Papers by He Cao

ConfSpec: Efficient Step-Level Speculative Reasoning via Confidence-Gated Verification (2026.acl-long)

Challenge:	Large language models have created significant safety concerns . factuality ability is crucial in determining whether they can be deployed and applied safely and compliantly within specific regions.
Approach:	They propose a benchmark to evaluate the factuality of large language models in China . they evaluate the models' ability to provide accurate and reliable information .
Outcome:	The proposed benchmark evaluates the factuality abilities of existing LLMs and compares them to LLM abilities.

Copied to clipboard

Siran Liu, Zane Cao, Yongchao He

All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG (2026.acl-long)

Challenge:	Existing approaches to chain-of-thought reasoning incur high inference latency due to long generation traces.
Approach:	They propose a confidence-gated cascaded verification framework that reduces the trade-off between generation and verification.
Outcome:	The proposed framework achieves 2.24 speedups while matching target-model accuracy.

Copied to clipboard

Dan Wang, Guozhao Mo, Yafei Shi, Cheng Zhang, Bo Zheng, Boxi Cao, Xuanang Chen, Yaojie Lu, Hongyu Lin, Ben He, Xianpei Han, Le Sun

Multilinguality

Challenge:	Existing mRAG systems suffer from a language bias during reranking, systematically favoring English and the query’s native language.
Approach:	They propose a language-agnostic utility-driven reranker alignment technique to mitigate language bias during re-ranking.
Outcome:	The proposed approach mitigates language bias and consistently improves mRAG performance across languages.

Data Selection Curriculum for Abstractive Text Summarization (2023.findings-emnlp)

Copied to clipboard

Shichao Sun, Ruifeng Yuan, Jianfei He, Ziqiang Cao, Wenjie Li, Xiaohua Jia

Summarization

Challenge:	Abstractive Text Summarization (ATS) models are commonly trained using large-scale data that is randomly shuffled.
Approach:	They propose a data selection curriculum scoring system that measures the learning difficulty of an ATS model and expected performance on an instance.
Outcome:	The proposed system surpasses baselines on CNN/DailyMail dataset, utilizing 20% of available instances.

RWKV: Reinventing RNNs for the Transformer Era (2023.findings-emnlp)

Copied to clipboard

Bo Peng, Eric Alcaide, Quentin Anthony, Alon Albalak, Samuel Arcadinho, Stella Biderman, Huanqi Cao, Xin Cheng, Michael Chung, Leon Derczynski, Xingjian Du, Matteo Grella, Kranthi Gv, Xuzheng He, Haowen Hou, Przemyslaw Kazienko, Jan Kocon, Jiaming Kong, Bartłomiej Koptyra, Hayden Lau, Jiaju Lin, Krishna Sri Ipsit Mantri, Ferdinand Mom, Atsushi Saito, Guangyu Song, Xiangru Tang, Johan Wind, Stanisław Woźniak, Zhenyuan Zhang, Qinghua Zhou, Jian Zhu, Rui-Jie Zhu

Beyond Token Length: Step Pruner for Efficient and Accurate Reasoning in Large Language Models (2026.findings-acl)

Challenge:	recurrent neural networks struggle to match the performance of Transformers due to limitations in parallelization and scalability.
Approach:	They propose a model architecture that combines the efficient parallelizable training of transformers with the efficient inference of RNNs.
Outcome:	The proposed model performs on par with similarly sized RNNs, suggesting future work can leverage this architecture to create more efficient models.

Copied to clipboard

Canhui Wu, Qiong Cao, Chang Li, Zhenfang Wang, Chao Xue, Yuwei Fan, Wei Xi, Xiaodong He

LEGO: A Multi-agent Collaborative Framework with Role-playing and Iterative Feedback for Causality Explanation Generation (2023.findings-emnlp)

Challenge:	Existing reinforcement learning methods for large reasoning models suffer from excessive verbosity, known as "overthinking." Existing models penalize generated tokens to promote conciseness, but these methods encounter two challenges: they may develop hacking behavior in later stages of training by discarding reasoning steps.
Approach:	They propose a framework that steers large reasoning models toward more efficient reasoning . they prioritize correctness while imposing penalties for redundant steps .
Outcome:	The proposed framework reduces token usage by 69.7% on AIME24.

Copied to clipboard

Zhitao He, Pengfei Cao, Yubo Chen, Kang Liu, Ruopeng Li, Mengshu Sun, Jun Zhao

Explainability & Interpretability in NLP

Challenge:	Causality explanation generation is a generative task that aims to explain why a given cause-effect pair is true using natural language.
Approach:	They propose a multi-agent framework with role-playing and iterative feedback for causality explanation generation.
Outcome:	The proposed framework is superior to existing frameworks on WIKIWHY and e-CARE datasets.

FlowRAG: Synergizing Explicit Reasoning via Frequency-Aware Multi-Granularity Graph Flow (2026.findings-acl)

Copied to clipboard

Bihao Zhan, Zongsheng Cao, Jie Zhou, Bo Zhang, Liang He

Information Retrieval

Challenge:	Existing methods for Graph-based retrieval-augmented generation rely on implicit semantic relevance propagation.
Approach:	They propose a semantic-aware retrieval framework that improves both semantic recall and explicit reasoning.
Outcome:	Extensive experiments show that FlowRAG improves both semantic recall and explicit reasoning.

AutoMedEval: Harnessing Language Models for Automatic Medical Capability Evaluation (2025.acl-long)

Copied to clipboard

Xiechi Zhang, Zetian Ouyang, Linlin Wang, Gerard De Melo, Zhu Cao, Xiaoling Wang, Ya Zhang, Yanfeng Wang, Liang He

Beyond Code: Evaluate Thought Steps for Complex Code Generation (2024.lrec-main)

Challenge:	Existing evaluation methods based on large language models (LLMs) are expensive and lack expertise due to limitations in human expertise.
Approach:	They propose an open-source automatic evaluation model with 13B parameters specifically engineered to measure the question-answering proficiency of medical LLMs.
Outcome:	The proposed model surpasses baselines in terms of correlation with human judgments.

Copied to clipboard

Liuwen Cao, Yi Cai, Jiexin Wang, Hongkui He, Hailin Huang

Programming Languages in NLP

Challenge:	Existing efforts to generate code in C++ rely on relatively simple programming problems . large language models (LLMs) pre-trained on numerous code data have opened up new opportunities for code generation.
Approach:	They propose a task that evaluates the quality of thought steps and code implementation . they construct a dataset of complex programming problems in C++ .
Outcome:	The proposed task evaluates the quality of thought steps and code implementation in a C++ programming language.

Enhancing Automated Essay Scoring Performance via Fine-tuning Pre-trained Language Models with Combination of Regression and Ranking (2020.findings-emnlp)

Copied to clipboard

Ruosong Yang, Jiannong Cao, Zhiyuan Wen, Youzheng Wu, Xiaodong He

Towards Efficient NLP: A Standard Evaluation and A Strong Baseline (2022.naacl-main)

Challenge:	Recent work on sentence prediction tasks uses shallow neural networks to learn essay representations and constrain calculated scores with regression loss or ranking loss.
Approach:	They propose to use a pre-trained language model to learn text representations first and then to constrain the scores with regression loss or ranking loss.
Outcome:	The proposed model outperforms state-of-the-art models on the Automated Student Assessment Prize dataset.

Copied to clipboard

Xiangyang Liu, Tianxiang Sun, Junliang He, Jiawen Wu, Lingling Wu, Xinyu Zhang, Hao Jiang, Zhao Cao, Xuanjing Huang, Xipeng Qiu

The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding (2020.acl-demos)

Challenge:	Rather than pursuing the reachless SOTA accuracy, researchers are focusing on model efficiency and usability.
Approach:	They propose an evaluation and a public leaderboard for efficient NLP models that depicts the Pareto Frontier for various language understanding tasks.
Outcome:	The proposed model outperforms or performs on par with SOTA compressed and early exiting models.

Copied to clipboard

Xiaodong Liu, Yu Wang, Jianshu Ji, Hao Cheng, Xueyun Zhu, Emmanuel Awa, Pengcheng He, Weizhu Chen, Hoifung Poon, Guihong Cao, Jianfeng Gao

Latent Suicide Risk Detection on Microblog via Suicide-Oriented Word Embeddings and Layered Attention (D19-1)

Challenge:	MT-DNN is an open-source natural language understanding toolkit . it allows researchers and developers to train customized deep learning models .
Approach:	They present MT-DNN, an open-source natural language understanding toolkit . it is designed to facilitate rapid customization for a broad spectrum of NLU tasks . MT supports multi-task knowledge distillation, which can substantially compress a deep neural model without significant performance drop.
Outcome:	The proposed model can significantly compress a large model without significant performance drop.

Copied to clipboard

Lei Cao, Huijun Zhang, Ling Feng, Zihan Wei, Xin Wang, Ningyun Li, Xiaohao He

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing (2026.acl-industry)

Challenge:	Existing approaches to detect suicidal ideation on social media are limited to a small group of people.
Approach:	They propose to use tree holes to embed words into microblogs to strengthen the sensibility of suicide-related lexicons and to use a two-layered attention mechanism to grasp intermittently changing points from individual's open blog streams.
Outcome:	The proposed approach can achieve over 91% accuracy with the use of suicide-oriented word embeddings and attention on a large-scale well-labelled suicide data set.

Copied to clipboard

Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Zirui Tang, Boyu Niu, Yuanhong Zheng, Dongsheng Ma, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Fangdong Wang, Jingzhou Chen, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, RuiLiang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Dechen Lin, null Shenguanlin, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He

Green & Sustainable NLP

Challenge:	Document images are characterized by higher resolutions, denser content, and more complex structural layouts.
Approach:	They propose a 1.2B-parameter document parsing vision-language model that decouples layout analysis from local content recognition.
Outcome:	The proposed model surpasses general-purpose and domain-specific models on multiple benchmarks while maintaining significantly lower computational overhead.

Sparse Activation Editing for Reliable Instruction Following in Narratives (2025.emnlp-main)

Copied to clipboard

Runcong Zhao, Chengyu Cao, Qinglin Zhu, Xiucheng Ly, Shun Shao, Lin Gui, Ruifeng Xu, Yulan He

Challenge:	Existing benchmarks fail to capture the challenges of instruction following in complex narrative contexts.
Approach:	They propose a training-free framework that identifies and edits instruction-relevant neurons using only natural language instructions without requiring labelled data.
Outcome:	The proposed framework improves instruction following by identifying and editing instruction-relevant neurons using only natural language instructions, without requiring labelled data.

ChatEdit: Towards Multi-turn Interactive Facial Image Editing via Dialogue (2023.emnlp-main)

Copied to clipboard

Xing Cui, Zekun Li, Pei Li, Yibo Hu, Hailin Shi, Chunshui Cao, Zhaofeng He

Visual Data in NLP

Challenge:	Existing approaches to interactive facial image editing treat multi-turn editing as a sequence of successive single-turn edits, leading to attribute forgetting and error accumulation.
Approach:	They propose a framework for interactive facial image editing through dialogues based on the CelebA-HQ dataset and a benchmark dataset to evaluate this.
Outcome:	The proposed framework outperforms existing methods and improves existing ones.

Memorizing is Not Enough: Deep Knowledge Injection Through Reasoning (2025.acl-long)

Copied to clipboard

Ruoxi Xu, Yunjie Ji, Boxi Cao, Yaojie Lu, Hongyu Lin, Xianpei Han, Ben He, Yingfei Sun, Xiangang Li, Le Sun

D-Artemis: A Deliberative Cognitive Framework for Mobile GUI Multi-Agents (2026.findings-acl)

Challenge:	Existing knowledge injection frameworks focus on knowledge memorization and retrieval, but static nature of large language models leads to outdated information as the real world evolves or when adapting to domain-specific knowledge.
Approach:	They propose a four-tier knowledge injection framework that defines the levels of knowledge injection: memorization, retrieval, reasoning, and association.
Outcome:	The proposed framework defines the levels of knowledge injection: memorization, retrieval, reasoning, and association.

Copied to clipboard

Hongze Mi, Yibo Feng, WenJie Lu, Yuqi Wang, Jinyuan Li, Song Cao, He Cui, Tengfei Tian, Xuelin Zhang, Haotian Luo, Di Sun, Jun Fang, Hua Chai, Naiqiang Tan, Gang Pan

Challenge:	Graphical User Interface (GUI) agents aim to automate a wide spectrum of human tasks by emulating user interaction.
Approach:	They propose a deliberative framework that leverages a fine-grained tip retrieval mechanism to inform its decision-making process.
Outcome:	The proposed framework achieves SOTA among open-source general models on AndroidWorld and ScreenSpot-V2 . it leverages a fine-grained, app-specific tip retrieval mechanism to inform its decision-making process .

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

Copied to clipboard

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

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

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

Copied to clipboard

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

Natural Language Interfaces

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

Planning Like Human: A Dual-process Framework for Dialogue Planning (2024.acl-long)

Copied to clipboard

Tao He, Lizi Liao, Yixin Cao, Yuanxing Liu, Ming Liu, Zerui Chen, Bing Qin

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

Challenge:	Large Language Models (LLMs) operate in a reactive mode, often resulting in efficiency issues or suboptimal performance.
Approach:	They propose a dual-process dialogue planning framework that leverages the dual-process theory of human cognition and a deliberative Monte Carlo Tree Search mechanism to emulate human-like conversational dynamics.
Outcome:	The proposed framework outperforms existing methods in achieving high-quality dialogues and operational efficiency.

Copied to clipboard

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

MoA: Heterogeneous Mixture of Adapters for Parameter-Efficient Fine-Tuning of Large Language Models (2026.acl-long)

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

Copied to clipboard

Jie Cao, Tianwei Lin, Bo Yuan, Rolan Yan, Hongyang He, Wenqiao Zhang, Juncheng Li, Dongping Zhang, Siliang Tang, Yueting Zhuang

INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent (2025.acl-long)

Challenge:	Existing methods for parameter-efficient fine-tuning (PEFT) are limited by computational costs and performance degradation.
Approach:	They propose a method that integrates Low-Rank Adaptation and Mixture-of-Experts (MoE) they propose combining expert load imbalance and representation collapse to improve LLM performance .
Outcome:	The proposed method outperforms homogeneous MoE-LoRA architectures in performance and parameter efficiency.

Copied to clipboard

Haohang Li, Yupeng Cao, Yangyang Yu, Shashidhar Reddy Javaji, Zhiyang Deng, Yueru He, Yuechen Jiang, Zining Zhu, K.p. Subbalakshmi, Jimin Huang, Lingfei Qian, Xueqing Peng, Jordan W. Suchow, Qianqian Xie

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

Challenge:	Recent advances have underscored the potential of large language model (LLM)-based agents in financial decision-making.
Approach:	They propose to evaluate LLM agents using 13 different LLMs as backbone models across various market environments and tasks.
Outcome:	The proposed framework assesses the reasoning and decision-making capabilities of 13 different LLMs across various market environments and tasks.

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 .

HiGMem: A Hierarchical and LLM-Guided Memory System for Long-Term Conversational Agents (2026.findings-acl)

Copied to clipboard

Shuqi Cao, Jingyi He, Fei Tan

Natural Language Interfaces

Challenge:	Existing memory systems rely on vector similarity for retrieval, resulting in bloated evidence sets . existing systems produce little additional recall, but this approach lowers retrieval precision .
Approach:	They propose a two-level event-turn memory system that uses event summaries as semantic anchors to predict which related turns are worth reading.
Outcome:	The proposed system achieves the best F1 on four of five question categories and improves adversarial F1 from 0.54 to 0.78 over A-Mem while retrieving an order of magnitude fewer turns.

Intuitive or Dependent? Investigating LLMs’ Behavior Style to Conflicting Prompts (2024.acl-long)

Copied to clipboard

Jiahao Ying, Yixin Cao, Kai Xiong, Long Cui, Yidong He, Yongbin Liu

CAPE: A Chinese Dataset for Appraisal-based Emotional Generation in Large Language Models (2025.findings-naacl)

Challenge:	Extensive experiments with seven Large Language Models reveal their varying behaviors.
Approach:	They investigate the behaviors of Large Language Models when faced with conflicting prompts versus their internal memory.
Outcome:	Extensive experiments with seven LLMs reveal their varying behaviors.

Copied to clipboard

June M. Liu, He Cao, Renliang Sun, Rui Wang, Yu Li, Jiaxing Zhang

Attribution-Based Analysis and Optimization of Modular Agentic Workflows (2026.findings-acl)

Challenge:	Existing LLMs fail to capture the nuances of human emotions, making their interactions seem impersonal or inadequate.
Approach:	They propose a two-stage automatic data generation framework to generate a Chinese dataset called CAPE . their data is a cognitive appraisal theory-based Emotional corpus that accounts for personal and situational factors.
Outcome:	The proposed framework can generate human-like responses in conversation with large language models.

Copied to clipboard

Yingxuan Yang, Bo Huang, Siyuan Qi, Chao Feng, Haoyi Hu, Yuxuan Zhu, Jinbo Hu, Haoran Zhao, Ziyi He, Xiao Liu, ZongYu Wang, Muning Wen, Lin Qiu, Xuezhi Cao, Xunliang Cai, Yong Yu, Weinan Zhang

Challenge:	Large Language Models (LLMs) have driven the rise of agentic workflows . yet, how can we attribute performance gains to individual upgrades and their interactions?
Approach:	They propose a game-theoretic framework that models component upgrades as players and evaluates component coalitions to compute Shapley values.
Outcome:	The proposed framework provides interaction-aware attribution and recommendation for model allocation under a fixed workflow structure.

Evaluating LLMs’ Assessment of Mixed-Context Hallucination Through the Lens of Summarization (2025.findings-acl)

Copied to clipboard

Siya Qi, Rui Cao, Yulan He, Zheng Yuan

Rethinking Text-based Protein Understanding: Retrieval or LLM? (2025.emnlp-main)

Challenge:	Large language models generate coherent text and follow instructions across diverse tasks, but a critical challenge in scaling LLM applications is hallucination, where the generated content lacks factual grounding or deviates from the intended discourse context.
Approach:	They use summarization as a representative task to evaluate LLMs' capability in detecting mixed-context hallucinations, specifically distinguishing between factual and non-factual hallucinos.
Outcome:	The proposed model distinguishes between factual and non-factual hallucinations, and their performance bottlenecks.

Copied to clipboard

Juntong Wu, Zijing Liu, He Cao, Li Hao, Bin Feng, Zishan Shu, Ke Yu, Li Yuan, Yu Li

Information Retrieval

Challenge:	Recent studies have focused on integrating protein-related knowledge into large language models through continued pretraining and multi-modal alignment.
Approach:	They propose a retrieval-enhanced method which significantly outperforms fine-tuned LLMs for protein-to-text generation and shows accuracy and efficiency in training-free scenarios.
Outcome:	The proposed method significantly outperforms fine-tuned LLMs for protein-to-text generation and shows accuracy and efficiency in training-free scenarios.

HMT: Hierarchical Memory Transformer for Efficient Long Context Language Processing (2025.naacl-long)

Copied to clipboard

Zifan He, Yingqi Cao, Zongyue Qin, Neha Prakriya, Yizhou Sun, Jason Cong

Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models (2026.findings-acl)

Challenge:	Existing models that memorize past tokens have “flat” memory architectures that restrict the context window.
Approach:	They propose a framework that imitates human memorization behavior by preserving tokens from early input segments, passing memory embeddings along the sequence, and recalling relevant information from history.
Outcome:	The proposed framework outperforms existing models in language modeling and question-answering tasks and achieves comparable or superior generation quality to long-context models with 2 57 fewer parameters and 2.5 116 less inference memory.

Copied to clipboard

Yuan Sui, Yufei He, Tri Cao, Sophia Simeng Han, Yulin Chen, Bryan Hooi

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

Challenge:	Recent advances on prompting and post-training have enabled LLMs to perform step-wise reasoning tasks, but they tend to explore unproductive solution paths without effective backtracking or strategy adjustment.
Approach:	They propose a framework that empowers LLMs to “think about how to think” and dynamically adapts reasoning strategies in real-time.
Outcome:	The proposed framework outperforms previous SOTA methods by 9-12% in accuracy while reducing inference time by 28-35% under the same compute budget.

Copied to clipboard

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

All That Glisters Is Not Gold: A Benchmark for Reference-Free Counterfactual Financial Misinformation Detection (2026.acl-long)

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

Copied to clipboard

Yuechen Jiang, Zhiwei Liu, Yupeng Cao, Yueru He, Ziyang Xu, Chen Xu, Zhiyang Deng, Prayag Tiwari, Xi Chen, Alejandro Lopez-Lira, Jimin Huang, Junichi Tsujii, Sophia Ananiadou

ChemAmp: Amplified Chemistry Tools via Composable Agents (2026.findings-acl)

Challenge:	RFC-Bench evaluates large language models on financial misinformation under realistic news . current models struggle to maintain coherent belief states without external grounding, study finds .
Approach:	They propose a benchmark for evaluating large language models on financial misinformation under realistic news.
Outcome:	The proposed model performs better when context is available, while reference-free settings expose significant weaknesses.

Copied to clipboard

Zhucong Li, Powei Chang, Jin Xiao, Zhijian Zhou, Qianyu He, Jiaqing Liang, Fenglei Cao, Xu Yinghui, Yuan Qi

Challenge:	LLM-based agents are powerful tools for automating complex scientific workflows, especially in chemistry, but their single-task performance is limited by tool constraints.
Approach:	They propose a framework that optimizes the collective capabilities of specialized tools by dynamic coordination within individual tasks.
Outcome:	The proposed framework outperforms chemistry-specialized models, generalist LLMs, and agent systems with tool orchestration.

Rethinking-based Code Summarization with Chain of Comments (2025.coling-main)

Copied to clipboard

Liuwen Cao, Hongkui He, Hailin Huang, Jiexin Wang, Yi Cai

Programming Languages in NLP

Challenge:	Existing methods focus on learning a direct mapping from pure code to summaries, overlooking the heterogeneity gap between code and summary.
Approach:	They propose a framework that uses chain of comments as auxiliary intermediate information to bridge the gap between code and summaries.
Outcome:	The proposed framework outperforms baseline models and multiple code Large Language Models by a large margin.

Vocabulary Pyramid Network: Multi-Pass Encoding and Decoding with Multi-Level Vocabularies for Response Generation (P19-1)

Copied to clipboard

Cao Liu, Shizhu He, Kang Liu, Jun Zhao

Domain-Lifelong Learning for Dialogue State Tracking via Knowledge Preservation Networks (2021.emnlp-main)

Challenge:	Conventional methods employ a fixed vocabulary and one-pass decoding, which make them prone to safe and general responses and lack further refinement to the first generated raw sequence.
Approach:	They propose a Vocabulary Pyramid Network which integrates multi-pass encoding and decoding with multi-level vocabularies into response generation.
Outcome:	The proposed system outperforms strong baselines on English Twitter and Chinese Weibo datasets.

Copied to clipboard

Qingbin Liu, Pengfei Cao, Cao Liu, Jiansong Chen, Xunliang Cai, Fan Yang, Shizhu He, Kang Liu, Jun Zhao

MoleculeQA: A Dataset to Evaluate Factual Accuracy in Molecular Comprehension (2024.findings-emnlp)

Challenge:	Existing offline DST models require a fixed dataset to train . Existing domain-lifelong learning methods are impractical in real-world applications .
Approach:	They propose a domain-lifelong learning method to continuously train a DST model on new data to learn incessantly emerging new domains while avoiding catastrophically forgetting old learned domains.
Outcome:	The proposed method outperforms state-of-the-art lifelong learning methods by 4.25% and 8.27% on the MultiWOZ and the SGD benchmarks.

Copied to clipboard

Xingyu Lu, He Cao, Zijing Liu, Shengyuan Bai, Leqing Chen, Yuan Yao, Hai-Tao Zheng, Yu Li

Question Answering

Challenge:	Existing models generate erroneous information and evaluations fail to assess factual correctness of models.
Approach:	They propose to use MoleculeQA to evaluate molecular factual correctness in large language models by organizing molecules into a taxonomy and building QA pairs through human and LLM efforts.
Outcome:	The proposed model improves the factual correctness of generated information and enables the development of new models.

MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)

Copied to clipboard

Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie

O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning (2026.findings-acl)

Challenge:	Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models.
Approach:	They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts.
Outcome:	The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings .

Copied to clipboard

Haotian Luo, Haiying He, Yibo Wang, Shiwei Liu, Wei Li, Xiaochun Cao, Dacheng Tao, Naiqiang Tan, Li Shen

Breaking the Reasoning Barrier A Survey on LLM Complex Reasoning through the Lens of Self-Evolution (2025.findings-acl)

Challenge:	Recent long-thought reasoning models adopt extended reasoning processes similar to how humans ponder over complex problems.
Approach:	They propose a model that uses RL-style fine-tuning to reduce inference overhead while maintaining accuracy.
Outcome:	The proposed model reduces inference overhead while maintaining accuracy.

Copied to clipboard

Tao He, Hao Li, Jingchang Chen, Runxuan Liu, Yixin Cao, Lizi Liao, Zihao Zheng, Zheng Chu, Jiafeng Liang, Ming Liu, Bing Qin

Learning to Evolve: A Self-Improving Framework for Multi-Agent Systems via Textual Parameter Graph Optimization (2026.findings-acl)

Challenge:	OpenAI's O1 and subsequent projects like DeepSeek R1 have significantly advanced research on complex reasoning in LLMs.
Approach:	They analyze existing reasoning studies from the perspective of self-evolution and summarize O1-like works from open-source projects like DeepSeek R1 and Kimi-k1.5.
Outcome:	The proposed models are based on open-source models and pioneer advanced methodologies like Scaling Reinforcement Learning (RL).

Copied to clipboard

Shan He, Runze Wang, Zhuoyun Du, Huiyu Bai, Zouying Cao, Yu Cheng, Bo Zheng

Structured Data in NLP

Challenge:	Existing methods for designing and optimizing multi-agent systems are static and do not learn from experience.
Approach:	They propose a framework that enables a multi-agent system to learn to evolve . they use "textual gradients" to pinpoint failures and suggest granular modifications .
Outcome:	a new framework enables a multi-agent system to learn to evolve . it learns from historical optimization experiences to improve its performance .

CGoDial: A Large-Scale Benchmark for Chinese Goal-oriented Dialog Evaluation (2022.emnlp-main)

Copied to clipboard

Yinpei Dai, Wanwei He, Bowen Li, Yuchuan Wu, Zheng Cao, Zhongqi An, Jian Sun, Yongbin Li

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

Challenge:	a new benchmark for goal-oriented dialog evaluation is needed to address the problem of knowledge sources, noisy user expressions, and the shortage of annotated data.
Approach:	They propose a Chinese benchmark for goal-oriented dialog evaluation that uses dialog sessions and 574,949 dialog turns to bridge the gap between academic benchmarks and spoken dialog scenarios.
Outcome:	The proposed benchmark contains 96,763 dialog sessions and 574,949 dialog turns totally.

Copied to clipboard

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

SimRPD: Optimizing Recruitment Proactive Dialogue Agents through Simulator-Based Data Evaluation and Selection (2026.acl-industry)

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

Copied to clipboard

Zhiyong Cao, Dunqiang Liu, Qi Dai, Haojun Xu, Huai Yuen Khor, Hao Wang, Huan He, Yafei Liu, Ke Ma, Ruqian Shi, Sicheng Zhou, Sijia Yao

Zero-Shot Cross-Lingual Document-Level Event Causality Identification with Heterogeneous Graph Contrastive Transfer Learning (2024.lrec-main)

Challenge:	High-quality data in training proactive dialogue agents is scarce, despite fine-tuning and reinforcement learning . a recent study has shown that the effectiveness of supervised fine-touring is limited by the lack of high-quality, domain-specific training data.
Approach:	They propose a framework for training recruitment proactive dialogue agents using a high-fidelity user simulator and a multi-dimensional evaluation framework based on Chain-of-Intention.
Outcome:	The proposed framework outperforms existing simulator-based data selection strategies in a real-world recruitment scenario.

Copied to clipboard

Zhitao He, Pengfei Cao, Zhuoran Jin, Yubo Chen, Kang Liu, Zhiqiang Zhang, Mengshu Sun, Jun Zhao

ACE-M3: Automatic Capability Evaluator for Multimodal Medical Models (2025.coling-main)

Challenge:	Existing studies focus on sentence-level ECI with high-resource languages, leaving document-level DECI with low-resourced languages under-explored.
Approach:	They propose a Heterogeneous Graph Interaction Model with Multi-granularity Contrastive Transfer Learning for zero-shot cross-lingual ECI.
Outcome:	The proposed model outperforms the state-of-the-art model on monolingual and multilingual scenarios by 9.4% and 8.2% of average F1 score.

Copied to clipboard

Xiechi Zhang, Shunfan Zheng, Linlin Wang, Gerard de Melo, Zhu Cao, Xiaoling Wang, Liang He

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

Challenge:	Existing metrics for multimodal large language models only focus on token overlap and may not align with human judgment.
Approach:	They propose an open-source model that assesses the question answering abilities of multimodal large language models.
Outcome:	Experiments show that the ACE-M3 model performs better than existing models and is more reliable than existing metrics.

Copied to clipboard

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

SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding (2022.coling-1)

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

Copied to clipboard

Wanwei He, Yinpei Dai, Binyuan Hui, Min Yang, Zheng Cao, Jianbo Dong, Fei Huang, Luo Si, Yongbin Li

CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems (2026.acl-long)

Challenge:	Existing methods for dialog understanding only consider self-augmented dialogs as positive samples and treat all other dialogs like negative ones.
Approach:	They propose a tree-structured pre-trained conversation model which learns dialog representations from limited labeled dialogs and large-scale unlabeled dialog corpora via semi-supervised contrastive pre-training.
Outcome:	The proposed model can achieve state-of-the-art results on the DialoGLUE benchmark.

Copied to clipboard

Yongxuan Wu, Xixun Lin, He Zhang, Nan Sun, Kun Wang, Chuan Zhou, Shirui Pan, Yanan Cao

Scholar Inbox: Personalized Paper Recommendations for Scientists (2025.acl-demo)

Challenge:	LLM-based multi-agent systems (MAS) have demonstrated remarkable capabilities in solving complex tasks.
Approach:	They propose a communication inference attack that constructs new adversarial queries to induce intermediate agents’ reasoning outputs and models their semantic correlations through the global bias disentanglement and LLM-guided weak supervision.
Outcome:	The proposed attack achieves an average AUC of 0.87 and a peak AUC up to 0.99, revealing the privacy risk in MAS.

Copied to clipboard

Markus Flicke, Glenn Angrabeit, Madhav Iyengar, Vitalii Protsenko, Illia Shakun, Jovan Cicvaric, Bora Kargi, Haoyu He, Lukas Schuler, Lewin Scholz, Kavyanjali Agnihotri, Yong Cao, Andreas Geiger

mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections (2022.emnlp-main)

Challenge:	Scholar Inbox is an open-access platform designed to address the challenges researchers face in staying current with the rapidly expanding volume of scientific publications.
Approach:	They propose to provide personalized recommendations, continuous updates from open-access archives, visual paper summaries, semantic search, and a range of tools to streamline research workflows and promote open access publications.
Outcome:	The proposed platform is based on a dataset of 800k user ratings and an extensive user study.

Copied to clipboard

Chenliang Li, Haiyang Xu, Junfeng Tian, Wei Wang, Ming Yan, Bin Bi, Jiabo Ye, He Chen, Guohai Xu, Zheng Cao, Ji Zhang, Songfang Huang, Fei Huang, Jingren Zhou, Luo Si

Visual Data in NLP

Challenge:	Existing pre-trained vision-language models suffer from inefficiency and linguistic signal overwhelmed by long visual sequences in cross-modal alignment.
Approach:	They propose a vision-language foundation model with cross-modal skip-connections that can be pre-trained end-to-end on large-scale image-text pairs with both discriminative and generative objectives.
Outcome:	The proposed model achieves state-of-the-art results on a wide range of vision-language downstream tasks, including image captioning, image-text retrieval, visual grounding and visual question answering.

Alignment Precedes Fusion: Open-Vocabulary Named Entity Recognition as Context-Type Semantic Matching (2023.findings-emnlp)

Copied to clipboard

Zhuoran Jin, Pengfei Cao, Zhitao He, Yubo Chen, Kang Liu, Jun Zhao

KQA Pro: A Dataset with Explicit Compositional Programs for Complex Question Answering over Knowledge Base (2022.acl-long)

Challenge:	Continual learning and zero-shot learning approaches have not been adopted to scale to novel-emerging types.
Approach:	They propose a method to recognize entities in novel types by their textual names or descriptions.
Outcome:	The proposed method outperforms the state-of-the-art methods on three challenging OVNER benchmarks by 9.7%, 9.5%, and 1.8% F1-score of novel types.

Copied to clipboard

Shulin Cao, Jiaxin Shi, Liangming Pan, Lunyiu Nie, Yutong Xiang, Lei Hou, Juanzi Li, Bin He, Hanwang Zhang

Natural Language Interfaces

Challenge:	Existing benchmarks for Complex KBQA lack compositional reasoning capabilities . Existing methods for Complex questions are poor in diversity or scale .
Approach:	They propose a compositional programming language to represent the reasoning process of complex questions.
Outcome:	The proposed dataset includes around 120K diverse natural language questions . it provides a compositional and interpretable programming language to represent the reasoning process of complex questions based on the proposed model .

HeteroSpec: Leveraging Contextual Heterogeneity for Efficient Speculative Decoding (2026.acl-long)

Copied to clipboard

Siran Liu, Yang Ye, Qianchao Zhu, Zane Cao, Yongchao He

Green & Sustainable NLP

Challenge:	Autoregressive decoding limits the inference throughput of Large Language Models due to its sequential dependency.
Approach:	They propose a framework that allocates verification effort in proportion to candidate uncertainty.
Outcome:	Speculative decoding achieves an average speedup over state-of-the-art methods . a small subset of high-confidence predictions accounts for most successful verifications .

ORMind: A Cognitive-Inspired End-to-End Reasoning Framework for Operations Research (2025.acl-industry)

Copied to clipboard

Zhiyuan Wang, Bokui Chen, Yinya Huang, Qingxing Cao, Ming He, Jianping Fan, Xiaodan Liang

From Informal to Formal – Incorporating and Evaluating LLMs on Natural Language Requirements to Verifiable Formal Proofs (2025.acl-long)

Challenge:	Large Language Models (LLMs) have shown promising results in various domains, but their practical application in industry-relevant operations research presents significant challenges and opportunities.
Approach:	They propose a cognitive-inspired framework that enhances optimization through counterfactual reasoning . they use a workflow that transforms requirements into mathematical models and executable solver code .
Outcome:	Experiments show that ORMind outperforms existing methods in the NL4Opt dataset and ComplexOR dataset.

Copied to clipboard

Jialun Cao, Yaojie Lu, Meiziniu Li, Haoyang Ma, Haokun Li, Mengda He, Cheng Wen, Le Sun, Hongyu Zhang, Shengchao Qin, Shing-Chi Cheung, Cong Tian

PRESTO: Progressive Pretraining Enhances Synthetic Chemistry Outcomes (2024.findings-emnlp)

Challenge:	Recent studies in formal mathematical reasoning have shown an unstoppable growth trend.
Approach:	They constructed 18k high-quality instruction-response pairs across five mainstream formal specification languages and evaluated them against ten open-sourced LLMs.
Outcome:	The proposed model compared instruction-response pairs across five formal specification languages and found that the LLMs were good at writing proof segments when given either the code, or the detailed description of proof steps.

Copied to clipboard

He Cao, Yanjun Shao, Zhiyuan Liu, Zijing Liu, Xiangru Tang, Yuan Yao, Yu Li

Non-Autoregressive Chinese ASR Error Correction with Phonological Training (2022.naacl-main)

Challenge:	Multimodal Large Language Models (MLLMs) have seen growing adoption across various scientific domains.
Approach:	They propose a framework that bridges the molecule-text modality gap by integrating a comprehensive benchmark of pretraining strategies and dataset configurations.
Outcome:	The proposed framework improves multimodal LLMs through cross-modal alignment and multi-graph understanding.

Copied to clipboard

Zheng Fang, Ruiqing Zhang, Zhongjun He, Hua Wu, Yanan Cao

Speech & Audio in NLP

Challenge:	Existing methods to correct ASR errors focus on fixed-length corrections, but rarely consider variable-length ones.
Approach:	They propose a non-autoregressive method to correct Chinese ASR errors . they use phonological tokens to extend the source sentence for variable-length correction .
Outcome:	The proposed method improves word error rate and speeds up inference by 6.2 times compared with the autoregressive model.

AgentsCourt: Building Judicial Decision-Making Agents with Court Debate Simulation and Legal Knowledge Augmentation (2024.findings-emnlp)

Copied to clipboard

Zhitao He, Pengfei Cao, Chenhao Wang, Zhuoran Jin, Yubo Chen, Jiexin Xu, Huaijun Li, Kang Liu, Jun Zhao

Are LLMs Rational Investors? A Study on the Financial Bias in LLMs (2025.findings-acl)

Challenge:	Recent advances in deep learning have significantly impacted the legal domain.
Approach:	They propose a multi-agent framework for judicial decision-making that simulates the court trial process . they propose 420 Chinese judgment documents to support their framework and build a large-scale legal knowledge base .
Outcome:	The proposed framework outperforms existing methods in various aspects, especially in generating legal articles.

Copied to clipboard

Yuhang Zhou, Yuchen Ni, Zhiheng Xi, Zhangyue Yin, Yu He, Gan Yunhui, Xiang Liu, Zhang Jian, Sen Liu, Xipeng Qiu, Yixin Cao, Guangnan Ye, Hongfeng Chai

CRUXEVAL-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution (2025.acl-long)

Challenge:	Existing studies on biases within specific domains, such as finance, remain limited.
Approach:	They propose a framework to detect, detect, analyze and mitigate financial biases in large language models.
Outcome:	The proposed framework reduces bias by 68% for the most biased model, according to key metrics.

Copied to clipboard

Ruiyang Xu, Jialun Cao, Yaojie Lu, Ming Wen, Hongyu Lin, Xianpei Han, Ben He, Shing-Chi Cheung, Le Sun

Programming Languages in NLP

Challenge:	Existing code benchmarks focus on code generation, while those for code reasoning are insufficient.
Approach:	They propose a multi-lingual code reasoning benchmark that contains 19 programming languages and at least 600 subjects for each language.
Outcome:	The proposed model trains on Python and achieves 34.4% Pass@1 in other languages, revealing the cross-language generalization of LLMs.

Dynamic Guided and Domain Applicable Safeguards for Enhanced Security in Large Language Models (2025.findings-naacl)

Copied to clipboard

Weidi Luo, He Cao, Zijing Liu, Yu Wang, Aidan Wong, Bin Feng, Yuan Yao, Yu Li

Generating Questions for Knowledge Bases via Incorporating Diversified Contexts and Answer-Aware Loss (D19-1)

Challenge:	Existing defense methods struggle with two key issues: inadequate defense capabilities and over-defensiveness.
Approach:	They propose a multi-agents-based framework that leverages accurate external information to provide an unbiased summary of user intentions and safety response guidance.
Outcome:	Experiments on popular jailbreak attacks and benign datasets show that the proposed framework can enhance LLM's robustness against jailbreaks without compromising its general functionality.

Copied to clipboard

Cao Liu, Kang Liu, Shizhu He, Zaiqing Nie, Jun Zhao

Knowledge Representation

Challenge:	Conventional methods for question generation neglect two crucial research issues: 1) the given predicate needs to be expressed; 2) the answer to the generated question needs to have a definitive answer.
Approach:	They propose a neural encoder-decoder model with multi-level copy mechanisms to generate questions . they also introduce answer-aware loss to make generated questions correspond to more definitive answers.
Outcome:	The proposed model achieves state-of-the-art performance while corresponding to more definitive answers.

InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery (2025.coling-main)

Copied to clipboard

He Cao, Zijing Liu, Xingyu Lu, Yuan Yao, Yu Li