Papers by Sheng Li

Beyond the Final Actor: Modeling the Dual Roles of Creator and Editor for Fine-Grained LLM-Generated Text Detection (2026.acl-long)

Challenge:	End-to-end speech-to speech (S2S) dialogue systems face key challenges in incorporating external knowledge into their models.
Approach:	They propose a framework that directly retrieves relevant textual knowledge from speech queries.
Outcome:	The proposed framework improves the performance of end-to-end speech-tospeech dialogue systems while achieving higher retrieval efficiency.

Copied to clipboard

Yang Li, Qiang Sheng, Zhengjia Wang, Yehan Yang, Danding Wang, Juan Cao

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

Challenge:	Existing methods to detect large language models (LLMs) use binary or ternary classifications, which can only distinguish pure human/LLM text or collaborative text at best.
Approach:	They propose a fine-grained method that characterizes distinct signatures of creator and editor by using Rhetorical Structure Theory to construct a logic graph for creator's foundation and extracting Elementary Discourse Unit (EDU)-level features for the editor's style.
Outcome:	The proposed method outperforms 12 baselines in identifying fine-grained types with low false alarms, offering a policy-aligned solution for LLM regulation.

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

Improving Event Coreference Resolution Using Document-level and Topic-level Information (2022.emnlp-main)

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

Sheng Xu, Peifeng Li, Qiaoming Zhu

Depression Detection on Social Media with Large Language Models (2025.emnlp-industry)

Challenge:	Experimental results show that our model outperforms the SOTA baselines due to the encoding length limitation.
Approach:	They propose a longformer-based encoder and an encoder with a trigger-mask mechanism to learn sentence-level embeddings based on local context.
Outcome:	The proposed model outperforms the baselines on the KBP 2017 dataset.

Copied to clipboard

Xiaochong Lan, Zhiguang Han, Yiming Cheng, Li Sheng, Jie Feng, Chen Gao, Yong Li

CorefPrompt: Prompt-based Event Coreference Resolution by Measuring Event Type and Argument Compatibilities (2023.emnlp-main)

Challenge:	Existing methods for analyzing social media data lack a systematic integration of medical knowledge, causing a critical treatment gap.
Approach:	They propose a framework that leverages Large Language Models to integrate medical knowledge into social media data.
Outcome:	The proposed framework can be used to distinguish depression from transient mood changes.

Copied to clipboard

Sheng Xu, Peifeng Li, Qiaoming Zhu

CodeRAG: Finding Relevant and Necessary Knowledge for Retrieval-Augmented Repository-Level Code Completion (2025.emnlp-main)

Challenge:	Existing methods for event coreference resolution (ECR) do not leverage human-summarized rules to guide the model.
Approach:	They propose to transform ECR into a cloze-style MLM task using a prompt-based approach . they introduce two auxiliary prompt tasks, event-type compatibility and argument compatibility .
Outcome:	The proposed method performs well in a state-of-the-art (SOTA) benchmark.

Copied to clipboard

Sheng Zhang, Yifan Ding, Shuquan Lian, Shun Song, Hui Li

Think Smart, Not Hard: Difficulty Adaptive Reasoning for Large Audio Language Models (2026.findings-acl)

Challenge:	Recent advances in code large language models have produced repository-level code completion methods that automatically predict the unfinished code based on the broader information from the repository.
Approach:	They propose a framework to identify relevant knowledge for retrieval-augmented repository-level code completion.
Outcome:	The proposed framework significantly outperforms state-of-the-art methods on ReccEval and CCEval.

Copied to clipboard

Zhichao Sheng, Shilin Zhou, Chen Gong, Zhenghua Li

How Well Do LLMs Handle Cantonese? Benchmarking Cantonese Capabilities of Large Language Models (2025.findings-naacl)

Challenge:	Existing methods to determine whether to perform reasoning lack fine-grained mechanisms to adapt reasoning length to problem complexity.
Approach:	They propose a difficulty-adaptive reasoning method that dynamically links reasoning length to the model’s perceived problem difficulty.
Outcome:	The proposed method reduces average reasoning length by 50%, achieving higher efficiency without sacrificing accuracy.

Copied to clipboard

Jiyue Jiang, Pengan Chen, Liheng Chen, Sheng Wang, Qinghang Bao, Lingpeng Kong, Yu Li, Chuan Wu

OptiCo: Adaptive Distributed Training Optimization via Collaborative Agent Reasoning (2026.acl-long)

Challenge:	Cantonese has scant representation in NLP research, especially compared to other languages from similarly developed regions.
Approach:	They propose to evaluate Cantonese LLM performance in factual generation, mathematical logic, complex reasoning, and general knowledge in Cantonesian.
Outcome:	The proposed models will evaluate Cantonese's performance in factual generation, mathematical logic, complex reasoning, and general knowledge in Cantone.

Copied to clipboard

Sheng Chen, Tang Zhe, Weixing Zhang, Fei Yang, Yuanyuan. Wang, Tianlin Li, Yang Liu

A Joint Model for Dropped Pronoun Recovery and Conversational Discourse Parsing in Chinese Conversational Speech (2021.acl-long)

Challenge:	Existing distributed training frameworks are plagued by over-reliance on prior profiling and poor generalization across models/hardware.
Approach:	They propose a model-driven multi-agent framework that leverages Large Language Models to enable automatic and explainable distributed training strategy configuration.
Outcome:	The proposed framework outperforms expert-designed training strategies within 20 iterations.

Copied to clipboard

Jingxuan Yang, Kerui Xu, Jun Xu, Si Li, Sheng Gao, Jun Guo, Nianwen Xue, Ji-Rong Wen

Edge: Enriching Knowledge Graph Embeddings with External Text (2021.naacl-main)

Challenge:	Existing work regards dropped pronoun recovery and conversational discourse parsing as two separate tasks and tackles them separately.
Approach:	They propose a neural model for dropped pronoun recovery and conversational discourse parsing in Chinese conversational speech.
Outcome:	The proposed model outperforms the state-of-the-art models on a new dataset . the proposed model is based on linguistic and semantic information from Chinese conversational speech .

Copied to clipboard

Saed Rezayi, Handong Zhao, Sungchul Kim, Ryan Rossi, Nedim Lipka, Sheng Li

Importance of Synthesizing High-quality Data for Text-to-SQL Parsing (2023.findings-acl)

Challenge:	Knowledge graphs suffer from sparsity which degrades the quality of representations generated by various methods.
Approach:	They propose a knowledge graph enrichment framework called Edge to enhance knowledge graphs based on "hard" co-occurrence of words in knowledge graph entities and external text.
Outcome:	The proposed framework achieves "soft" augmentation by combining external text with knowledge graph entities.

Copied to clipboard

Yiqun Hu, Yiyun Zhao, Jiarong Jiang, Wuwei Lan, Henghui Zhu, Anuj Chauhan, Alexander Hanbo Li, Lin Pan, Jun Wang, Chung-Wei Hang, Sheng Zhang, Jiang Guo, Mingwen Dong, Joseph Lilien, Patrick Ng, Zhiguo Wang, Vittorio Castelli, Bing Xiang

Programming Languages in NLP

Challenge:	Existing text-to-SQL parsers lack the data to perform well with augmented synthetic data.
Approach:	They propose a framework that imposes strong typing constraints and incorporates key relationships from schema.
Outcome:	The proposed framework improves on the high-quality synthesized SQL and natural language question (NLQ) models have significant accuracy boosts and achieve new state-of-the-art performance on spider.

RCI: A Score for Evaluating Global and Local Reasoning in Multimodal Benchmarks (2025.emnlp-industry)

Copied to clipboard

Amit Agarwal, Hitesh Laxmichand Patel, Srikant Panda, Hansa Meghwani, Jyotika Singh, Karan Dua, Paul Li, Tao Sheng, Sujith Ravi, Dan Roth

Article Reranking by Memory-Enhanced Key Sentence Matching for Detecting Previously Fact-Checked Claims (2021.acl-long)

Challenge:	Existing evaluation methods do not explicitly measure this distinction, hindering effective dataset curation and real-world focused model development.
Approach:	They introduce a region-based score to quantify a dataset's reliance on global versus local visual information.
Outcome:	The proposed model-based score systematically compares model performance on image patches versus full images to determine if tasks require holistic image understanding or can be solved with partial or localized visual cues.

Copied to clipboard

Qiang Sheng, Juan Cao, Xueyao Zhang, Xirong Li, Lei Zhong

A Prism Module for Semantic Disentanglement in Name Entity Recognition (P19-1)

Challenge:	Existing methods to detect false claims ignore the characteristics of FC-articles . claims are often quoted to describe checked events, providing lexical information . sentence templates to introduce or debunk claims are common across articles, providing pattern information.
Approach:	They propose a model to rerank FC-articles using key sentences and pattern information.
Outcome:	The proposed model outperforms existing methods on two real-world datasets showing that key sentences can be used to predict if an article fact-checks the given claim.

Copied to clipboard

Kun Liu, Shen Li, Daqi Zheng, Zhengdong Lu, Sheng Gao, Si Li

A Review on Deep Learning Techniques Applied to Answer Selection (C18-1)

Challenge:	Xu et al., 2015) proposed a noise reduction mechanism to disentangle semantics of words . hard and soft attention mechanisms are used to reduce noise in NLP tasks .
Approach:	They propose a prism module to disentangle semantic aspects of words and reduce noise . they propose combining prism modules with downstream models to improve model performance .
Outcome:	The proposed method significantly improves the performance of baselines on named entity recognition (NER) tasks.

Copied to clipboard

Tuan Manh Lai, Trung Bui, Sheng Li

Question Answering

Challenge:	Existing deep learning methods for answer selection are not feature engineering or expensive external resources.
Approach:	They propose to use deep learning methods to analyze and predict answer quality . they use a set of candidate answers to identify which of the candidates answers the question correctly.
Outcome:	The proposed methods produce impressive performance without feature engineering or expensive external resources.

SGPVT: Self-Generated Proximal Visual Tokens for Mitigating Proximal Collateral Damage in MLLM Unlearning (2026.acl-long)

Copied to clipboard

Jiaqi Li, Zhijing Zhang, Jiahui Geng, Sheng Bi, Chuanyi Zhang, Fan Liu, Guilin Qi

Knowledge-enriched, Type-constrained and Grammar-guided Question Generation over Knowledge Bases (2020.coling-main)

Challenge:	Existing approaches focus on general utility metrics, overlooking the preservation of semantically related concepts.
Approach:	They propose a method that introduces self-generated proximal visual tokens to prevent forgetting vulnerability.
Outcome:	The proposed framework outperforms existing methods in preserving semantically related concepts while achieving effective target unlearning.

Copied to clipboard

Sheng Bi, Xiya Cheng, Yuan-Fang Li, Yongzhen Wang, Guilin Qi

Can Language Models Capture Human Writing Preferences for Domain-Specific Text Summarization? (2025.findings-acl)

Challenge:	Existing methods for question generation over knowledge bases have low diversity and poor fluency due to the limited information contained in the subgraphs and semantic drift due to decoder’s oblivion of the semantics of the answer entity.
Approach:	They propose a knowledge-enriched, type-constrained and grammar-guided KBQG model that generates natural-language questions over a set of triples in the KB.
Outcome:	The proposed model outperforms existing methods on two widely-used benchmark datasets.

Copied to clipboard

Jingbao Luo, Ming Liu, Ran Liu, Yongpan Sheng, Xin Hu, Gang Li, WupengNjust WupengNjust

Guiding Generation for Abstractive Text Summarization Based on Key Information Guide Network (N18-2)

Challenge:	Recent studies employ large language models as auxiliary tools for humancentered NLP.
Approach:	They construct a model to capture human writing preferences by fine-tuning pre-trained models with data and designing prompts to optimize the output of large language models.
Outcome:	The proposed model captures human writing preferences through the dimensions of length, content depth, tone & style, and summary format.

Copied to clipboard

Chenliang Li, Weiran Xu, Si Li, Sheng Gao

Employing Text Matching Network to Recognise Nuclearity in Chinese Discourse (C18-1)

Challenge:	Abstractive text summarization models are hard to be controlled in the process of generation, which leads to a lack of key information.
Approach:	They propose a guiding generation model that combines extractive and abstractive methods to generate text summarization.
Outcome:	The proposed model improves on the CNN/Daily Mail dataset.

Copied to clipboard

Sheng Xu, Peifeng Li, Guodong Zhou, Qiaoming Zhu

Challenge:	Experimental results show that nuclearity recognition is a challenging task in Chinese discourse parsing due to the need for more deep semantic information.
Approach:	They propose a text matching network that encodes discourse units and paragraphs by combining Bi-LSTM and CNN to capture global dependency information and local n-gram information.
Outcome:	The proposed model outperforms baselines on the Chinese Discourse TreeBank . the proposed model is based on a novel text matching network .

Adversarial Speech Generation and Natural Speech Recovery for Speech Content Protection (2022.lrec-1)

Copied to clipboard

Sheng Li, Jiyi Li, Qianying Liu, Zhuo Gong

Measuring Pointwise 𝒱-Usable Information In-Context-ly (2023.findings-emnlp)

Challenge:	Currently, researchers focus on how to protect the speaker's identifiable information, represented as voiceprint, contained in the speech.
Approach:	They propose a frame-by-frame adversarial speech generation system to protect speech . they build an adversarials-based method that converts adversarially generated speech to human speech.
Outcome:	The proposed method can encode and recover any sensitive audio, and it is easy to be conducted with publicly available speech recognition technology.

Copied to clipboard

Sheng Lu, Shan Chen, Yingya Li, Danielle Bitterman, Guergana Savova, Iryna Gurevych

Challenge:	In-context learning (ICL) is a new learning paradigm that has gained popularity along with the development of large language models.
Approach:	They propose to adapt a recently proposed hardness metric, pointwise V-usable information (PVI), to an in-context version.
Outcome:	The proposed hardness metric is compared with the original model and is more efficient because it requires only a few exemplars and does not require fine-tuning.

Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgments (2026.acl-long)

Copied to clipboard

Hao Mi, Qiang Sheng, Shaofei Wang, Beizhe Hu, Yifan Sun, Zhengjia Wang, Hengqi Zeng, Yang Li, Danding Wang, Juan Cao

Adaptive Knowledge-Enhanced Bayesian Meta-Learning for Few-shot Event Detection (2021.findings-acl)

Challenge:	Existing methods for hallucination detection focus on implicit neural uncertainty or explicit symbolic reasoning, ignoring factual hallucinosities.
Approach:	They propose a framework that bridges neural features and symbolic judgments for hallucination detection by leveraging a "meta-judgment" process to map symbolic labels back into the feature space.
Outcome:	Extensive experiments on 4 public datasets, across 4 LLMs, against 8 baselines demonstrate the superiority of LaaB.

Copied to clipboard

Shirong Shen, Tongtong Wu, Guilin Qi, Yuan-Fang Li, Gholamreza Haffari, Sheng Bi

Derailer-Rerailer: Adaptive Verification for Efficient and Reliable Language Model Reasoning (2025.findings-acl)

Challenge:	Event detection typically does not have sufficient labelled data, thus can be formulated as a few-shot learning problem.
Approach:	They propose a knowledge-based fewshot event detection method which introduces external event knowledge as the knowledge prior of event types.
Outcome:	Experiments show that the proposed method outperforms baselines by 15 F 1 points . event detection is an important task in information extraction .

Copied to clipboard

Guangya Wan, Yuqi Wu, Hao Wang, Shengming Zhao, Jie Chen, Sheng Li

Developing and Utilizing a Large-Scale Cantonese Dataset for Multi-Tasking in Large Language Models (2025.findings-emnlp)

Challenge:	Existing prompting methods struggle with complex tasks and reasoning stability, limiting their practical deployment.
Approach:	They propose a framework that adaptively balances reasoning accuracy and computational efficiency by employing a lightweight Derailer mechanism to assess reasoning stability and selectively triggers an advanced Rerailer verification process only when necessary.
Outcome:	The proposed framework achieves significant accuracy improvements (8-11%) while maintaining 2-3 times better efficiency than existing verification methods.

Copied to clipboard

Jiyue Jiang, Alfred Kar Yin Truong, Yanyu Chen, Qinghang Bao, Sheng Wang, Pengan Chen, Jiuming Wang, Lingpeng Kong, Yu Li, Chuan Wu

GAVEL: Evidence-Contract Debate with Mechanized Scrutiny for Provenance-Grounded Fact-Checking (2026.findings-acl)

Challenge:	Cantonese is considered a low-resource language due to the dominance of Mandarin . rich colloquial vocabulary of Cantone, English loanwords, and code-switching characteristics add to the complexity of corpus collection and processing.
Approach:	We collect Cantonese texts from open source corpora, Hong Kong-specific forums, Wikipedia . we refine the model through supervised fine-tuning on curated Cantonesian tasks .
Outcome:	The model achieves state-of-the-art (SOTA) performance on four Cantonese benchmarks.

Copied to clipboard

Ruoyu Xu, Gaoxiang Li, Victor S. Sheng

RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging (2025.emnlp-main)

Challenge:	Evidence-grounded fact-checking requires predicting claim veracity while returning faithful evidence at fine granularity.
Approach:	They propose a multi-agent debate framework that enforces evidence grounding throughout inference.
Outcome:	The proposed framework improves provenance-aware metrics over existing frameworks.

Copied to clipboard

Bowen Wang, Haiyuan Wan, Liwen Shi, Chen Yang, Peng He, Yue Ma, Haochen Han, Wenhao Li, Tiao Tan, Yongjian Li, Fangming Liu, Gong Yifan, Sheng Zhang

Agentic Episodic Control (2026.findings-acl)

Challenge:	Existing models that require task labels or performance trade-offs are susceptible to catastrophic forgetting.
Approach:	They propose a representation-aware model merging framework for continual learning without access to historical data.
Outcome:	The proposed framework outperforms baselines in knowledge retention and generalization across five NLP tasks and multiple continual learning scenarios.

Copied to clipboard

Xidong Yang, Wenhao Li, Junjie Sheng, Yun Hua, Haosheng Chen, Chuyun Shen, Xiangfeng Wang

Green & Sustainable NLP

Challenge:	Existing methods for reinforcement learning (RL) are limited by poor data efficiency and weak generalization.
Approach:	They propose a novel architecture that integrates large language models into episodic RL.
Outcome:	The proposed architecture achieves 2–6 higher data efficiency than baselines and is the only method to solve complex tasks like UnlockLocal with over 90% success.

A Cognitive Stimulation Dialogue System with Multi-source Knowledge Fusion for Elders with Cognitive Impairment (2023.acl-long)

Copied to clipboard

Jiyue Jiang, Sheng Wang, Qintong Li, Lingpeng Kong, Chuan Wu

Dialogue Systems & Conversational Agents

Challenge:	Existing cognitive stimulation systems lack data on how to integrate emotional support and therapy principles into chit-chat dialogue systems.
Approach:	They propose a multi-source knowledge fusion method for CS dialogue to generate open-ended responses guided by the therapy principle and emotional support strategy.
Outcome:	The proposed method generates open-ended responses guided by the therapy principle and emotional support strategy of the target response.

MCDTB: A Macro-level Chinese Discourse TreeBank (C18-1)

Copied to clipboard

Feng Jiang, Sheng Xu, Xiaomin Chu, Peifeng Li, Qiaoming Zhu, Guodong Zhou

Syntactic Text Processing

Challenge:	Discourse analysis is becoming increasingly important in the field of natural language processing.
Approach:	They propose to annotate macro discourse information and additional discourse information to make annotation more objective and accurate.
Outcome:	The results show that the annotations are more objective and accurate than the previous ones.

Event Causality Extraction with Event Argument Correlations (2022.coling-1)

Copied to clipboard

Shiyao Cui, Jiawei Sheng, Xin Cong, Quangang Li, Tingwen Liu, Jinqiao Shi

Syntactic Text Processing

Challenge:	Event Causality Identification (ECI) ignores crucial event structure and cause-effect component information, making it struggle for downstream applications.
Approach:	They propose a task to extract event causality pairs with their structured event information from plain text.
Outcome:	The proposed method captures the intra- and inter-event argument correlations for ECE and provides several future directions.

Test-Time Code-Switching for Cross-lingual Aspect Sentiment Triplet Extraction (2025.naacl-long)

Copied to clipboard

Dongming Sheng, Kexin Han, Hao Li, Yan Zhang, Yucheng Huang, Jun Lang, Wenqiang Liu

Multilinguality

Challenge:	Aspect Sentiment Triplet Extraction (ASTE) is a thriving research area . current code-switching methods suffer from term boundary detection issues and out-of-dictionary problems.
Approach:	They propose a test-time code-switching framework which bridges the gap between bilingual training and monolingual test- time prediction.
Outcome:	The proposed framework achieves an average improvement of 3.7% on four cross-lingual datasets.

Forget the Token and Pixel: Rethinking Gradient Ascent for Concept Unlearning in Multimodal Generative Models (2025.findings-acl)

Copied to clipboard

Jiaqi Li, Chuanyi Zhang, Miaozeng Du, Hui Zhang, Yongrui Chen, Qianshan Wei, Junfeng Fang, Ruipeng Wang, Sheng Bi, Guilin Qi

Multi-Domain Dialogue State Tracking with Disentangled Domain-Slot Attention (2023.findings-acl)

Challenge:	Gradient Ascent (GA) has emerged as a promising approach for concept unlearning in Multimodal Generative Models (MGMs).
Approach:	They propose a novel approach that selectively applies GA to targeted Conceptual Knowledge while preserving Natural Knowledge through Gradient Descent (GD).
Outcome:	The proposed approach removes Conceptual Knowledge and inadvertently diminishes Natural Knowledge, resulting in utility degradation.

Copied to clipboard

Longfei Yang, Jiyi Li, Sheng Li, Takahiro Shinozaki

Natural Language Interfaces

Challenge:	Multi-domain dialogue state tracking is a challenge for task-oriented dialogue systems . domains and slots are aggregated into a single query to generate domain-slot specific representations .
Approach:	They propose to disentangle domain-slot attention for multi-domain dialogue state tracking by separating query about domains and slots from the attention component.
Outcome:	The proposed approach outperforms the standard multi-head attention with aggregated domain-slot query.

Semantic-Aware Logical Reasoning via a Semiotic Framework (2026.acl-long)

Copied to clipboard

Yunyao Zhang, Xinglang Zhang, Junxi Sheng, Wenbing Li, Junqing Yu, Yi-Ping Phoebe Chen, Wei Yang, Zikai Song

Benchmarking Diverse-Modal Entity Linking with Generative Models (2023.findings-acl)

Challenge:	Existing studies largely overlook the interplay between logical complexity and semantic complexity, limiting their robustness under abstract propositions, ambiguous contexts, and conflicting stances.
Approach:	They propose a semiotic-square-guided framework that integrates automated deduction with reflective verification to manage logical complexity across deeper reasoning chains.
Outcome:	The proposed framework achieves state-of-the-art performance on RepublicQA with 6.25% average gain, and generalizes well to four mainstream logical reasoning benchmarks with an additional 7.05% improvement.

Copied to clipboard

Sijia Wang, Alexander Hanbo Li, Henghui Zhu, Sheng Zhang, Pramuditha Perera, Chung-Wei Hang, Jie Ma, William Yang Wang, Zhiguo Wang, Vittorio Castelli, Bing Xiang, Patrick Ng

MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search (2026.acl-long)

Challenge:	Existing models for diverse-mode entity linking (EL) work well on per modality configurations, but it is more challenging to design a unified model for diverse modality.
Approach:	They propose a generative diverse-modal model that integrates text, image and table . they propose combining a multimodal encoder-decoder paradigm with a fine-tuning GDMM .
Outcome:	The proposed model outperforms state-of-the-art models by 8.51 F1 on average for diverse-modal EL.

Copied to clipboard

Sheng Zhang, Junyi Li, Yingyi Zhang, Pengyue Jia, Yichao Wang, Xiaowei Qian, Wenlin Zhang, Maolin Wang, Yong Liu, Xiangyu Zhao

DCT-Centered Temporal Relation Extraction (2022.coling-1)

Challenge:	Existing methods for memory management struggle to capture fine-grained semantic relations between queries and documents.
Approach:	They propose a framework for reasoning and agentic search that grows fine-grained memory fragments from seed tokens from queries, then retraces and deep refines the memory via a contribution function.
Outcome:	Experiments on eight benchmark datasets show that MemSearch-o1 significantly mitigates memory dilution and more effectively activates reasoning potential of diverse LLMs.

Copied to clipboard

Liang Wang, Peifeng Li, Sheng Xu

Transformer-GCRF: Recovering Chinese Dropped Pronouns with General Conditional Random Fields (2020.findings-emnlp)

Challenge:	Existing work on temporal relation extraction focuses on extracting temporal relations between events . previous work on relation extraction focused on focusing on event-centered tasks .
Approach:	They propose a temporal relation extraction model that unifies events, timexes and DCT . they propose combining event mentions, time expressions and document creation time into a sentence-style model .
Outcome:	The proposed model outperforms baselines on E-E, E-T and E-D significantly.

Copied to clipboard

Jingxuan Yang, Kerui Xu, Jun Xu, Si Li, Sheng Gao, Jun Guo, Ji-Rong Wen, Nianwen Xue

“I See What You Did There”: Can Large Vision-Language Models Understand Multimodal Puns? (2026.acl-long)

Challenge:	Existing approaches to recover dropped pronouns ignore the dependencies between pronounes in neighboring utterances.
Approach:	They propose a framework that combines Transformer network and General Conditional Random Fields to model the dependencies between pronouns in neighboring utterances.
Outcome:	The proposed framework outperforms state-of-the-art models on three Chinese conversation datasets showing that it captures the dependencies between pronouns in neighboring utterances.

Copied to clipboard

Naen Xu, Jiayi Sheng, Changjiang Li, Chunyi Zhou, Yuyuan Li, Tianyu Du, Jun Wang, Zhihui Fu, Jinbao Li, Shouling Ji

Can LLMs be Good Graph Judge for Knowledge Graph Construction? (2025.emnlp-main)

Challenge:	Puns are a common form of rhetorical wordplay that exploits polysemy and phonetic similarity to create humor.
Approach:	They propose a multimodal pun generation pipeline and a model to evaluate their understanding of puns.
Outcome:	The proposed benchmark improves the understanding of multimodal puns by 16.5% in the F1 test.

Copied to clipboard

Haoyu Huang, Chong Chen, Zeang Sheng, Yang Li, Wentao Zhang

Structured Data in NLP

Challenge:	Existing methods for converting unstructured text into structured Knowledge Graphs (KGs) have limitations such as large amount of noise, inaccurate knowledge, and hallucination .
Approach:	They propose a GraphJudge framework to reduce noise in real-world documents . they propose Graphjudge to fine-tune a LLM as a graph judge to enhance quality .
Outcome:	The proposed framework eliminates noise in real-world documents and improves the quality of generated KGs.

SpeechIQ: Speech-Agentic Intelligence Quotient Across Cognitive Levels in Voice Understanding by Large Language Models (2025.acl-long)

Copied to clipboard

Zhen Wan, Chao-Han Huck Yang, Yahan Yu, Jinchuan Tian, Sheng Li, Ke Hu, Zhehuai Chen, Shinji Watanabe, Fei Cheng, Chenhui Chu, Sadao Kurohashi

Zoom Out and Observe: News Environment Perception for Fake News Detection (2022.acl-long)

Challenge:	SIQ quantifies voice understanding abilities and provides unified comparisons between cascaded methods and end-to-end models.
Approach:	They propose a human cognition-inspired evaluation pipeline for voice understanding large language models (LLM_Voice) that quantifies voice understanding abilities and provides unified comparisons between cascaded methods and end-to-end models.
Outcome:	The proposed framework quantifies voice understanding abilities and provides unified comparisons between cascaded methods and end-to-end models, identifies annotation errors in existing benchmarks, and detects hallucinations in LLM_Voice.

Copied to clipboard

Qiang Sheng, Juan Cao, Xueyao Zhang, Rundong Li, Danding Wang, Yongchun Zhu

RGL: A Simple yet Effective Relation Graph Augmented Prompt-based Tuning Approach for Few-Shot Learning (2022.findings-naacl)

Challenge:	Existing methods for fake news detection "zoom in" to verify content with knowledge sources or check readers’ replies to posts but neglect information in the external news environment where a fake news post is created and disseminated.
Approach:	They propose a framework to capture news environment signals and a module to perceive useful signals and assist final prediction.
Outcome:	The proposed framework can improve the performance of basic fake news detectors by capturing the environmental signals of news posts and analyzing the results.

Copied to clipboard

Yaqing Wang, Xin Tian, Haoyi Xiong, Yueyang Li, Zeyu Chen, Sheng Guo, Dejing Dou

Open-World Attribute Mining for E-Commerce Products with Multimodal Self-Correction Instruction Tuning (2025.acl-long)

Challenge:	Pre-trained language models (PLMs) are a good starting point for downstream applications, but it is difficult to generalize them to new tasks given a few labeled samples.
Approach:	They propose to use Relation Graph augmented learning to improve the performance of few-shot natural language understanding tasks by rewriting the input sequence into a cloze question with masks.
Outcome:	Extensive experiments show that Relation Graph augmented learning (RGL) improves performance of prompt-based tuning strategies.

Copied to clipboard

Jiaqi Li, Yanming Li, Xiaoli Shen, Chuanyi Zhang, Guilin Qi, Sheng Bi

FAEDKV: Infinite-Window Fourier Transform for Unbiased KV Cache Compression (2025.findings-emnlp)

Challenge:	Current AM methods focus on extracting attributes from unimodal text, underutilizing multimodal data.
Approach:	They propose a framework for multimodal self-correction instruction tuning to extract new attributes from images and text with Multimodal Large Language Models.
Outcome:	The proposed framework outperforms state-of-the-art methods on two datasets.

Copied to clipboard

Runchao Li, Yao Fu, Mu Sheng, Xianxuan Long, Haotian Yu, Pan Li

Tag-grounded Visual Instruction Tuning with Retrieval Augmentation (2024.emnlp-main)

Challenge:	Current compression strategies, including token eviction and learned projections, often lead to biased representations and may require costly model retraining.
Approach:	They propose a training-free KV cache compression framework that equalizes the contribution of all tokens to the compressed representation.
Outcome:	The proposed framework ensures unbiased information retention in the KV cache.

Copied to clipboard

Daiqing Qi, Handong Zhao, Zijun Wei, Sheng Li

Graph Enhanced Dual Attention Network for Document-Level Relation Extraction (2020.coling-main)

Challenge:	Multimodal Large Language Models (MLLMs) have seen remarkable progress in providing general instruction-following ability, but struggle with critical problems when required to provide a detailed and accurate response to a visual instruction.
Approach:	They propose to enhance the mapping process by using retrieval-augmented tag tokens, which contain rich object-aware information such as object names and attributes.
Outcome:	The proposed model outperforms baselines that share the same language model and training data on 12 benchmarks and shows zero-shot capability when provided with specific datastores.

Copied to clipboard

Bo Li, Wei Ye, Zhonghao Sheng, Rui Xie, Xiangyu Xi, Shikun Zhang

Too Big to Fail: Larger Language Models are Disproportionately Resilient to Induction of Dementia-Related Linguistic Anomalies (2024.findings-acl)

Challenge:	Document-level relation extraction requires inter-sentence reasoning capabilities to capture local and global contextual information for multiple relation facts.
Approach:	They propose to characterize the interaction between sentences and potential relation instances via a Graph Enhanced Dual Attention network (GEDA) . they also propose a simple yet effective regularizer based on the natural duality of the S2R and R2S attentions, whose weights are also supervised by the supporting evidence of relation instances during training.
Outcome:	The proposed model achieves competitive performance on an existing large-scale dataset while the predictions can be interpretable and easily observed.

Copied to clipboard

Changye Li, Zhecheng Sheng, Trevor Cohen, Serguei Pakhomov

Forewarned is Forearmed: Pre-Synthesizing Jailbreak-like Instructions to Enhance LLM Safety Guardrail to Potential Attacks (2025.findings-emnlp)

Challenge:	Existing studies show that the attention mechanism in transformer-based NLMs may present an analogue to the notions of cognitive and brain reserve.
Approach:	They propose a bidirectional ablation method that masks attention heads to display degradation of similar magnitude to masking in smaller models.
Outcome:	The proposed method exhibits properties attributed to the concepts of cognitive and brain reserve in human brain studies.

Copied to clipboard

Sheng Liu, Qiang Sheng, Danding Wang, Yang Li, Guang Yang, Juan Cao

Robustness in NLP

Challenge:	Despite advances in improving large language model (LLM) to refuse to answer malicious instructions, LLMs remain vulnerable to jailbreak attacks where attackers generate instructions with distributions differing from safety alignment corpora.
Approach:	They propose a framework that leverages embedding space distribution analysis to generate jailbreak-like instructions.
Outcome:	The proposed framework shows significant decreases in attack success rate on Qwen2.5, Llama3.1, and Llma3.2 without compromising their utility.

Unveiling Factual Recall Behaviors of Large Language Models through Knowledge Neurons (2024.emnlp-main)

Copied to clipboard

Yifei Wang, Yuheng Chen, Wanting Wen, Yu Sheng, Linjing Li, Daniel Zeng

CoVoGER: A Multilingual Multitask Benchmark for Speech-to-text Generative Error Correction with Large Language Models (2025.emnlp-main)

Challenge:	Recent advances in Large Language Models have underscored their exceptional reasoning prowess with natural language understanding across a broad spectrum of tasks.
Approach:	They examine whether Large Language Models actively recall or retrieve their internal repositories of factual knowledge when faced with reasoning tasks.
Outcome:	The proposed model improves reasoning performance while suppressing it leads to notable degradation.

Copied to clipboard

Zhengdong Yang, Zhen Wan, Sheng Li, Chao-Han Huck Yang, Chenhui Chu

Cross-Document Event Coreference Resolution on Discourse Structure (2023.emnlp-main)

Challenge:	Large language models can fix recognition or translation errors that traditional rescoring cannot fix.
Approach:	They propose a benchmark for GER that covers both ASR and speech-to-text translation across 15 languages and 28 language pairs.
Outcome:	The proposed benchmark is built on common voice 20.0 and CoVoST-2 with Whisper and SeamlessM4T.

Copied to clipboard

Xinyu Chen, Sheng Xu, Peifeng Li, Qiaoming Zhu

Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling (2025.naacl-long)

Challenge:	Experimental results show that our proposed model outperforms several baselines and achieves the competitive performance with the start-of-the-art baselines.
Approach:	They propose to use discourse rhetorical structure constructor to construct tree structures to represent documents and a multi-layer perceptron to capture similarities of event mention pairs.
Outcome:	The proposed model outperforms baselines and achieves competitive performance with the start-of-the-art baselines.

Copied to clipboard

Guangya Wan, Yuqi Wu, Jie Chen, Sheng Li

Reducing Token Redundancy in LVLMs: A Systematic Review of Token Pruning Methods (2026.acl-long)

Challenge:	Large Language Models (LLMs) generate reasoning paths before answers, but lack a systematic approach to determine optimal number of samples or select the most faithful rationale.
Approach:	They propose a framework that evaluates the quality of reasoning and consistency of answers for each generated sample and uses criteria-based stopping and weighted majority voting to guide early stopping decisions and rationale selection.
Outcome:	The proposed framework outperforms existing methods while maintaining accuracy.

Copied to clipboard

Hanzhang Yuan, Mengxuan Hu, Wenhao Zhang, Tianlong Wang, Zhongliang Zhou, Jiasen Lu, Sheng Li

Visual Data in NLP

Challenge:	Large Vision-Language Models (LVLMs) excel at visual understanding but face severe computational bottlenecks when processing high-resolution images and long videos due to massive visual token counts.
Approach:	They propose a taxonomy categorizing methods into vision-side, LLM-side and hybrid paradigms and analyze token selection mechanisms and pruning strategy.
Outcome:	The proposed method selectively removes less informative tokens while maintaining performance.

When Truthful Representations Flip Under Deceptive Instructions? (2025.emnlp-main)

Copied to clipboard

Xianxuan Long, Yao Fu, Runchao Li, Mu Sheng, Haotian Yu, Xiaotian Han, Pan Li

Representation Learning

Challenge:	Large language models (LLMs) follow maliciously crafted instructions to generate deceptive responses, posing safety challenges.
Approach:	They use Sparse Autoencoders to analyze LLM's internal representations to determine when and how they "flip" from truthful to deceptive under deceptively crafted instructions.
Outcome:	The proposed model's True/False output is predictable across all conditions based on the model''s representation, and the Deceptive instructions induce significant representational shifts compared to Truthful/Neutral representations.

CasEE: A Joint Learning Framework with Cascade Decoding for Overlapping Event Extraction (2021.findings-acl)

Copied to clipboard

Jiawei Sheng, Shu Guo, Bowen Yu, Qian Li, Yiming Hei, Lihong Wang, Tingwen Liu, Hongbo Xu

DYNTEXT: Semantic-Aware Dynamic Text Sanitization for Privacy-Preserving LLM Inference (2025.findings-acl)

Challenge:	Existing methods assume that events appear in sentences without overlaps . overlapping event extraction is a challenging task in natural language understanding .
Approach:	They propose a joint learning framework with cascade decoding for overlapping event extraction . they sequentially perform type detection, trigger extraction and argument extraction based on the specific former prediction .
Outcome:	The proposed framework improves on a public event extraction benchmark . it sequentially performs type detection, trigger extraction and argument extraction .

Copied to clipboard

Juhua Zhang, Zhiliang Tian, Minghang Zhu, Yiping Song, Taishu Sheng, Siyi Yang, Qiunan Du, Xinwang Liu, Minlie Huang, Dongsheng Li

Simple or Complex? Complexity-controllable Question Generation with Soft Templates and Deep Mixture of Experts Model (2021.findings-emnlp)

Challenge:	Existing methods to protect privacy of sensitive data are differential privacy (DP) and DP is used to protect users from privacy leakage.
Approach:	They propose an LDP-based Dynamic Text sanitization for privacy-preserving LLM inference that dynamically constructs semantic-aware adjacency lists of sensitive tokens to sample non-sensitive tokens for perturbation.
Outcome:	The proposed model excels on three datasets.

Copied to clipboard

Sheng Bi, Xiya Cheng, Yuan-Fang Li, Lizhen Qu, Shirong Shen, Guilin Qi, Lu Pan, Yinlin Jiang

Recovering dropped pronouns in Chinese conversations via modeling their referents (N19-1)

Challenge:	Existing work on complex questions does not consider controlling complexity of generated questions.
Approach:	They propose an end-to-end neural complexity-controllable question generation model that incorporates a mixture of experts as the selector of soft templates to capture question similarity while avoiding the expensive construction of actual templates.
Outcome:	The proposed model is superior to state-of-the-art methods in both automatic and manual evaluations on two benchmark QA datasets.

Copied to clipboard

Jingxuan Yang, Jianzhuo Tong, Si Li, Sheng Gao, Jun Guo, Nianwen Xue

Dialogue Systems & Conversational Agents

Challenge:	Pronouns are often dropped in conversational genres as their referents can be easily understood from context.
Approach:	They propose an end-to-end neural network model to recover dropped pronouns in conversational data.
Outcome:	The proposed model improves on three different conversational genres.

Topic Tensor Network for Implicit Discourse Relation Recognition in Chinese (P19-1)

Copied to clipboard

Sheng Xu, Peifeng Li, Fang Kong, Qiaoming Zhu, Guodong Zhou

Challenge:	Currently, most studies on implicit discourse relation recognition use sentence-level representations . Chinese is a paratactic language that tends to pro-drop clause connectives .
Approach:	They propose a topic tensor network to recognize Chinese implicit discourse relations with both sentence-level and topic-level representations.
Outcome:	The proposed model outperforms state-of-the-art models in micro and macro F1 scores on a Chinese discourse corpus.

ProReason: Multi-Modal Proactive Reasoning with Decoupled Eyesight and Wisdom (2025.emnlp-main)

Copied to clipboard

Jingqi Zhou, Sheng Wang, Jingwei Dong, Kai Liu, Lei Li, Jiahui Gao, Jiyue Jiang, Lingpeng Kong, Chuan Wu

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

Challenge:	Large vision-language models often prioritize language knowledge over image information on visual reasoning tasks, incurring performance degradation.
Approach:	They propose a visual reasoning framework that decouples vision-reasoning capabilities and multi-run proactive perception.
Outcome:	The proposed framework outperforms existing models on benchmarks for open-source and closed-source models with 13.2% performance gain.

Copied to clipboard

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

Green & Sustainable NLP

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.

MMAD:Multi-modal Movie Audio Description (2024.lrec-main)

Copied to clipboard

Xiaojun Ye, Junhao Chen, Xiang Li, Haidong Xin, Chao Li, Sheng Zhou, Jiajun Bu

Code Membership Inference for Detecting Unauthorized Data Use in Code Pre-trained Language Models (2024.findings-emnlp)

Challenge:	Current methods of creating accessible movies rely on manual work, resulting in high costs and limited scalability.
Approach:	They propose a multi-modal movie audio description pipeline that generates narrations of information that is not accessible through unimodal hearing in movies.
Outcome:	The proposed pipeline surpasses existing baselines in performance on widely used datasets.

Copied to clipboard

Sheng Zhang, Hui Li, Rongrong Ji

PCRI: Measuring Context Robustness in Multimodal Models for Enterprise Applications (2025.emnlp-industry)

Challenge:	Code pre-trained language models (CPLMs) are trained on open-source code, raising concerns about data infringement.
Approach:	They propose a framework for detecting unauthorized code use in CPLMs . they use signal extraction from pre-training tasks and weighted inference to identify code membership status accurately.
Outcome:	The proposed framework detects unauthorized code use with high accuracy.

Copied to clipboard

Hitesh Laxmichand Patel, Amit Agarwal, Srikant Panda, Hansa Meghwani, Karan Dua, Paul Li, Tao Sheng, Sujith Ravi, Dan Roth

Robustness in NLP

Challenge:	Existing evaluation metrics for Multimodal Large Language Models (MLLMs) are inadequate to assess their robustness to irrelevant or distracting visual context.
Approach:	They propose a patch-context-robustness index to measure MLLMs' robustness to visual context variations.
Outcome:	The proposed score measures the robustness of MLLMs to visual contexts across 15 vision-language benchmarks.

UltraIF: Advancing Instruction Following from the Wild (2025.emnlp-main)

Copied to clipboard

Kaikai An, Li Sheng, Ganqu Cui, Shuzheng Si, Ning Ding, Yu Cheng, Baobao Chang

Retrieved Sequence Augmentation for Protein Representation Learning (2024.emnlp-main)

Challenge:	a lack of transparency has resulted in a gap between research community and leading companies . large language models have demonstrated remarkable capabilities in following complex instructions .
Approach:	They propose a method to build large language models that can follow complex instructions with open-source data.
Outcome:	The proposed approach can synergize complex instructions and filter responses with evaluation questions.

Copied to clipboard

Chang Ma, Haiteng Zhao, Lin Zheng, Jiayi Xin, Qintong Li, Lijun Wu, Zhihong Deng, Yang Lu, Qi Liu, Sheng Wang, Lingpeng Kong

AMPO: Automatic Multi-Branched Prompt Optimization (2024.emnlp-main)

Challenge:	Using multiple sequence alignments (MSA) to extract evolutionary knowledge is limited.
Approach:	They propose to use multiple sequence alignments to augment protein representations . they propose to employ Retrieved Sequence Augmentation to enhance protein representation learning .
Outcome:	The proposed method surpasses MSA Transformer by 5% in structural and property prediction tasks while being 373 times faster.

Copied to clipboard

Sheng Yang, Yurong Wu, Yan Gao, Zineng Zhou, Bin Zhu, Xiaodi Sun, Jian-Guang Lou, Zhiming Ding, Anbang Hu, Yuan Fang, Yunsong Li, Junyan Chen, Linjun Yang

Scaling Vision-Language Models with Sparse Mixture of Experts (2023.findings-emnlp)

Challenge:	Existing prompt engineering techniques are limited to producing single flow instructions, struggling with handling diverse patterns.
Approach:	They propose an automatic prompt optimization method that iteratively develops a multi-branched prompt using failure cases as feedback.
Outcome:	The proposed method achieves the best results across five tasks and demonstrates significant optimization efficiency due to adoption of a minimal search strategy.

Copied to clipboard

Sheng Shen, Zhewei Yao, Chunyuan Li, Trevor Darrell, Kurt Keutzer, Yuxiong He

Generative Error Correction for Emotion-aware Speech-to-text Translation (2025.findings-acl)

Challenge:	a study explores the effectiveness of mixture-of-experts (MoE) techniques in scaling vision-language models . alayrac and colleagues demonstrate the effectiveness and performance of MoE in scaling VLMs .
Approach:	They propose to use sparsely-gated mixture-of-experts techniques to scale vision-language models . they show that MoE can achieve state-of the-art performance over dense models a range of benchmarks .
Outcome:	The proposed approach achieves state-of-the-art performance over dense models of equivalent computational cost.

Copied to clipboard

Zhengdong Yang, Sheng Li, Chenhui Chu

Mitigating Confounding in Speech-Based Dementia Detection through Weight Masking (2025.acl-long)

Challenge:	Despite recent advances in speech-to-text translation, the impact of the emotion content has been overlooked.
Approach:	They propose to use generative error correction (GER) to generate the translation based on the decoded N-best hypotheses and combine emotion and sentiment labels into the LLM finetuning process to enable the model to consider the emotion content.
Outcome:	The proposed model can translate speech in English-Chinese using GER and emotion and sentiment labels.

Copied to clipboard

Zhecheng Sheng, Xiruo Ding, Brian Hur, Changye Li, Trevor Cohen, Serguei V. S. Pakhomov

Generative Giants, Retrieval Weaklings: Why do Multimodal Large Language Models Fail at Multimodal Retrieval? (2026.findings-acl)

Challenge:	Pre-trained neural language models fine-tuned on AD transcripts perform well, but little research has explored the effects of the gender of the speakers represented by these transcripts.
Approach:	They propose to use the Extended Confounding Filter and the Dual Filter to isolate and ablate weights associated with gender in dementia datasets.
Outcome:	The proposed methods overfit to training data distributions and disrupt gender-related weights, with the trade-off of slightly reduced dementia detection performance.

Copied to clipboard

Hengyi Feng, Zeang Sheng, Meiyi Qiang, Yang Li, Wentao Zhang

Supervised Treebank Conversion: Data and Approaches (P18-1)

Challenge:	Rapid advances in multimodal large language models have revolutionized cross-modality understanding.
Approach:	They propose a method that uses whitening transformations to adjust MLLM representation spaces . they propose ML models that are dominated by textual semantics and visual semantics .
Outcome:	The proposed approach improves zero-shot multimodal retrieval performance without fine-tuning efforts.

Copied to clipboard

Xinzhou Jiang, Zhenghua Li, Bo Zhang, Min Zhang, Sheng Li, Luo Si

Syntactic Text Processing

Challenge:	Existing work on treebank conversion focuses on unsupervised treebanks . lack of manually labeled data means that sentences have two syntactic trees at the same time.
Approach:	They propose supervised treebank conversion using bi-tree aligned sentences . they propose two conversion approaches based on state-of-the-art deep biaffine parser .
Outcome:	The proposed method outperforms the state-of-the-art deep biaffine parser on the English WSJ dataset by 0.97 (93.76% -92.79%)

COMPASS: Enhancing Agent Long-Horizon Reasoning with Evolving Context (2026.acl-long)

Copied to clipboard

Guangya Wan, Mingyang Ling, Xiaoqi Ren, Rujun Han, Sheng Li, Zizhao Zhang

Exploiting Entity BIO Tag Embeddings and Multi-task Learning for Relation Extraction with Imbalanced Data (P19-1)

Challenge:	Long-horizon tasks that require sustained reasoning and multiple tool interactions remain challenging for LLM agents.
Approach:	They propose a framework that separates tactical execution, strategic oversight, and context organization into three specialized components.
Outcome:	The proposed framework improves accuracy by 20% relative to baselines on GAIA, BrowseComp, and Humanity’s Last Exam tasks.

Copied to clipboard

Wei Ye, Bo Li, Rui Xie, Zhonghao Sheng, Long Chen, Shikun Zhang

Aligning Large Multimodal Models with Factually Augmented RLHF (2024.findings-acl)

Challenge:	Existing methods to perform relation extraction are feature-based or kernel-based, but the results of our study show that they can improve the performance of a baseline model with more than 10% absolute increase in F1-score.
Approach:	They propose a multi-task architecture which jointly trains a model to perform relation identification with cross-entropy loss and relation classification with ranking loss.
Outcome:	The proposed model outperforms the state-of-the-art models on ACE 2005 Chinese and English corpus and significantly improves the performance of a baseline model with more than 10% increase in F1-score.

Copied to clipboard

Zhiqing Sun, Sheng Shen, Shengcao Cao, Haotian Liu, Chunyuan Li, Yikang Shen, Chuang Gan, Liangyan Gui, Yu-Xiong Wang, Yiming Yang, Kurt Keutzer, Trevor Darrell

PAR2-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering (2026.acl-industry)

Challenge:	Large Multimodal Models (LMMs) are built across modalities and the misalignment between two modality can result in "hallucination" . developing LMMs faces challenges such as a lack of data and a limited number of data sets.
Approach:	They propose a new algorithm that augments the reward model with additional factual information such as image captions and ground-truth multi-choice options.
Outcome:	The proposed approach improves on the LLaVA-Bench dataset with the 96% performance level of the text-only GPT-4 and an improvement of 60% on MMHAL-BENCH over other baselines.

Copied to clipboard

Xingyu Li, Rongguang Wang, Yuying Wang, Mengqing Guo, Chenyang Li, Tao Sheng, Sujith Ravi, Dan Roth

Information Retrieval

Challenge:	Multi-hop question answering is a practical bottleneck in industry applications . large language models (LLMs) fail frequently when evidence coverage is incomplete or reasoning trajectories drift .
Approach:	They propose a training-free two-stage framework that separates coverage from commitment . it performs breadth-first anchoring to build a high-recall evidence frontier . compared with IRCoT, it achieves 23.5% higher answer accuracy .
Outcome:	The proposed framework outperforms strong baselines in MHQA benchmarks and achieves 23.5% higher answer accuracy and 10.5% NDCG gains in retrieval quality.

Hierarchical Chinese Legal event extraction via Pedal Attention Mechanism (2020.coling-main)

Copied to clipboard

Shirong Shen, Guilin Qi, Zhen Li, Sheng Bi, Lusheng Wang

JW-SVD: Bridging the Cross-Modal Mismatch in Post-Training MLLM Compression (2026.acl-long)

Challenge:	Existing methods for event extraction cannot express connections between arguments, which are crucial in legal events.
Approach:	They propose a dynamic event structure for Chinese legal events to distinguish between similar events by hierarchical event features for event detection and a pedal attention mechanism to extract the semantic relation between two words through their dependent adjacent words.
Outcome:	The proposed model surpasses state-of-the-art models on a Chinese legal event dataset.

Copied to clipboard

Runchao Li, Yao Fu, Mu Sheng, Haotian Yu, Xianxuan Long, Kenneth A. Loparo

A Neural Local Coherence Analysis Model for Clarity Text Scoring (2020.coling-main)

Challenge:	Existing methods for compression of Multimodal Large Language Models lack multimodal adaptation to preserve cross-modal synergy.
Approach:	They propose a framework that aligns vision and language manifolds via a Joint Covariance basis and propose Global Spectrum-Aware Truncation to dynamically transfer parameter budget to the sensitive Backbone.
Outcome:	Experiments on Qwen2.5-VL and Llama-3-Next confirm that JW-SVD retains both text and image capabilities.

Copied to clipboard

Panitan Muangkammuen, Sheng Xu, Fumiyo Fukumoto, Kanda Runapongsa Saikaew, Jiyi Li

Uncertainty Unveiled: Can Exposure to More In-context Examples Mitigate Uncertainty for Large Language Models? (2025.findings-acl)

Challenge:	Existing methods for scoring text clarity use local coherence between adjacent sentences . local cohesion is one of the main properties to identify whether a text is well-structured or not.
Approach:	They propose a method for scoring text clarity by utilizing local coherence between adjacent sentences.
Outcome:	The proposed method improves on the PeerRead benchmark dataset.

Copied to clipboard

Yifei Wang, Yu Sheng, Linjing Li, Daniel Dajun Zeng

Towards Speech Dialogue Translation Mediating Speakers of Different Languages (2023.findings-acl)

Challenge:	Recent advances in handling long sequences have unlocked new possibilities for long-context in-contact learning (ICL).
Approach:	They investigate how increased examples influence predictive uncertainty . they quantify uncertainty across different “shot” configurations and focus on EU .
Outcome:	The proposed model reduces uncertainty in simple and complex tasks by injecting task-specific knowledge.

Copied to clipboard

Shuichiro Shimizu, Chenhui Chu, Sheng Li, Sadao Kurohashi

Speech & Audio in NLP

Challenge:	a new task is proposed to mediate speakers of different languages using speech dialogue translation . we consider context as an important aspect that needs to be addressed in this task . speech translation (ST) has also recently shown success in monologue translation - but no study has focused on ST of dialogues .
Approach:	They propose a task to mediate speakers of different languages using speech dialogue translation . they construct a speechBSD dataset and conduct baseline experiments .
Outcome:	The proposed task mediates speakers of different languages using speech dialogue translation dataset . it shows that bilingual context performs better in our settings .

Towards Scalable Lightweight GUI Agents via Multi-role Orchestration (2026.findings-acl)

Copied to clipboard

Ziwei Wang, Junjie Zheng, Leyang Yang, Sheng Zhou, Xiaoxuan Tang, Fang Zhouhua, Zhiwei Liu, Dajun Chen, Yong Li, Jiajun Bu

Challenge:	Advanced GUI agents suffer from prohibitive deployment costs on resource-constrained devices.
Approach:	They propose a lightweight GUI agent with GUI-specific knowledge and task scalability . LAMO-3B supports monolithic execution and MAS-style orchestration .
Outcome:	The proposed GUI agent LAMO-3B supports monolithic execution and MAS-style orchestration.

from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors (2025.acl-long)

Copied to clipboard

Yu Yan, Sheng Sun, Zenghao Duan, Teli Liu, Min Liu, Zhiyi Yin, LeiJingyu LeiJingyu, Qi Li

Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem (2020.findings-emnlp)

Challenge:	Recent studies have exposed the risk of Large Language Models (LLMs) generating harmful content by jailbreak attacks.
Approach:	They propose a framework that exploits AdVersArial meTAphoR to induce LLMs to calibrate harmful metaphors for jailbreaking.
Outcome:	The proposed framework can successfully jailbreak Large Language Models (LLMs) by leveraging the AdVersArial meTAphoR (AVATAR) framework achieves state-of-the-art attack success rate across multiple advanced LLMs.

Copied to clipboard

Shucheng Li, Lingfei Wu, Shiwei Feng, Fangli Xu, Fengyuan Xu, Sheng Zhong

Multilinguality

Challenge:	Graph2Tree model encodes graph-structured input and decodes tree-structures output.
Approach:	They propose a novel Graph-to-Tree Neural Network consisting of a graph encoder and a hierarchical tree decoder that encodes an augmented graph-structured input and decodes a tree-structure-output.
Outcome:	The proposed model outperforms or matches the performance of other state-of-the-art models on two problems, neural semantic parsing and math word problem.

HyperMem: Hypergraph Memory for Long-Term Conversations (2026.acl-long)

Copied to clipboard

Juwei Yue, Chuanrui Hu, Jiawei Sheng, Zuyi Zhou, Wenyuan Zhang, Tingwen Liu, Li Guo, Yafeng Deng

Natural Language Interfaces

Challenge:	Existing approaches to long-term memory management rely on pairwise relations, causing fragmented retrieval.
Approach:	They propose a hypergraph-based hierarchical memory architecture that explicitly models high-order associations using hyperedges.
Outcome:	Experiments show that HyperMem achieves state-of-the-art performance with 92.73% accuracy for long-term conversations.

Enhancing the Comprehensibility of Text Explanations via Unsupervised Concept Discovery (2025.findings-acl)

Copied to clipboard

Yifan Sun, Danding Wang, Qiang Sheng, Juan Cao, Jintao Li

No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users (2025.findings-emnlp)

Challenge:	Existing concepts-based explainable approaches do not discover unseen concepts . a recent approach to solve this problem is concept-based explanations .
Approach:	They propose a framework that extracts comprehensible concepts automatically with no annotations . ECO-Concept uses an object-centric architecture to extract task-specific semantic concepts .
Outcome:	a new framework extracts comprehensible concepts with no concept annotations . the proposed framework outperforms existing methods in computability tests on diverse tasks .

Copied to clipboard

Mengxuan Hu, Hongyi Wu, Ronghang Zhu, Zihan Guan, Dongliang Guo, Daiqing Qi, Sheng Li

Improving Fake News Detection of Influential Domain via Domain- and Instance-Level Transfer (2022.coling-1)

Challenge:	Retrieval-augmented generation is widely adopted for its effectiveness and cost-efficiency in mitigating hallucinations.
Approach:	They propose a practical three-level threat model from the perspective of user fairness awareness.
Outcome:	The proposed model shows that RAG can undermine fairness alignment without fine-tuning or retraining.

Copied to clipboard

Qiong Nan, Danding Wang, Yongchun Zhu, Qiang Sheng, Yuhui Shi, Juan Cao, Jintao Li

Evaluating Generalization Capability of Language Models across Abductive, Deductive and Inductive Logical Reasoning (2025.coling-main)

Challenge:	Social media spreads both real news and fake news in various domains including politics, health, entertainment, etc.
Approach:	They propose a Domain- and Instance-level Transfer Framework for Fake News Detection which could improve the performance of specific target domains.
Outcome:	The proposed framework improves performance of target domains by hurting other domains, resulting in unsatisfactory performance in the target domain.

Copied to clipboard

Yu Sheng, Wanting Wen, Linjing Li, Daniel Zeng

Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs (2025.emnlp-main)

Challenge:	Recent research in language models (LMs) have demonstrated remarkable performance on many natural language tasks, yet to what extent LMs possess the capability of generalizing to unseen logical rules remains unclear.
Approach:	They propose to use a dataset to assess the generalization capabilities of LMs on ADI reasoning to assess their generalization abilities.
Outcome:	The proposed dataset shows that LMs perform poorly on ADI reasoning tasks and lacks generalization capabilities.

Copied to clipboard

Yao Fu, Xianxuan Long, Runchao Li, Haotian Yu, Mu Sheng, Xiaotian Han, Yu Yin, Pan Li

Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge (2023.findings-acl)

Challenge:	Quantization enables efficient deployment of large language models in resource-constrained environments . but impact on truthfulness remains largely unexplored .
Approach:	They propose a framework to assess the truthfulness of quantized large language models . they find quantized models retain internally truthful representations but produce false outputs .
Outcome:	The framework assesses the truthfulness of quantized models across three dimensions . it finds that quantized model models retain internally truthful representations but are more susceptible to false outputs .

Copied to clipboard

Xingyu Fu, Sheng Zhang, Gukyeong Kwon, Pramuditha Perera, Henghui Zhu, Yuhao Zhang, Alexander Hanbo Li, William Yang Wang, Zhiguo Wang, Vittorio Castelli, Patrick Ng, Dan Roth, Bing Xiang

What Really Matters for Table LLMs? A Meta-Evaluation of Model and Data Effects (2026.findings-eacl)

Challenge:	Open-ended Visual Question Answering (VQA) requires models to reason over visual and natural language inputs using world knowledge.
Approach:	They propose a new VQA pipeline that deploys a generate-then-select strategy guided by world knowledge for the first time.
Outcome:	The proposed pipeline expands the knowledge coverage from in-domain training data by 4.1% on OK-VQA, without additional computation cost.

Copied to clipboard

Naihao Deng, Sheng Zhang, Henghui Zhu, Shuaichen Chang, Jiani Zhang, Alexander Hanbo Li, Chung-Wei Hang, Hideo Kobayashi, Yiqun Hu, Patrick Ng