on two knowledge-grounded dialogue datasets.

Copied to clipboard

Xiaoya Li, Xiaofei Sun, Yuxian Meng, Junjun Liang, Fei Wu, Jiwei Li

Syntactic Text Processing

Challenge:	Using dice loss, we find that data imbalance is a common issue in many NLP tasks . data imbalance affects the performance of many tasks, such as tagging and machine reading comprehension .
Approach:	They propose to use dice loss to replace the standard cross-entropy objective for data-imbalanced NLP tasks.
Outcome:	The proposed training objective achieves significant performance boost on a wide range of data imbalanced tasks.

A Unified MRC Framework for Named Entity Recognition (2020.acl-main)

Copied to clipboard

Xiaoya Li, Jingrong Feng, Yuxian Meng, Qinghong Han, Fei Wu, Jiwei Li

A Dual-Channel Framework for Sarcasm Recognition by Detecting Sentiment Conflict (2022.findings-naacl)

Challenge:	Named entity recognition is divided into nested NER and flat NER depending on whether entities are nesting.
Approach:	They propose to formulate named entity recognition task as machine reading comprehension task instead of sequence labeling problem .
Outcome:	The proposed framework achieves vast amount of performance boost over current models on nested and flat NER datasets.

Copied to clipboard

Yiyi Liu, Yequan Wang, Aixin Sun, Xuying Meng, Jing Li, Jiafeng Guo

Sentiment Analysis

Challenge:	Sarcasm employs ambivalence, where one says something positive but actually means negative . linguistically, it is difficult to recognize such sentiment conflict because the sentiments are mixed or even implicit .
Approach:	They propose a Dual-Channel Framework to model literal and implied sentiments separately . they propose sarcastic networks that can detect sarcasm sentiments in political debates .
Outcome:	The proposed framework achieves state-of-the-art on political debates and Twitter datasets.

AlphaQT-Bench: Diagnosing the Gap between Financial Code Generation and Quantitative Reasoning in LLMs (2026.findings-acl)

Copied to clipboard

Sichun Luo, Yi Huang, Shichang Meng, Fengyuan Liu, Mukai Li, Qinghua Yao, Zefa Hu, Junlan Feng, Qi Liu

Programming Languages in NLP

Challenge:	Existing benchmarks rely on outcome-driven metrics such as profitability and look-ahead bias.
Approach:	They propose a diagnostic benchmark for instruction-grounded financial code generation under strict semantic and temporal constraints.
Outcome:	The proposed benchmarks show that the models fail under causal, structural, or functional constraints.

Multi-step Jailbreaking Privacy Attacks on ChatGPT (2023.findings-emnlp)

Copied to clipboard

Haoran Li, Dadi Guo, Wei Fan, Mingshi Xu, Jie Huang, Fanpu Meng, Yangqiu Song

What Factors Influence LLMs’ Judgments? A Case Study on Question Answering (2024.lrec-main)

Challenge:	With the rapid evolution of large language models (LLMs), many downstream NLP tasks can be well solved given appropriate prompts.
Approach:	They propose to integrate ChatGPT and Bing GPT3 into their applications to create a set of LLMs that can be used to generate NLP tasks with appropriate prompts.
Outcome:	The proposed models can be zero-shot or few-shot learners to solve specified tasks and can even be zero or few shot learners.

Copied to clipboard

Lei Chen, Bobo Li, Li Zheng, Haining Wang, Zixiang Meng, Runfeng Shi, Hao Fei, Jun Zhou, Fei Li, Chong Teng, Donghong Ji

Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation (2025.emnlp-main)

Challenge:	Existing studies indicate that Large Language Models perform at a level comparable to humans with advantages of speed and cost-effectiveness in different fields.
Approach:	They propose to introduce four unexplored factors and a new dimension of question difficulty to provide a more comprehensive understanding of LLMs’ judgments across varying question intricacies.
Outcome:	The proposed dimensions of question difficulty and answer quantity provide valuable insights into optimizing LLMs’ performance as judges.

Copied to clipboard

Song Wang, Zihan Chen, Peng Wang, Zhepei Wei, Zhen Tan, Yu Meng, Cong Shen, Jundong Li

Text Clustering

Challenge:	Large language models (LLMs) lack robustness in knowledge-intensive tasks due to noisy or irrelevant retrieved data.
Approach:	They propose a multi-agent debate-based RAG framework that integrates external knowledge sources into large language models to improve their accuracy.
Outcome:	The proposed framework is unsupervised and leverages pretrained LLMs without fine-tuning, making it easily adaptable to various tasks.

The Digital Dunning-Kruger Effect: Decoupling Hallucinations via Geometric Hidden-state Observation for Semantic Truthfulness (2026.acl-long)

Copied to clipboard

Yueheng Mao, Min Yu, Gengwang Li, Jianguo Jiang, Gang Li, Meng Zhang, Zhen Xu, Weiqing Huang, Ming Liu

Target-to-Source Augmentation for Aspect Sentiment Triplet Extraction (2023.emnlp-main)

Challenge:	Large Language Models (LLMs) often generate overconfident yet factually incorrect hallucinations.
Approach:	They propose a black-box-based framework that captures stubborn hallucinations by integrating internal geometric dynamics with output probability distributions.
Outcome:	The proposed framework outperforms white-box methods and reduces computational overhead by over 90%.

Copied to clipboard

Yice Zhang, Yifan Yang, Meng Li, Bin Liang, Shiwei Chen, Ruifeng Xu

Sentiment Analysis

Challenge:	Aspect Sentiment Triplet Extraction (ASTE) is an important task in sentiment analysis, but data scarcity limits performance of existing methods.
Approach:	They propose a target-to-source augmentation approach to alleviate the issue of data scarcity in Aspect Sentiment Triplet Extraction (ASTE) they use fluency and alignment discriminators to provide feedback and use this feedback to optimize the generator.
Outcome:	The proposed approach significantly improves the performance of existing methods.

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

Copied to clipboard

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

Summarize, Outline, and Elaborate: Long-Text Generation via Hierarchical Supervision from Extractive Summaries (2022.coling-1)

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.

Copied to clipboard

Xiaofei Sun, Zijun Sun, Yuxian Meng, Jiwei Li, Chun Fan

More than Minorities and Majorities: Understanding Multilateral Bias in Language Generation (2024.findings-acl)

Challenge:	Existing models focus on local word prediction, and cannot make high level plans on what to generate.
Approach:	They propose a pipelined system that summarises, outlines and elaborates on each bullet point to generate the corresponding segment.
Outcome:	The proposed system produces long texts with significantly better quality and faster convergence speed.

Copied to clipboard

Jiaxu Zhao, Zijing Shi, Yitong Li, Yulong Pei, Ling Chen, Meng Fang, Mykola Pechenizkiy

Psyche-R1: Towards Reliable Psychological LLMs through Unified Empathy, Expertise, and Reasoning (2026.acl-long)

Challenge:	Existing studies on bias dataset construction and mitigation focus on one demographic group . in real-world applications, there are more than two demographic groups at risk of the same bias.
Approach:	They propose to analyze and reduce biases across multiple demographic groups using a multi-demographic bias dataset.
Outcome:	The proposed method can mitigate biases among multiple demographic groups effectively, the authors show .

Copied to clipboard

Chongyuan Dai, Jinpeng Hu, Hongchang Shi, Zhuo Li, Dan Guo, Xun Yang, Meng Wang

Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative Training (2022.findings-naacl)

Challenge:	Recent reasoning-augmented LLMs have demonstrated impressive capabilities across a wide range of domains owing to their exceptional text understanding capabilities.
Approach:	They propose a Chinese psychological LLM that integrates empathy, psychological expertise, and reasoning.
Outcome:	The proposed model produces over 75k high-quality psychological questions paired with detailed rationales, generated through and iterative prompt-rationale optimization procedure, along with 73k empathetic dialogues.

Copied to clipboard

Yifan Gao, Qingyu Yin, Zheng Li, Rui Meng, Tong Zhao, Bing Yin, Irwin King, Michael Lyu

Information Retrieval

Challenge:	Existing studies on keyphrase generation on non-English languages haven’t been vastly investigated.
Approach:	They propose a retrieval-augmented method for multilingual keyphrase generation that leverages keyphrase annotations in English datasets to facilitate generating keyphrases in low-resource languages.
Outcome:	The proposed model outperforms baselines on non-English keyphrase generation datasets and the proposed model is scalable.

Target Foresight Based Attention for Neural Machine Translation (N18-1)

Copied to clipboard

Xintong Li, Lemao Liu, Zhaopeng Tu, Shuming Shi, Max Meng

STRIDE-ED: A Strategy-Grounded Stepwise Reasoning Framework for Empathetic Dialogue Systems (2026.acl-long)

Challenge:	Empirical experiments on Chinese-to-English and Japanese-to English datasets show that the proposed attention model delivers significant improvements in terms of alignment error rate and BLEU.
Approach:	They propose to explicitly access the target foresight word in the attention model to improve alignment and translation accuracy.
Outcome:	Empirical results show that the proposed model improves alignment error rate and BLEU on Chinese-to-English and Japanese-toEnglish datasets.

Copied to clipboard

Hongru Ji, Yuyin Fan, Meng Zhao, Xianghua Li, Lianwei Wu, Chao Gao

UniCreative: Unifying Long-form Logic and Short-form Sparkle via Reference-Free Reinforcement Learning (2026.findings-acl)

Challenge:	Empathetic dialogue requires not only recognizing a user’s emotional state but also making strategy-aware, context-sensitive decisions throughout response generation.
Approach:	They propose a STRategy-grounded, interpretable, and DEep reasoning framework that models Empathetic Dialogue through structured, strategy-conditioned reasoning.
Outcome:	The proposed framework outperforms existing methods on automatic metrics and human evaluations.

Copied to clipboard

Xiaolong Wei, Zerun Zhu, Simin Niu, Xingyu Zhang, Peiying Yu, Changxuan Xiao, Yuchen Li, Jicheng Yang, Zhejun Zhao, Chong Meng, Long Xia, Daiting Shi

Challenge:	Existing alignment paradigms for creative writing use static reward signals and supervised data.
Approach:	They propose a constraint-aware reward model that synthesizes query-specific criteria to provide fine-grained preference judgments.
Outcome:	The proposed framework aligns models with human preferences across content quality and structural paradigms without supervised fine-tuning and ground-truth references.

How Chain-of-Thought Works? Tracing Information Flow from Decoding, Projection, and Activation (2026.findings-acl)

Copied to clipboard

Hao Yang, Qinghua Zhao, Lei Li, Lingyi Meng, Mengda Yu

PanoramaRAG: Enabling Consistent Global Topic Awareness in Graph-Based RAG (2026.findings-acl)

Challenge:	Chain-of-Thought (CoT) prompting significantly enhances model reasoning, yet its internal mechanisms remain poorly understood.
Approach:	They reversely traced information flow across decoding, projection, and activation phases and found that CoT may serve as a decoding space pruner .
Outcome:	The proposed framework can be used to design more efficient and robust prompts.

Copied to clipboard

Ding Deng, Xiang Li, Yaqing Zhang, Meng Li, Xiting Wang

Multi-Perspective Context Aggregation for Semi-supervised Cloze-style Reading Comprehension (C18-1)

Challenge:	Existing graph-based methods for enhancing Large Language Models (LLMs) with external knowledge are focusing on local relationships, resulting in suboptimal performance for tasks that require global context.
Approach:	They propose a "panorama"-guided paradigm that integrates a light yet comprehensive "panoramic" of the corpus to guide all stages of the retrieval process.
Outcome:	The proposed paradigm performs well across five datasets and a variety of tasks.

Copied to clipboard

Liang Wang, Sujian Li, Wei Zhao, Kewei Shen, Meng Sun, Ruoyu Jia, Jingming Liu

Representations of Fact, Fiction and Forecast in Large Language Models: Epistemics and Attitudes (2025.acl-long)

Challenge:	Recent studies have shown that cloze-style reading comprehension is a popular task for measuring the progress of natural language understanding.
Approach:	They propose a multi-perspective framework which can be seen as joint training of heterogeneous experts and aggregate context information from different perspectives.
Outcome:	The proposed framework achieves new state-of-the-art over previous strong baselines on a recently released cloze-test dataset.

Copied to clipboard

Meng Li, Michael Vrazitulis, David Schlangen