Papers by Yiming Zhang

HalluAudio: A Comprehensive Benchmark for Hallucination Detection in Large Audio-Language Models (2026.acl-long)

Challenge:	Current training recipes often rely on datasets dominated by short annotations with limited rationales, hindering the models' ability to generalize to tasks requiring comprehensive reasoning.
Approach:	They propose a two-stage post-training strategy that augments short answers with CoT reasoning generated by GPT-4o, enhancing the VLM's CoT capabilities through fine-tuning.
Outcome:	The proposed strategy enhances the model's CoT capabilities through fine-tuning and reinforcement learning.

Copied to clipboard

Feiyu Zhao, Yiming Chen, Wenhuan Lu, Daipeng Zhang, Xianghu Yue, Jianguo Wei

Generate, Discriminate and Contrast: A Semi-Supervised Sentence Representation Learning Framework (2022.emnlp-main)

Challenge:	Existing studies on hallucination focus on text or vision, while few audio-oriented studies are limited in scale, modality coverage, and diagnostic depth.
Approach:	They propose a large-scale benchmark for evaluating hallucinations across speech, sound, and music.
Outcome:	The proposed model improves hallucination rate, yes/no bias, error-type analysis, and refusal rate.

Copied to clipboard

Yiming Chen, Yan Zhang, Bin Wang, Zuozhu Liu, Haizhou Li

GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment (2026.acl-long)

Challenge:	Existing supervised sentence embedding techniques rely on expensive human-annotated sentence pairs as the supervised signals.
Approach:	They propose a semi-supervised sentence embedding framework that leverages large-scale unlabeled data.
Outcome:	The proposed framework surpasses state-of-the-art methods on four domain adaptation tasks.

Copied to clipboard

Jiwei Tang, Zhicheng Zhang, Shunlong Wu, Jingheng Ye, Lichen Bai, Zitai Wang, Tingwei Lu, Lin Hai, Yiming Zhao, Hai-Tao Zheng, Hong-Gee Kim

DeFine: Decision-Making with Analogical Reasoning over Factor Profiles (2025.findings-acl)

Challenge:	Large Language Models (LLMs) have achieved remarkable performance across NLP tasks . however, in long-context scenarios, they face high computational cost and information redundancy.
Approach:	They propose an encoder-decoder context compression framework that generates a compact sequence of soft tokens for downstream tasks.
Outcome:	Experiments show that GMSA outperforms baselines on multiple long-context question answering and summarization benchmarks while maintaining low end-to-end latency.

Copied to clipboard

Yebowen Hu, Xiaoyang Wang, Wenlin Yao, Yiming Lu, Daoan Zhang, Hassan Foroosh, Dong Yu, Fei Liu

CMQA: A Dataset of Conditional Question Answering with Multiple-Span Answers (2022.coling-1)

Challenge:	Large language models are ideal for decision-making, but they can be difficult to process when they are verbose and include repetition, hedging, and vagueness.
Approach:	They propose a framework that constructs probabilistic factor profiles from complex scenarios and integrates them with analogical reasoning to guide LLMs in making decisions in new situations.
Outcome:	The proposed framework separates the tasks of quantifying uncertainty and incorporating it into LLM decision-making.

Copied to clipboard

Yiming Ju, Weikang Wang, Yuanzhe Zhang, Suncong Zheng, Kang Liu, Jun Zhao

DARM: Distribution-Aware Reward Modeling by Alleviating Biases from Low Preference-Context Dependency Data (2026.acl-long)

Challenge:	Existing QA datasets only contain unconditional and parallel answers . conditional question answering with hierarchical multi-span answers is challenging for the community to solve .
Approach:	They propose a conditional question answering task with hierarchical multi-span answers . they propose CMQA, which contains conditional and hierarchic samples .
Outcome:	The proposed task can be used to build more reliable and sophisticated QA systems.

Copied to clipboard

Shaofan Liu, Guoqiang Zhang, Shihan Dou, Huiyuan Zheng, Yiming Zhou, Junjie Ye, Shaowen Wang, Shichun Liu, Jiazheng Zhang, Tao Gui, Qi Zhang, Xuanjing Huang

Challenge:	Existing methods for training reward models are vulnerable to context neglect and degraded accuracy.
Approach:	They propose distribution-aware reward modeling that augments the RM objective with a conditional mutual information regularizer that maximizes context and the predicted reward conditioned on the response.
Outcome:	The proposed model improves performance in RLHF and improves accuracy in other settings.

LLM-Driven Knowledge Injection Advances Zero-Shot and Cross-Target Stance Detection (2024.naacl-short)

Copied to clipboard

Zhao Zhang, Yiming Li, Jin Zhang, Hui Xu

Sentiment Analysis

Challenge:	Existing methods for stance detection focus on background information and not on the accompanying input texts.
Approach:	They propose to prompt Large Language Models to explicitly extract the relationship between paired text and unseen target as contextual knowledge and inject it into a generation model BART to exploit the rich contexts and semantics.
Outcome:	The proposed model is able to detect stance labels in zero-shot and cross-target scenarios.

MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models (2025.findings-acl)

Copied to clipboard

Boyang Xue, Hongru Wang, Rui Wang, Sheng Wang, Zezhong Wang, Yiming Du, Bin Liang, Wenxuan Zhang, Kam-Fai Wong

FinDVer: Explainable Claim Verification over Long and Hybrid-content Financial Documents (2024.emnlp-main)

Challenge:	Existing studies on LLM confidence estimations in languages other than English have been limited to English.
Approach:	They propose to use question-related language to prompt LLMs to assess their confidence in large language models.
Outcome:	The proposed model improves on question-related language prompts for LS tasks, while English exhibits notable linguistic dominance in confidence estimations.

Copied to clipboard

Yilun Zhao, Yitao Long, Tintin Jiang, Chengye Wang, Weiyuan Chen, Hongjun Liu, Xiangru Tang, Yiming Zhang, Chen Zhao, Arman Cohan

Unveiling the Achilles’ Heel of NLG Evaluators: A Unified Adversarial Framework Driven by Large Language Models (2024.findings-acl)

Challenge:	FinDVer is a benchmark to evaluate the explainable claim verification capabilities of LLMs . financial documents are typically long, intricate and dense, and they include both quantita and numerical reasoning.
Approach:	They propose a benchmark to evaluate the explainable claim verification capabilities of LLMs . they assess 25 LLM systems under long-context and RAG settings .
Outcome:	The proposed benchmark can be used to evaluate the explainable claim verification capabilities of LLMs in financial documents.

Copied to clipboard

Yiming Chen, Chen Zhang, Danqing Luo, Luis Fernando D’Haro, Robby Tan, Haizhou Li

Meta-Reasoning: Semantics-Symbol Deconstruction for Large Language Models (2024.findings-acl)

Challenge:	Recent studies have highlighted various neural metrics that align well with human evaluations.
Approach:	They propose a black-box adversarial framework that generates strong disagreements between human and victim evaluators.
Outcome:	The proposed framework can significantly improve the performance of human and victim evaluators.

Copied to clipboard

Yiming Wang, Zhuosheng Zhang, Pei Zhang, Baosong Yang, Rui Wang

GODBench: A Benchmark for Multimodal Large Language Models in Video Comment Art (2025.acl-long)

Challenge:	Existing methods rely on syntactically mapping natural languages to complete formal languages like Python and SQL.
Approach:	They propose to deconstruct reasoning-independent semantic information into generic symbolic representations, thereby efficiently capturing more generalized reasoning knowledge.
Outcome:	The proposed method improves in-context reasoning accuracy, learning efficiency, out-of-domain generalization, and output stability compared to the Chain-of thought technique.

Copied to clipboard

Yiming Lei, Chenkai Zhang, Zeming Liu, Haitao Leng, ShaoGuo Liu, Tingting Gao, Qingjie Liu, Yunhong Wang

pEBR: A Probabilistic Approach to Embedding Based Retrieval (2025.emnlp-industry)

Challenge:	Existing benchmarks for video comment art are constrained by their limited modalities and insufficient categories, hindering creativity in video-based comment art creation.
Approach:	They propose a benchmark that integrates video and text modalities to evaluate MLLMs’ abilities to compose video Comment art.
Outcome:	The proposed framework integrates video and text modalities to evaluate MLLMs’ abilities to compose video comment art.

Copied to clipboard

Han Zhang, Yunjiang Jiang, Mingming Li, Haowei Yuan, Yiming Qiu, Wen-Yun Yang

DORY: Deliberative Prompt Recovery for LLM (2024.findings-acl)

Challenge:	Existing embedding-based retrieval systems rely on heuristic and suboptimal cutoffs for item retrieval.
Approach:	They propose a probabilistic Embedding-Based Retrieval framework that learns a shared semantic representation space for both queries and items.
Outcome:	The proposed framework improves retrieval precision and recall, and ablation studies show it captures the differences between head-to-tail queries.

Copied to clipboard

Lirong Gao, Ru Peng, Yiming Zhang, Junbo Zhao

NegVQA: Can Vision Language Models Understand Negation? (2025.findings-acl)

Challenge:	Large language models (LLMs) are used for their groundbreaking performance across various tasks.
Approach:	They propose a method that leverages uncertainty to recover prompts accurately using a single LLM without external resources or models.
Outcome:	The proposed approach outperforms baselines across diverse LLMs and prompt benchmarks and establishes a new state-of-the-art record in prompt recovery tasks.

Copied to clipboard

Yuhui Zhang, Yuchang Su, Yiming Liu, Serena Yeung-Levy

Leveraging Large Language Models for Conversational Multi-Doc Question Answering: The First Place of WSDM Cup 2024 (2025.findings-acl)

Challenge:	NegVQA is a visual question answering (VQA) benchmark consisting of 7,379 two-choice questions covering diverse negation scenarios and image-question distributions.
Approach:	They propose a visual question answering benchmark consisting of 7,379 two-choice questions covering diverse negation scenarios and image-question distributions.
Outcome:	The proposed model fails to correctly interpret negation, leading to critical errors in interactive AI systems.

Copied to clipboard

Yiming Li, Zhao Zhang

Rethinking RL Evaluation: Can Benchmarks Truly Reveal Failures of RL Methods? (2026.findings-acl)

Challenge:	WSDM Cup 2024 presents a challenge for conversational multi-doc question answering using large language models . a hybrid training strategy is developed to make the most of in-domain unlabeled data .
Approach:	They propose a conversational multi-doc question answering challenge in WSDM Cup 2024 . they adapt LLMs to the task, then devise a hybrid training strategy to make the most of unlabeled data.
Outcome:	The proposed approach ranked 1st in the WSDM Cup 2024 challenge . it exploits the superior natural language understanding and generation capability of Large Language Models .

Copied to clipboard

Zihan Chen, Yiming Zhang, Hengguang Zhou, Zenghui Ding, Yining Sun, Cho-Jui Hsieh

Challenge:	Existing benchmarks for reinforcement learning for large language models do not accurately assess generalization.
Approach:	They propose three core principles for designing more faithful benchmarks: sufficient difficulty, balanced evaluation, and distributional robustness.
Outcome:	The proposed benchmarks do not accurately assess generalization across distribution shifts, difficulty levels, and counterfactual scenarios.

SEAD: A Surrogate-free Label-only Membership Inference Attack against Pre-trained LLMs with Semantic-Aware Density (2026.findings-acl)

Copied to clipboard

Biao Yi, Jiahao Li, Yiming Li, Yu He, Baolei Zhang, Zheli Liu, Dacheng Tao

When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations (2025.acl-long)

Challenge:	Existing membership inference attacks require access to complete logits, but such access is often unavailable in real-world deployments where only the generated text is exposed.
Approach:	They propose a surrogate-free label-only MIA approach that directly estimates token probabilities through Monte Carlo sampling of the target model.
Outcome:	The proposed approach outperforms existing label-only attacks and serves as a foundational density estimator in the label-exclusive setting.

Copied to clipboard

Huaizhi Ge, Yiming Li, Qifan Wang, Yongfeng Zhang, Ruixiang Tang

KwaiChat: A Large-Scale Video-Driven Multilingual Mixed-Type Dialogue Corpus (2025.findings-naacl)

Challenge:	Recent studies have shown that Large Language Models (LLMs) are susceptible to backdoor attacks, where triggers embedded in poisoned data can maliciously alter LLMs’ behaviors.
Approach:	They propose to leverage LLMs' generative capabilities to generate human-readable explanations for their decisions, enabling direct comparisons between explanations of clean and poisoned data.
Outcome:	The proposed model produces coherent explanations for clean inputs but logically flawed explanations on poisoned data.

Copied to clipboard

Xiaoming Shi, Zeming Liu, Yiming Lei, Chenkai Zhang, Haitao Leng, Chuan Wang, Qingjie Liu, Wanxiang Che, Yunhong Wang

LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces (2026.findings-acl)

Challenge:	Currently, video-based dialogue systems rely on a single dialogue type, hindering their versatility in practical applications.
Approach:	They propose to generate video-driven multilingual mixed-type dialogues using KwaiChat . they propose to create a video-based multilingual mix of 4 dialogue types, 30 domains, 4 languages, 13 topics .
Outcome:	The proposed model performs best on KwaiChat but is not perfect in this situation.

Copied to clipboard

Yukang Feng, Jianwen Sun, Zelai Yang, Jiaxin Ai, Chuanhao Li, Zizhen Li, Fanrui Zhang, Kang He, Rui Ma, Jifan Lin, Jie Sun, Yang Xiao, Sizhuo Zhou, Wenxiao Wu, Yiming Liu, Pengfei Liu, Shenglin Zhang, Kaipeng Zhang

FLamE: Few-shot Learning from Natural Language Explanations (2023.acl-long)

Challenge:	Existing benchmarks for agentic programming in long-horizon command-line interface tasks are limited by short task horizons, data contamination from GitHub scraping, and a lack of fine-grained evaluation metrics.
Approach:	They propose a benchmark to evaluate agentic capabilities across long-horizon command-line interface tasks.
Outcome:	The proposed benchmarks cover four engineering categories: from scratch, feature addition, bug fixing, and refactoring.

Copied to clipboard

Yangqiaoyu Zhou, Yiming Zhang, Chenhao Tan

RouteMoA: Dynamic Routing without Pre-Inference Boosts Efficient Mixture-of-Agents (2026.acl-long)

Challenge:	Recent work has shown limited utility of natural language explanations in improving classification.
Approach:	They propose a two-stage few-shot learning framework that generates explanations and fine-tunes a smaller model with generated explanations.
Outcome:	The proposed framework increases inference accuracy over strong baselines, but human evaluation reveals that the majority of generated explanations does not adequately justify classification decisions.

Copied to clipboard

Jize Wang, Han Wu, Zhiyuan You, Yiming Song, Yijun Wang, Zifei Shan, Yining Li, Songyang Zhang, Xinyi Le, Cailian Chen, Xinping Guan, Dacheng Tao

Green & Sustainable NLP

Challenge:	Existing methods for mixing-of-agents (MoA) lack model selection criteria and struggle with large model pools.
Approach:	They propose a mixture-of-agents framework with dynamic routing that uses a lightweight scorer to perform initial screening and refines the model scores through self- and cross-assessment.
Outcome:	The proposed framework outperforms existing methods for large model pools and tasks . it reduces cost by 89.8% and latency by 63.6% in the large-scale model pool.

PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning (2026.findings-acl)

Copied to clipboard

Ruixiang Feng, Yuntao Wen, Silin Zhou, Ke Shi, Yifan Wang, Ran Le, Zhenwei An, Zongchao Chen, Chen Yang, Guangyue Peng, Yiming Jia, Dongsheng Wang, Tao Zhang, Lisi Chen, Yang Song, Shen Gao, Shuo Shang

RPDR: A Round-trip Prediction-Based Data Augmentation Framework for Long-Tail Question Answering (2025.emnlp-main)

Challenge:	Existing LRMs often suffer from "overthinking" and excessively long reasoning traces . a dual-level framework for length compression of LRM is proposed .
Approach:	They propose a framework for prefix-protected and difficulty-aware compression under hierarchical supervision.
Outcome:	The proposed framework reduces token usage while improving accuracy on math benchmarks.

Copied to clipboard

Yiming Zhang, Siyue Zhang, Junbo Zhao, Chen Zhao

CLUE: A Chinese Language Understanding Evaluation Benchmark (2020.coling-main)

Challenge:	Long-tail question answering presents significant challenges for large language models due to limited ability to acquire and accurately recall less common knowledge.
Approach:	They propose a data augmentation framework that selects high-quality easy-to-learn training data to enhance dense retrieval models.
Outcome:	The proposed framework improves on two long-tail retrieval benchmarks, PopQA and EntityQuestion, and shows that it outperforms existing retrievers on extremely long-tailed questions.

Copied to clipboard

Liang Xu, Hai Hu, Xuanwei Zhang, Lu Li, Chenjie Cao, Yudong Li, Yechen Xu, Kai Sun, Dian Yu, Cong Yu, Yin Tian, Qianqian Dong, Weitang Liu, Bo Shi, Yiming Cui, Junyi Li, Jun Zeng, Rongzhao Wang, Weijian Xie, Yanting Li, Yina Patterson, Zuoyu Tian, Yiwen Zhang, He Zhou, Shaoweihua Liu, Zhe Zhao, Qipeng Zhao, Cong Yue, Xinrui Zhang, Zhengliang Yang, Kyle Richardson, Zhenzhong Lan

Challenge:	Existing language evaluation benchmarks for English are limited to English . lack of such benchmarks makes it difficult to replicate success in other languages .
Approach:	They introduce a large-scale Chinese language understanding evaluation benchmark . the benchmark uses a set of current state-of-the-art pre-trained Chinese models .
Outcome:	The first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark is released . the benchmark evaluates models across a wide range of tasks on original Chinese text . existing language evaluation benchmarks are mostly limited to English .

PromptSculptor: Multi-Agent Based Text-to-Image Prompt Optimization (2025.emnlp-demos)

Copied to clipboard

Dawei Xiang, Wenyan Xu, Kexin Chu, Tianqi Ding, Zixu Shen, Yiming Zeng, Jianchang Su, Wei Zhang

Low-Resource NLP

Challenge:	PromptSculptor automates the iterative prompt optimization process for Text-to-Image models . previous work focused on generating detailed, high-quality prompts based on user feedback .
Approach:	They propose a framework that decomposes a task into four specialized agents . they use Chain-of-Thought reasoning to transform a short, vague user prompt into a comprehensive, refined prompt.
Outcome:	The proposed framework significantly improves output quality and reduces iterations needed for user satisfaction.

RECOST: External Knowledge Guided Data-efficient Instruction Tuning (2024.findings-acl)

Copied to clipboard

Qi Zhang, Yiming Zhang, Haobo Wang, Junbo Zhao

Fine-Grained Data Ordering Improves Fine-Tuning for Large Language Models (2026.findings-acl)

Challenge:	Considering the high computing power overhead, data-efficient instruction tuning is proposed to reduce the training data size.
Approach:	They propose a framework to improve instruction tuning by integrating external knowledge into a single pipeline.
Outcome:	The proposed method achieves better results with only 1% of the full dataset.

Copied to clipboard

Xiaomeng Hu, Yixuan Tang, Haoze Li, Hao Chen, Qi Zhang, Zhanming Shen, Yiming Zhang, Haobo Wang, Junbo Zhao

PESCO: Prompt-enhanced Self Contrastive Learning for Zero-shot Text Classification (2023.acl-long)

Challenge:	Prior work focused on data preprocessing, focusing on filtering and cleaning data . a study aimed to improve fine-grained scheduling of data order in epochs .
Approach:	They propose a fine-grained scheduling method of data order in epochs to fill this gap . they define data difficulty based on relevance between data and model .
Outcome:	The proposed method improves on pre-training and small-scale fine-tuning experiments 2.4% over baselines.

Copied to clipboard

Yau-Shian Wang, Ta-Chung Chi, Ruohong Zhang, Yiming Yang

CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models (2024.findings-acl)

Challenge:	Existing text classification frameworks require large amounts of human-labeled documents to train .
Approach:	They propose a contrastive learning framework that improves zero-shot text classification . they add prompts to enhance label retrieval and use retrieved labels to enrich training .
Outcome:	The proposed framework achieves state-of-the-art on four benchmark text classification datasets.

Copied to clipboard

Yizhi Li, Ge Zhang, Xingwei Qu, Jiali Li, Zhaoqun Li, Noah Wang, Hao Li, Ruibin Yuan, Yinghao Ma, Kai Zhang, Wangchunshu Zhou, Yiming Liang, Lei Zhang, Lei Ma, Jiajun Zhang, Zuowen Li, Wenhao Huang, Chenghua Lin, Jie Fu

AnchorAttention: Difference-Aware Sparse Attention with Stripe Granularity (2025.emnlp-main)

Challenge:	a recent study shows that large language models have limited generalization in low-resource languages like Chinese.
Approach:	They propose to evaluate the zero-shot generalizability of large language models to the Chinese language . they release only half of the dataset publicly, with the remainder kept private .
Outcome:	The Chinese Instruction-Following Benchmark evaluates the generalizability of LLMs to the Chinese language.

Copied to clipboard

Yu Zhang, Dong Guo, Fang Wu, Guoliang Zhu, Dian Ding, Yiming Zhang

Green & Sustainable NLP

Challenge:	Existing methods for large language models with extended context lengths face significant computational challenges during the prefill phase.
Approach:	They propose a difference-aware, dynamic sparse attention mechanism that efficiently identifies critical attention regions at a finer stripe granularity while adapting to global contextual information.
Outcome:	The proposed model achieves a speedup of 1.44 while maintaining higher recall rates.

ChatMusician: Understanding and Generating Music Intrinsically with LLM (2024.findings-acl)

Copied to clipboard

Ruibin Yuan, Hanfeng Lin, Yi Wang, Zeyue Tian, Shangda Wu, Tianhao Shen, Ge Zhang, Yuhang Wu, Cong Liu, Ziya Zhou, Liumeng Xue, Ziyang Ma, Qin Liu, Tianyu Zheng, Yizhi Li, Yinghao Ma, Yiming Liang, Xiaowei Chi, Ruibo Liu, Zili Wang, Chenghua Lin, Qifeng Liu, Tao Jiang, Wenhao Huang, Wenhu Chen, Jie Fu, Emmanouil Benetos, Gus Xia, Roger Dannenberg, Wei Xue, Shiyin Kang, Yike Guo

Debt Collection Negotiations with Large Language Models: An Evaluation System and Optimizing Decision Making with Multi-Agent (2025.findings-acl)

Challenge:	Despite LLMs' impressive capabilities in musical knowledge, music reasoning remains an unsolved task.
Approach:	They propose an open-source large language model (LLM) that integrates intrinsic musical abilities into LLaMA2 and GPT-3.5.
Outcome:	The proposed model can understand and generate music with a pure text tokenizer without external multi-modal neural structures or tokenizers.

Copied to clipboard

Xiaofeng Wang, Zhixin Zhang, Jin Guang Zheng, Yiming Ai, Rui Wang

Towards Unifying the Label Space for Aspect- and Sentence-based Sentiment Analysis (2022.findings-acl)

Challenge:	Debt collection negotiations (DCN) are vital for managing non-performing loans (NPLs) prior systems lacking dynamic negotiation and real-time decision-making capabilities.
Approach:	They propose a framework for debt negotiation that incorporates planning and judging modules to improve decision rationality.
Outcome:	The proposed framework improves decision rationality and integrates planning and judging modules to improve decision rationalness.

Copied to clipboard

Yiming Zhang, Min Zhang, Sai Wu, Junbo Zhao

Sentiment Analysis

Challenge:	Existing methods to train ABSA model are limited by lack of annotated data . a dual-granularity pseudo labeling approach is proposed to solve this problem .
Approach:	They propose a framework for aspect-based sentiment analysis that uses annotated data to train ABSA models.
Outcome:	The proposed framework surpasses previous methods on benchmarks.

Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM (2024.eacl-long)

Copied to clipboard

Ruohong Zhang, Yau-Shian Wang, Yiming Yang

Context-Sensitive Generation of Open-Domain Conversational Responses (C18-1)

Challenge:	a novel method to train a smaller model with LLMs for zero-shot text classification requires immense computational resources due to their substantial model size.
Approach:	They propose a method which leverages the generative power of large language models to train a smaller model.
Outcome:	The proposed method outperforms state-of-the-art methods when limited data is available.

Copied to clipboard

Weinan Zhang, Yiming Cui, Yifa Wang, Qingfu Zhu, Lingzhi Li, Lianqiang Zhou, Ting Liu

Understanding the Dark Side of LLMs’ Intrinsic Self-Correction (2025.acl-long)

Challenge:	Existing studies on single-turn conversation generation focus on coherence and context-sensitive generation of open-domain conversational responses.
Approach:	They propose static and dynamic attention based approaches for context-sensitive generation of open-domain conversational responses.
Outcome:	The proposed model outperforms all baselines on automatic and human evaluation on two public datasets.

Copied to clipboard

Qingjie Zhang, Di Wang, Haoting Qian, Yiming Li, Tianwei Zhang, Minlie Huang, Ke Xu, Hewu Li, Liu Yan, Han Qiu

Challenge:	Recent studies show that LLMs’ intrinsic self-correction fails without oracle labels as feedback.
Approach:	They propose to use one simple task and three complex tasks with state-of-the-art LLMs like ChatGPT, Llama, and DeepSeek to interpret LLM's intrinsic self-correction.
Outcome:	The proposed methods reveal the dark side of LLMs’ intrinsic self-correction for different tasks, especially for those failure cases.

EventWeave: A Dynamic Framework for Capturing Core and Supporting Events in Dialogue Systems (2026.acl-long)

Copied to clipboard

Zhengyi Zhao, Shubo Zhang, Yiming Du, Bin Liang, Baojun Wang, Zhongyang Li, Binyang Li, Kam-Fai Wong

Can MLLMs Understand the Deep Implication Behind Chinese Images? (2025.acl-long)

Challenge:	Existing dialogue systems process conversational turns in isolation, overlooking event structures that guide natural interactions.
Approach:	They propose a framework that explicitly models relationships between conversational events to generate more contextually appropriate dialogue responses.
Outcome:	Experiments on three dialogue datasets show that the proposed approach produces more natural responses while requiring less computational overhead.

Copied to clipboard

Chenhao Zhang, Xi Feng, Yuelin Bai, Xeron Du, Jinchang Hou, Kaixin Deng, Guangzeng Han, Qinrui Li, Bingli Wang, Jiaheng Liu, Xingwei Qu, Yifei Zhang, Qixuan Zhao, Yiming Liang, Ziqiang Liu, Feiteng Fang, Min Yang, Wenhao Huang, Chenghua Lin, Ge Zhang, Shiwen Ni

Revisiting the Knowledge Injection Frameworks (2023.emnlp-main)

Challenge:	MLLMs perform poorly on traditional culture images, indicating limitations in understanding high-level semantics and lacking a deep knowledge base of Chinese traditional culture.
Approach:	They propose to use Chinese images to assess MLLMs' higher-order perception and understanding of Chinese visual content.
Outcome:	The proposed model incorporates images that represent Chinese traditional culture, such as famous Chinese traditional paintings, to ensure the authenticity of the Chinese context.

Copied to clipboard

Peng Fu, Yiming Zhang, Haobo Wang, Weikang Qiu, Junbo Zhao

Beyond Single-Audio: Advancing Multi-Audio Processing in Audio Large Language Models (2024.findings-emnlp)

Challenge:	Injecting unaligned knowledge tuple into large language models achieves comparable (and sometimes better) results than aligned knowledge.
Approach:	They propose a technique to inject random knowledge into large language models to improve performance.
Outcome:	The proposed technique overcomes the sanity problem and pushes the performance limit.

Copied to clipboard

Yiming Chen, Xianghu Yue, Xiaoxue Gao, Chen Zhang, Luis Fernando D’Haro, Robby Tan, Haizhou Li

CIE: Controlling Language Model Text Generations Using Continuous Signals (2025.emnlp-main)

Challenge:	Existing evaluations of audio large language models focus on single audio inputs, but real-world applications often require processing multiple audio streams simultaneously.
Approach:	They propose a multi-audio evaluation benchmark that combines 20 audio inputs from 11 audio tasks to capture audio context.
Outcome:	The proposed model outperforms baseline models and achieves high data efficiency without human annotations.

Copied to clipboard

Vinay Samuel, Harshita Diddee, Yiming Zhang, Daphne Ippolito

EfficientLLM: Unified Pruning-Aware Pretraining for Auto-Designed Compact Language Models (2026.acl-long)

Challenge:	Existing methods to control language models with intent are brittle and hard to scale.
Approach:	They propose to use a set of LMs to fine-tune to expect a control vector that is interpolated between a "low" and a 'high' token embedding.
Outcome:	The proposed method can be finetuned to expect a control vector that is interpolated between a “low” and a ‘high” token embedding.

Copied to clipboard

Xingrun Xing, Zheng Liu, Shitao Xiao, Boyan Gao, Yiming Liang, Haokun Lin, Xianlin Zeng, Guoqi Li, Jiajun Zhang

Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward (2025.naacl-long)

Challenge:	Large language models (LLMs) driven by scaling laws can be developed in large model sizes.
Approach:	They propose a pruning-aware pretraining approach that decouples LLM pruning from direct pretraining.
Outcome:	The proposed model outperforms pretraining models with 100M 1B parameters in commen sense benchmarks.

Copied to clipboard

Ruohong Zhang, Liangke Gui, Zhiqing Sun, Yihao Feng, Keyang Xu, Yuanhan Zhang, Di Fu, Chunyuan Li, Alexander G Hauptmann, Yonatan Bisk, Yiming Yang

FRAME: Feedback-Refined Agent Methodology for Enhancing Medical Research Insights (2025.findings-acl)

Challenge:	Existing studies have demonstrated that direct preference optimization (DPO) can be effective in generalizing large language models, but its effectiveness in video domain remains limited.
Approach:	They propose a framework that utilizes detailed video captions as a proxy of video content to enable language models to incorporate this information as supporting evidence for scoring video Question Answering (QA) predictions.
Outcome:	The proposed framework shows that it can be used to align language models with video content and improves performance on open-ended video QA tasks.

Copied to clipboard

Chengzhang Yu, Yiming Zhang, Zhixin Liu, Zenghui Ding, Yining Sun, Zhanpeng Jin

Exposing Numeracy Gaps: A Benchmark to Evaluate Fundamental Numerical Abilities in Large Language Models (2025.findings-acl)

Challenge:	Existing approaches to automate scientific research are limited by human cognitive constraints and timeintensive workflows.
Approach:	They propose a framework that enhances medical paper generation through iterative refinement and structured feedback.
Outcome:	The proposed framework achieves significant improvements over conventional methods across multiple models and evaluation dimensions.

Copied to clipboard

Haoyang Li, Xuejia Chen, Zhanchao Xu, Darian Li, Nicole Hu, Fei Teng, Yiming Li, Luyu Qiu, Chen Jason Zhang, Li Qing, Lei Chen

Can LLMs Act as Historians? Evaluating Historical Research Capabilities of LLMs via the Chinese Imperial Examination (2026.acl-long)

Challenge:	Existing benchmarks focus on linguistic competence or structured mathematical problem-solving, neglecting fundamental numerical reasoning required in real-world scenarios.
Approach:	They propose a benchmark to evaluate numerical capabilities for large language models . they use a dataset to assess number recognition, arithmetic operations, contextual retrieval, comparison, summary, and multi-step reasoning.
Outcome:	The proposed benchmark evaluates six fundamental numerical capabilities: number recognition, arithmetic operations, contextual retrieval, comparison, summary, and multi-step reasoning.

Copied to clipboard

Lirong Gao, Zeqing Wang, Yuyan Cai, Jiayi Deng, Yanmei Gu, Yiming Zhang, Jia Zhou, Yanfei Zhang, Junbo Zhao

COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values (2026.findings-eacl)

Challenge:	Existing benchmarks assess basic knowledge breadth or lexical understanding, failing to capture higher-order skills that are central to historical research.
Approach:	They propose a benchmark anchored in the Chinese Imperial Examination system that assesses historical knowledge and lexical understanding.
Outcome:	The new benchmark aims to assess the ability of LLMs to process historical materials and documents.

Copied to clipboard

Siwei Wu, JinCheng Ren, Xeron Du, Shuyue Guo, Xingwei Qu, Yiming Liang, Jie Liu, Yunwen Li, Tyler Loakman, Tianyu Zheng, Boyu Feng, Huaqing Yuan, Zili Wang, Jiaheng Liu, Wenhao Huang, Chenglin Cai, Haoran Que, Jian Yang, Yuelin Bai, Zekun Moore Wang, Zhouliang Yu, Qunshu Lin, Ding Pan, Yuchen Eleanor Jiang, Tiannan Wang, Wangchunshu Zhou, Shenzhi Wang, Xingyuan Bu, Minghao Liu, Guoyin Wang, Ge Zhang, Chenghua Lin

Active Example Selection for In-Context Learning (2022.emnlp-main)

Challenge:	Existing Chinese preference datasets suffer from limited scale, restricted domain coverage, and insufficiently rigorous data validation.
Approach:	They propose an LLM-based data annotation pipeline with no human intervention to annotate Chinese preference datasets.
Outcome:	The proposed pipeline outperforms existing Chinese preference datasets on AlignBench and Chinese Reward Benchmark.

Copied to clipboard

Yiming Zhang, Shi Feng, Chenhao Tan

Kill two birds with one stone: generalized and robust AI-generated text detection via dynamic perturbations (2025.naacl-long)

Challenge:	In-context learning performance is unstable across samples of examples, suggesting the idiosyncrasies of how language models acquire information.
Approach:	They propose a reinforcement learning algorithm for identifying generalizable policies to select demonstration examples and propose 'in-context learning' performance can be highly unstable across samples of examples, suggesting the idiosyncrasies of how language models acquire information.
Outcome:	The proposed model can perform tasks with examples with a 5.8% improvement on GPT-2 and GPT-3, but the improvement diminishes on larger models, suggesting emerging capabilities of large language models.

Copied to clipboard

Yinghan Zhou, Juan Wen, Wanli Peng, Xue Yiming, ZiWei Zhang, Wu Zhengxian

Do BERT-Like Bidirectional Models Still Perform Better on Text Classification in the Era of LLMs? (2025.findings-emnlp)

Challenge:	Existing methods focus on model generalization or focus on robustness.
Approach:	They propose a model-based AIGT detection method that can be generalized and robust under two adversarial attacks.
Outcome:	The proposed method outperforms state-of-the-art methods for generalization and robustness under two text adversarial attacks.

Copied to clipboard

Junyan Zhang, Yiming Huang, Shuliang Liu, Yubo Gao, Xuming Hu

Information Extraction & Text Mining

Challenge:	Rapid adoption of LLMs has overshadowed the potential advantages of traditional BERT-like models in text classification.
Approach:	They compare BERT-like models fine-tuning, LLM internal state utilization, and LLM zero-shot inference across six datasets.
Outcome:	The proposed method outperforms LLMs on six challenging datasets.

Long-tailed Extreme Multi-label Text Classification by the Retrieval of Generated Pseudo Label Descriptions (2023.findings-eacl)

Copied to clipboard

Ruohong Zhang, Yau-Shian Wang, Yiming Yang, Donghan Yu, Tom Vu, Likun Lei

Information Retrieval

Challenge:	Extreme Multi-label text classification (XMTC) is a tough challenge due to the sheer size of the label spaces and the severe data scarcity problem associated with the long tail of rare labels in highly skewed distributions.
Approach:	They propose to use a trained bag-of-words classifier to generate pseudo label descriptions from a training bag- of-word classifier.
Outcome:	The proposed approach outperforms the existing models in the tail label prediction problem and achieves state-of-the-art (SOTA) performance on XMTC benchmark datasets.

D-NET: A Pre-Training and Fine-Tuning Framework for Improving the Generalization of Machine Reading Comprehension (D19-58)

Copied to clipboard

Hongyu Li, Xiyuan Zhang, Yibing Liu, Yiming Zhang, Quan Wang, Xiangyang Zhou, Jing Liu, Hua Wu, Haifeng Wang

Translationese-index: Using Likelihood Ratios for Graded and Generalizable Measurement of Translationese (2025.emnlp-main)

Challenge:	MRC requires machines to understand text and answer questions about the text.
Approach:	They propose a simple system Baidu submitted for MRQA 2019 Shared Task that focused on generalization of machine reading comprehension (MRC) models.
Outcome:	The proposed system is ranked at top 1 of all participants in terms of averaged F1 score.

Copied to clipboard

Yikang Liu, Wanyang Zhang, Yiming Wang, Jialong Tang, Pei Zhang, Baosong Yang, Fei Huang, Rui Wang, Hai Hu

Machine Translation

Challenge:	Translationese is a linguistic property that is often introduced in the translation process that is different from those of original texts.
Approach:	They propose to use synthesized translations and translations in the wild to evaluate T-index's generalizability in cross-domain settings and its validity against human judgments.
Outcome:	The proposed measure can generalize to unseen genres, authors, and language pairs.

MIND: Towards Immersive Psychological Healing with Multi-Agent Inner Dialogue (2025.findings-emnlp)

Copied to clipboard

Yujia Chen, Changsong Li, Yiming Wang, Tianjie Ju, Qingqing Xiao, Nan Zhang, Zifan Kong, Peng Wang, Binyu Yan

R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (2024.findings-emnlp)

Challenge:	Mental health issues are worsening in today’s competitive society, such as depression and anxiety.
Approach:	They propose a multi-agent inner dialogue paradigm that provides more immersive psychological healing environments.
Outcome:	The proposed paradigm provides more immersive psychological healing environments.

Copied to clipboard

Tongxin Yuan, Zhiwei He, Lingzhong Dong, Yiming Wang, Ruijie Zhao, Tian Xia, Lizhen Xu, Binglin Zhou, Fangqi Li, Zhuosheng Zhang, Rui Wang, Gongshen Liu

Challenge:	Large language models (LLMs) have shown compelling abilities in reasoning, decision-making, and instruction following.
Approach:	They propose a benchmark to evaluate the proficiency of large language models (LLMs) in judging and identifying safety risks given agent interaction records.
Outcome:	The proposed model outperforms the best-performing model, GPT-4o, while no other models significantly exceed the random.

Uncertainty-Calibrated Elastic Alignment for Multimodal Sentiment Analysis with Missing Modalities (2026.findings-acl)

Copied to clipboard

Kang He, Yuzhe Ding, Rao Fu, Yukang Feng, Kaipeng Zhang, Yiming Liu, Fei Li, Chong Teng, Donghong Ji

Learning to Ignore Adversarial Attacks (2023.eacl-main)

Challenge:	Existing methods for multimodal sentiment analysis are often dynamically incomplete.
Approach:	They propose a new uncertainty-calibrated elastic alignment framework to address these issues by employing probabilistic imputation to capture cross-modal ambiguity and leverage the estimated uncertainty to drive elastic alignment.
Outcome:	The proposed framework outperforms state-of-the-art models in multiple benchmarks and consistently outperformed existing models.

Copied to clipboard

Yiming Zhang, Yangqiaoyu Zhou, Samuel Carton, Chenhao Tan

Fast Adaptation via Prompted Data: An Efficient Cross-Domain Fine-tuning Method for Large Language Models (2024.lrec-main)

Challenge:	Despite the strong performance of current NLP models, they can be brittle against adversarial inputs.
Approach:	They propose a rationale model that explicitly learns to ignore adversarial tokens . their approach leads to sizable improvements in robustness over baseline models .
Outcome:	The proposed model outperforms data augmentation with adversarial examples and closes the gap between model performance and an attacked test set.

Copied to clipboard

Yiming Zhang, Hantao Yang, Haobo Wang, Jake Zhao

Analyzing and Evaluating Faithfulness in Dialogue Summarization (2022.emnlp-main)

Challenge:	Large language models (LLMs) have been successful in a variety of natural language understanding tasks, but domain discrepancies between the downstream task and the pre-training corpora may have hindered LLMs to excel further in the vertical applications.
Approach:	They propose a Fast Adaptation method for LLMs via Prompted Data that integrates downstream text corpora, gold labels and external knowledge sources into a highly controllable prompt.
Outcome:	The proposed method bridges the gap between the downstream task and the pre-training corpora and integrates downstream text corpors, gold labels and external knowledge sources into a highly controllable prompt.

Copied to clipboard

Bin Wang, Chen Zhang, Yan Zhang, Yiming Chen, Haizhou Li

SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval (2024.findings-acl)

Challenge:	Existing studies on faithfulness of text summarization have not been conducted on abstractive summarizing.
Approach:	They propose a method to evaluate faithfulness of dialogue summarization models by multi-choice questions.
Outcome:	The proposed method can facilitate the development of dialogue summarization systems.

Copied to clipboard

Siwei Wu, Yizhi Li, Kang Zhu, Ge Zhang, Yiming Liang, Kaijing Ma, Chenghao Xiao, Haoran Zhang, Bohao Yang, Wenhu Chen, Wenhao Huang, Noura Al Moubayed, Jie Fu, Chenghua Lin

A Hierarchical Explanation Generation Method Based on Feature Interaction Detection (2023.findings-acl)

Challenge:	Multi-modal information retrieval (MMIR) is a rapidly evolving field . current benchmarks for image-text pairings overlook the scientific domain .
Approach:	They develop a scientific domain-specific MMIR benchmark to evaluate image-text pairings using open-access research paper corpora.
Outcome:	The proposed benchmarks are based on 530K image-text pairs extracted from scientific documents with detailed captions.

Copied to clipboard

Yiming Ju, Yuanzhe Zhang, Kang Liu, Jun Zhao

Explainability & Interpretability in NLP

Challenge:	Existing work on hierarchical attributions tends to limit text groups to a continuous text span, which is difficult for humans to read.
Approach:	They propose a method which captures feature interactions and converts non-hierarchical explanations into hierarchical versions.
Outcome:	The proposed method can convert ubiquitous non-hierarchical explanations into their corresponding hierarchical versions.

SynthAgent: Adapting Web Agents with Synthetic Supervision (2026.acl-long)

Copied to clipboard

Zhaoyang Wang, Yiming Liang, Xuchao Zhang, Qianhui Wu, Siwei Han, Anson Bastos, Rujia Wang, Chetan Bansal, Baolin Peng, Jianfeng Gao, Saravan Rajmohan, Huaxiu Yao

Evo-Attacker: Memory-Augmented Reinforcement Learning for Long-Horizon Tool Attacks on LLM-MAS (2026.acl-long)

Challenge:	Existing studies have focused on synthetic supervision but have encountered data quality issues.
Approach:	They propose a fully synthetic supervision framework that aims at improving data quality via dual refinement of both tasks and trajectories.
Outcome:	The proposed framework outperforms existing methods on standardized benchmarks and shows promising results on a standardized test.

Copied to clipboard

Bingyu Yan, Xiaoming Zhang, JinYu Hou, Chaozhuo Li, Ziyi Zhou, Yiming Hei, Litian Zhang

MMRA: A Benchmark for Evaluating Multi-Granularity and Multi-Image Relational Association Capabilities in Large Visual Language Models (2026.findings-eacl)

Challenge:	Existing tool attacks are limited by domain specificity or fixed and static templates.
Approach:	They propose an attack-based memory-augmented reinforcement learning process that constructs a dynamic attack memory and employs deliberative reasoning to retrieve adversarial patterns.
Outcome:	Evo-Attacker outperforms baselines in the long-horizon credit assignment challenge.

Copied to clipboard

Siwei Wu, King Zhu, Yu Bai, Yiming Liang, Yizhi Li, Haoning Wu, Jiaheng Liu, Ruibo Liu, Xingwei Qu, Xuxin Cheng, Ge Zhang, Wenhao Huang, Chenghua Lin

GaLa: Hypergraph-Guided Visual Language Models for Procedural Planning (2026.findings-acl)

Challenge:	Current multimodal benchmarks focus on facts within individual images, but neglect associative relations among multiple images.
Approach:	They propose a multi-image relational association task and a MMRA benchmark to evaluate LVLMs.
Outcome:	The proposed benchmarks show that entity-level multi-image perception tasks pose greater challenges than image-level tasks.

Copied to clipboard

Kun Wang, Li Yiming, Mingcheng Qu, Aqiang Zhang, Guang Yang, Tonghua Su

Enhancing Multiple-choice Machine Reading Comprehension by Punishing Illogical Interpretations (2021.emnlp-main)

Challenge:	Existing methods for procedural planning over-rely on visual inputs and lack structured semantic information.
Approach:	They propose a vision–language framework for multimodal procedural planning that exploits implicit spatial relations and deep semantics encoded in object attributes.
Outcome:	The proposed framework outperforms existing methods in terms of execution success rate, LCS, and planning correctness.

Copied to clipboard

Yiming Ju, Yuanzhe Zhang, Zhixing Tian, Kang Liu, Xiaohuan Cao, Wenting Zhao, Jinlong Li, Jun Zhao

BiasX: “Thinking Slow” in Toxic Content Moderation with Explanations of Implied Social Biases (2023.emnlp-main)

Challenge:	Multiple-choice MRC is one of the most studied tasks in MRC due to the convenience of evaluation and the flexibility of answer format.
Approach:	They propose to use multiple-choice MRC to explain a trained model and reveal how it arrives at the prediction by punishing illogical attributions.
Outcome:	The proposed method improves model performance without external information and model structure change without any external information.

Copied to clipboard

Yiming Zhang, Sravani Nanduri, Liwei Jiang, Tongshuang Wu, Maarten Sap

DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models (2024.emnlp-main)

Challenge:	Toxicity annotators and content moderators often default to mental shortcuts when making decisions, leading to subtle toxicity being missed and seemingly harmless content being over-detected.
Approach:	They propose a framework that provides AI-generated explanations of statements’ implied social biases to enhance content moderation setups.
Outcome:	The proposed framework significantly improves content moderation setups by enabling users to think more thoroughly about their decisions.

Copied to clipboard

Yiming Huang, Jianwen Luo, Yan Yu, Yitong Zhang, Fangyu Lei, Yifan Wei, Shizhu He, Lifu Huang, Xiao Liu, Jun Zhao, Kang Liu

Programming Languages in NLP

Challenge:	DA-Code is a code generation benchmark designed to assess LLMs on agent-based data science tasks.
Approach:	They propose a code generation benchmark specifically designed for LLMs on agent-based data science tasks.
Outcome:	The benchmark performs better than existing frameworks, but lacks accuracy . it is based on real-world data, and includes examples that cover a wide range of tasks .

MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answering (2025.findings-emnlp)

Copied to clipboard

Siyue Zhang, Yuxiang Xue, Yiming Zhang, Xiaobao Wu, Anh Tuan Luu, Chen Zhao

EFSA: Towards Event-Level Financial Sentiment Analysis (2024.acl-long)

Challenge:	Existing methods for answering time-sensitive questions lack temporal reasoning . existing methods struggle with these time-intensive questions, authors say .
Approach:	They propose a temporal-based question-answering framework that integrates temporal perturbations and gold evidence labels into a question processing framework.
Outcome:	The proposed framework outperforms baseline retrieval methods in retrieval performance.

Copied to clipboard

Tianyu Chen, Yiming Zhang, Guoxin Yu, Dapeng Zhang, Li Zeng, Qing He, Xiang Ao

Sentiment Analysis

Challenge:	a large-scale Chinese dataset contains 12,160 news articles and 13,725 quintuples . a four-hop Chain-of-Thought LLM-based approach is devised for this task .
Approach:	They propose to extend financial sentiment analysis to event-level since events usually serve as the subject of the sentiment in financial text.
Outcome:	The proposed method can reach the current state-of-the-art on a large-scale Chinese dataset.

COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning (2025.findings-naacl)

Copied to clipboard

Yuelin Bai, Xeron Du, Yiming Liang, Leo Jin, Junting Zhou, Ziqiang Liu, Feiteng Fang, Mingshan Chang, Tianyu Zheng, Xincheng Zhang, Nuo Ma, Zekun Moore Wang, Ruibin Yuan, Haihong Wu, Hongquan Lin, Wenhao Huang, Jiajun Zhang, Chenghua Lin, Jie Fu, Min Yang, Shiwen Ni, Ge Zhang

Revisiting Self-training for Few-shot Learning of Language Model (2021.emnlp-main)

Challenge:	Existing datasets for Chinese instruction tuning are not well-aligned with Chinese users’ interaction patterns.
Approach:	They propose to use Chinese instruction tuning datasets to improve instruction fine-tuning for Chinese users.
Outcome:	The proposed dataset shows that Chinese models achieve competitive performance in diverse benchmarks.

Copied to clipboard

Yiming Chen, Yan Zhang, Chen Zhang, Grandee Lee, Ran Cheng, Haizhou Li

The Paradox of Outcome Optimization: A Causal Information-Theoretic Bound on Reasoning Shortcuts in LLMs (2026.acl-long)

Challenge:	Unlabeled data are useful for few-shot learning of language models.
Approach:	They propose a prompt-based few-shot learner that uses unlabeled data to fine-tune language models.
Outcome:	The proposed approach outperforms state-of-the-art models on six sentence classification and six sentence-pair classification benchmarking tasks.

Copied to clipboard

Zihan Chen, Yiming Zhang, Wenxiang Geng, Zenghui Ding, Yining Sun

BadActs: A Universal Backdoor Defense in the Activation Space (2024.findings-acl)

Challenge:	Large Language Models (LLMs) aligned via outcome-based Reinforcement Learning (RL) exhibit a critical failure mode: they exhibit brittle reasoning capabilities on out-of-distribution tasks.
Approach:	They propose a framework bridging Structural Causal Models and the Information Bottleneck principle to explain this paradox.
Outcome:	The proposed framework bridges the framework between SCM and IB principles to explain the problem.

Copied to clipboard

Biao Yi, Sishuo Chen, Yiming Li, Tong Li, Baolei Zhang, Zheli Liu

Data or Language Supervision: What Makes CLIP Better than DINO? (2025.findings-emnlp)

Challenge:	Backdoor attacks pose an increasingly severe security threat to Deep Neural Networks . existing methods focused on the word space are ineffective against feature-space triggers - a recent study has shown .
Approach:	They propose a backdoor defense that purifies backdoor samples in the activation space . they aim to eliminate backdoor triggers while preserving the integrity of clean data .
Outcome:	The proposed method achieves state-of-the-art against backdoor attacks on clean data.

Copied to clipboard

Yiming Liu, Yuhui Zhang, Dhruba Ghosh, Ludwig Schmidt, Serena Yeung-Levy

Element-aware Summarization with Large Language Models: Expert-aligned Evaluation and Chain-of-Thought Method (2023.acl-long)

Challenge:	CLIP outperforms self-supervised models like DINO as vision encoders for vision-language models (VLMs) but it remains unclear whether this advantage stems from CLIP’s language supervision or its much larger training data.
Approach:	Embedding analysis shows CLIP captures high-level semantics while DINO is more responsive to low-level features like colors and styles.
Outcome:	Embedding analysis shows that CLIP captures high-level semantics, while DINO is more responsive to low-level features like colors and styles.

Copied to clipboard

Yiming Wang, Zhuosheng Zhang, Rui Wang

VoiceBench: Benchmarking LLM-Based Voice Assistants (2026.tacl-1)

Challenge:	Experimental results show that automatic summarization generates concise summaries that contain key ideas of source documents.
Approach:	They propose to use Element-aware test sets to annotate news-related reference summaries to focus on more fine-grained news elements objectively and comprehensively.
Outcome:	The proposed method outperforms state-of-the-art fine-tuned PLMs and zero-shot LLMs by +4.33/+4.77 on the two datasets, respectively.

Copied to clipboard

Yiming Chen, Xianghu Yue, Chen Zhang, Xiaoxue Gao, Robby T. Tan, Haizhou Li

Speech & Audio in NLP

Challenge:	Recent advances in large language models (LLMs) have enabled real-time speech interactions through LLMs.
Approach:	They propose a benchmark specifically designed to assess LLM-based voice assistants.
Outcome:	The proposed benchmark measures the performance of LLM-based voice assistants across eight tasks.

Tree-of-Quote Prompting Improves Factuality and Attribution in Multi-Hop and Medical Reasoning (2025.emnlp-main)

Copied to clipboard

Justin Xu, Yiming Li, Zizheng Zhang, Augustine Yui Hei Luk, Mayank Jobanputra, Samarth Oza, Ashley Murray, Meghana Reddy Kasula, Andrew Parker, David W Eyre

Low-Resource NLP

Challenge:	Large language models (LLMs) produce fluent but factually incorrect outputs, a phenomenon commonly referred to as hallucination.
Approach:	They propose a Tree-of-Quote framework that decomposes complex questions into subquestions and generates quotes to support each step without retrieval.
Outcome:	Experiments on StrategyQA, 2WikiMultiHopQA, MuSiQue, MoreHopQ, and MedQA show that ToQ improves factuality and attribution over baselines.

Logic Traps in Evaluating Attribution Scores (2022.acl-long)

Copied to clipboard

Yiming Ju, Yuanzhe Zhang, Zhao Yang, Zhongtao Jiang, Kang Liu, Jun Zhao

Embedding and Gradient Say Wrong: A White-Box Method for Hallucination Detection (2024.emnlp-main)

Challenge:	Modern deep learning models are notoriously opaque, which has motivated the development of methods for interpreting how deep models predict.
Approach:	They propose to review existing methods for evaluating attribution scores and summarize the logic traps in these methods.
Outcome:	The proposed methods show that they do not contain logic traps and that they are not reliable.

Copied to clipboard

Xiaomeng Hu, Yiming Zhang, Ru Peng, Haozhe Zhang, Chenwei Wu, Gang Chen, Junbo Zhao

LinguaGame: A Linguistically Grounded Game-Theoretic Paradigm for Multi-Agent Dialogue Generation (2026.findings-acl)

Challenge:	Existing methods for hallucination detection have attracted more attention from the community.
Approach:	They propose to model the distributional distance between the regular conditional output and the unconditional output, which is generated without a given input text.
Outcome:	The proposed model achieves state-of-the-art on the hallucination benchmarks HADES and other datasets.

Copied to clipboard

Yuxiao Ye, Yiming Zhang, Yiran Rex Ma, Huiyuan Xie, Huining Zhu, Zhiyuan Liu

Mitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging (2024.emnlp-main)

Challenge:	Large Language Models (LLMs) have enabled Multi-Agent Systems (MASs) where agents interact through natural language to solve complex tasks or simulate multi-party dialogues.
Approach:	They propose a linguistically-grounded game-theoretic paradigm for multi-agent dialogue generation that uses a training-free equilibrium approximation algorithm to model dialogue over communicative intents and strategies.
Outcome:	The proposed framework improves agents’ communication efficiency by helping them convey their intended meaning more effectively through language.

Copied to clipboard

Yiming Ju, Ziyi Ni, Xingrun Xing, Zhixiong Zeng, Hanyu Zhao, Siqi Fan, Zheng Zhang