Papers by Jun Cao

Length-Induced Embedding Collapse in PLM-based Models (2025.acl-long)

Challenge:	Multimodal Large Language Models (MLLMs) are developing but lack external feedback . there is no clear on how to select reward models for agents .
Approach:	They propose a benchmark to evaluate agent reward modeling ability in MLLMs . they use multiple dimensions and real-world agent scenarios evaluation .
Outcome:	The proposed benchmark evaluates agent performance in multimodal large language models . it covers perception, planning, and safety with 7 scenarios and is highly difficult and high-quality .

Copied to clipboard

Yuqi Zhou, Sunhao Dai, Zhanshuo Cao, Xiao Zhang, Jun Xu

Event Ontology Completion with Hierarchical Structure Evolution Networks (2023.emnlp-main)

Challenge:	In text embeddings from PLMs are essential for many NLP applications, but performance degrades on longer texts.
Approach:	They propose a method which mitigates the phenomenon of Length Collapse . they propose TempScale to ensure more consistent embeddings across different text lengths .
Outcome:	The proposed method improves performance on MTEB and LongEmbed by 0.94% on short and 1.10% on long texts.

Copied to clipboard

Pengfei Cao, Yupu Hao, Yubo Chen, Kang Liu, Jiexin Xu, Huaijun Li, Xiaojian Jiang, Jun Zhao

Sharing, Teaching and Aligning: Knowledgeable Transfer Learning for Cross-Lingual Machine Reading Comprehension (2023.findings-emnlp)

Challenge:	Existing methods for event detection require predefined schemas, but manual defining is expensive and labor-intensive.
Approach:	They propose a task to achieve event clustering, hierarchy expansion and type naming . they propose 'neighbor Contrastive Clustering' module and a Hierarchy-Aware Linking module .
Outcome:	The proposed method outperforms baseline methods on three datasets.

Copied to clipboard

Tingfeng Cao, Chengyu Wang, Chuanqi Tan, Jun Huang, Jinhui Zhu

Multilinguality

Challenge:	X-STA is a new approach for cross-lingual machine reading comprehension . the variation of answer span positions in different languages makes it difficult to transfer knowledge across languages.
Approach:	They propose a method that leverages an attentive teacher to subtly transfer the answer spans of the source language to the answer output space of the target.
Outcome:	The proposed method outperforms state-of-the-art approaches on three multi-lingual datasets.

Unified Thinker: A General Reasoning Core for Image Generation (2026.acl-long)

Copied to clipboard

Sashuai Zhou, Qiang Zhou, Jijin Hu, Hanqing Yang, Yue Cao, Junpeng Ma, Yinchao Ma, Jun Song, Tiezheng Ge, Cheng Yu, Bo Zheng, Zhou Zhao

Continual Few-shot Event Detection via Hierarchical Augmentation Networks (2024.lrec-main)

Challenge:	generative models struggle with logic-intensive instruction following, exposing a persistent reasoning–execution gap.
Approach:	They propose a task-agnostic reasoning architecture for general image generation . they propose pixel-level feedback to ground the Thinker's policy in pixel feedback .
Outcome:	The proposed system significantly improves image reasoning and generation quality.

Copied to clipboard

Chenlong Zhang, Pengfei Cao, Yubo Chen, Kang Liu, Zhiqiang Zhang, Mengshu Sun, Jun Zhao

Improving Event Detection via Open-domain Trigger Knowledge (2020.acl-main)

Challenge:	Existing methods for continual few-shot event detection use labeled data, but in real-world applications, new event types emerge continually.
Approach:	They propose a memory-based framework for continual few-shot event detection . they incorporate prototypical augmentation into the memory set to memorize previous event types .
Outcome:	The proposed method outperforms existing methods in multiple continual few-shot event detection tasks.

Copied to clipboard

Meihan Tong, Bin Xu, Shuai Wang, Yixin Cao, Lei Hou, Juanzi Li, Jun Xie

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

Challenge:	Existing methods for event detecting are prone to overfitting densely labeled trigger words due to the small scale of training data.
Approach:	They propose a novel Enrichment Knowledge Distillation model to leverage external open-domain trigger knowledge to reduce in-built biases to frequent trigger words in annotations.
Outcome:	The proposed model outperforms nine strong baselines and is especially effective for unseen/sparsely labeled trigger words.

Copied to clipboard

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

Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do (2026.acl-long)

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.

Copied to clipboard

Zhuoran Jin, Kejian Zhu, Hongbang Yuan, Yupu Hao, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing (2024.findings-acl)

Challenge:	Existing open-source models often yield only marginal overall improvements, possibly due to an overemphasis on mathematical reasoning at the expense of broader capabilities.
Approach:	They evaluate 12 multimodal tasks using 14 non-reasoning models and 8 reasoning models.
Outcome:	The proposed method is effective in multimodal reasoning tasks, the authors show . they show that it lacks the ability to maintain deep visual introspection throughout the reasoning process.

Copied to clipboard

Chenhui Hu, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

Media Source Matters More Than Content: Unveiling Political Bias in LLM-Generated Citations (2025.emnlp-main)

Challenge:	Existing knowledge editing methods focus on single editing, failing to meet the requirements for lifelong editing.
Approach:	They propose an approach that selects editing layer based on the pattern matching degree of editing knowledge across different layers in language models.
Outcome:	The proposed method improves on GPT2-XL and GPT-J in lifelong editing compared to state-of-the-art methods .

Copied to clipboard

Sunhao Dai, Zhanshuo Cao, Wenjie Wang, Liang Pang, Jun Xu, See-Kiong Ng, Tat-Seng Chua

Tug-of-War between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models (2024.lrec-main)

Challenge:	generative search engines rely on in-line citations as the key gateway to original webpages . a recent study shows that LLMs tend to cite left-leaning sources at higher rates compared to traditional retrieval systems .
Approach:	They construct a dataset of news articles labeled with left- or right-leaning stances . they find that LLMs tend to cite left-leansing sources at higher rates than traditional retrieval systems .
Outcome:	The proposed dataset shows that LLMs tend to cite left-leaning sources at higher rates than traditional retrieval systems.

Copied to clipboard

Zhuoran Jin, Pengfei Cao, Yubo Chen, Kang Liu, Xiaojian Jiang, Jiexin Xu, Li Qiuxia, Jun Zhao

Uncertain Local-to-Global Networks for Document-Level Event Factuality Identification (2021.emnlp-main)

Challenge:	Existing knowledge conflicts in RALMs can ensnare them in a tug-of-war between knowledge and evidence, limiting their practical applicability.
Approach:	They propose a method called Conflict-Disentangle Contrastive Decoding (CD2) to better calibrate the model’s confidence.
Outcome:	The proposed method can resolve knowledge conflicts in large language models with the help of conflict-disentangle contrast decoding (CD2) .

Copied to clipboard

Pengfei Cao, Yubo Chen, Yuqing Yang, Kang Liu, Jun Zhao

Challenge:	Existing studies focus on identifying event factuality at sentence level, which leads to conflicts between different mentions of the same event.
Approach:	They propose a document-level event factuality identification model that uses local uncertainty and global structure to model event factuality.
Outcome:	The proposed method outperforms existing models on two widely used datasets.

Interpretable Proof Generation via Iterative Backward Reasoning (2022.naacl-main)

Copied to clipboard

Hanhao Qu, Yu Cao, Jun Gao, Liang Ding, Ruifeng Xu

CogKTR: A Knowledge-Enhanced Text Representation Toolkit for Natural Language Understanding (2022.emnlp-demos)

Challenge:	Existing proof generation tasks require reasoning capabilities, but they usually just request for an answer without the reasoning procedure that would make it interpretable.
Approach:	They propose an iterative backward reasoning model to solve the proof generation tasks on rule-based Question Answering.
Outcome:	The proposed model improves in-domain performance and cross-domain transferability over existing models.

Copied to clipboard

Zhuoran Jin, Tianyi Men, Hongbang Yuan, Yuyang Zhou, Pengfei Cao, Yubo Chen, Zhipeng Xue, Kang Liu, Jun Zhao

Know-MRI: A Knowledge Mechanisms Revealer&Interpreter for Large Language Models (2025.acl-demo)

Challenge:	Existing knowledge-enhanced methods are limited to knowledge-intensive tasks.
Approach:	They propose a knowledge-enhanced text representation toolkit for natural language understanding . it combines knowledge acquisition, knowledge representation, knowledge injection and knowledge application .
Outcome:	The proposed toolkit supports knowledge acquisition, knowledge representation, knowledge injection, and knowledge application.

Copied to clipboard

Jiaxiang Liu, Boxuan Xing, Chenhao Yuan, ChenxiangZhang ChenxiangZhang, Di Wu, Xiusheng Huang, Haida Yu, Chuhan Lang, Pengfei Cao, Jun Zhao, Kang Liu

A Troublemaker with Contagious Jailbreak Makes Chaos in Honest Towns (2025.acl-long)

Challenge:	Existing interpretation methods only support tasks with specific inputs, limiting their practical applications.
Approach:	They propose an extensible module that matches different input data with interpretation methods and consolidates the interpreting outputs.
Outcome:	The proposed module can match different input data with interpretation methods and consolidate the interpreting outputs.

Copied to clipboard

Tianyi Men, Pengfei Cao, Zhuoran Jin, Yubo Chen, Kang Liu, Jun Zhao

Robustness in NLP

Challenge:	Existing research focuses on single-agent attacks and shared memory attacks, but real-world scenarios often involve independent memory.
Approach:	They propose a large-scale, multi-agent, multitopology attack evaluation framework that exploits the memory of an agent to make it more vulnerable to jailbreak attacks.
Outcome:	The proposed framework improves on the troublemaker makes chaos in Honest Town task with 23.51%, 18.95%, and 52.93% improvements in line, star topologies, and 100-agent settings.

Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models (2024.findings-acl)

Copied to clipboard

Zhuoran Jin, Pengfei Cao, Hongbang Yuan, Yubo Chen, Jiexin Xu, Huaijun Li, Xiaojian Jiang, Kang Liu, Jun Zhao

Focus on Your Question! Interpreting and Mitigating Toxic CoT Problems in Commonsense Reasoning (2024.acl-long)

Challenge:	Existing methods to expand internal memory boundaries of language models by providing external context can often conflict, leading to knowledge conflicts.
Approach:	They propose a method that prunes conflicting attention heads without updating model parameters.
Outcome:	The proposed method can flexibly control eight LMs to use internal memory or external context without updating model parameters.

Copied to clipboard

Jiachun Li, Pengfei Cao, Chenhao Wang, Zhuoran Jin, Yubo Chen, Daojian Zeng, Kang Liu, Jun Zhao

InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning (2026.acl-long)

Challenge:	Large language models exhibit high-level commonsense reasoning abilities, especially with enhancement methods like Chain-of-Thought (CoT).
Approach:	They propose a chain-of-thought-like method to elicit models' potential abilities to generate rationales and answers that are based on attribution tracing and causal tracers to probe the internal working mechanism of the LLM.
Outcome:	The proposed method eliminates Toxic CoT problems and improves the model’s overall commonsense reasoning performance by 5.5%.

Copied to clipboard

Qihang Ai, Pi Bu, Yue Cao, Yingyao Wang, Jihao Gu, Jingxuan Xing, Zekun Zhu, Wei Jiang, Zhicheng Zheng, Jun Song, Yuning Jiang

An Empirical Comparison of Unsupervised Constituency Parsing Methods (2020.acl-main)

Challenge:	Recent advances in Vision-Language Models (VLMs) have enabled mobile agents to perceive and interact with real-world mobile environments based on human instructions.
Approach:	They propose a vision-language model that actively seeks human confirmation at critical decision points and a model inspired by reinforcement learning.
Outcome:	The proposed model achieves an improvement of 46.8% in inquiry success rate and the best overall success rate among existing baselines on InquireBench.

Copied to clipboard

Jun Li, Yifan Cao, Jiong Cai, Yong Jiang, Kewei Tu

Xiaomingbot: A Multilingual Robot News Reporter (2020.acl-demos)

Challenge:	Existing methods for unsupervised constituency parsing are inconsistent due to data preprocessing, lexicalization, and evaluation metrics.
Approach:	They propose to standardize experimental settings for better comparability between methods . they compare existing methods with those proposed by decade-old models .
Outcome:	The proposed methods perform better than decade-old models on English and Japanese, respectively, compared with decade- old models.

Copied to clipboard

Runxin Xu, Jun Cao, Mingxuan Wang, Jiaze Chen, Hao Zhou, Ying Zeng, Yuping Wang, Li Chen, Xiang Yin, Xijin Zhang, Songcheng Jiang, Yuxuan Wang, Lei Li

DisCal: Distribution-Aware Calibration for Mathematical Reasoning Under Character-Level Noisy Inputs (2026.acl-long)

Challenge:	Xiaomingbot is a multilingual and multimodal software robot with four capabilities: news generation, news translation, news reading and avatar animation.
Approach:	They propose to build a multilingual and multimodal software robot with four inte- gal capabilities: news generation, news translation, news reading and avatar animation.
Outcome:	The proposed system generates Chinese news, then reads it in multiple languages and generates an animated avatar reading it.

Copied to clipboard

Bo Zhang, Jiawei Zhang, Cong Gao, Bingxu Han, Minghao Hu, Jun Zhang, Yunbo Cao, Zhunchen Luo, Wen Yao, Guotong Geng, Zhong Wang

CoMoL: Efficient Mixture of LoRA Experts via Dynamic Core Space Merging (2026.findings-acl)

Challenge:	Existing methods for calibration of large reasoning models (LRMs) focus on clean inputs, leaving noise unexplored.
Approach:	They propose a confidence calibration framework for character-level noisy inputs that extracts uncertainty signals from both the empirical answer distribution and the model’s predictive distribution and integrates them via a learned calibrator.
Outcome:	Experiments on multiple mathematical reasoning benchmarks show that DisCal outperforms existing calibration methods under noisy inputs, reducing expected calibration error (ECE) by up to 39.21% and improving Area Under the Receiver Operating Characteristic Curve (AUROC) by 31.44%.

Copied to clipboard

Jie Cao, Zhenxuan Fan, Zhuonan Wang, Tianwei Lin, Ziyuan Zhao, Rolan Yan, Wenqiao Zhang, Feifei Shao, Hongwei Wang, Jun Xiao, Siliang Tang

Green & Sustainable NLP

Challenge:	Existing PEFT methods suffer from limited parameter efficiency and coarse-grained adaptation due to proliferation of LoRA experts and instance-level routing.
Approach:	They propose a new MoE-LoRA framework that incorporates expert diversity, parameter efficiency, and fine-grained adaptation.
Outcome:	The proposed framework outperforms existing methods on multiple tasks while maintaining parameter efficiency.

Interpreting Sentiment Composition with Latent Semantic Tree (2023.findings-acl)

Copied to clipboard

Zhongtao Jiang, Yuanzhe Zhang, Cao Liu, Jiansong Chen, Jun Zhao, Kang Liu

MULFE: A Multi-Level Benchmark for Free Text Model Editing (2024.acl-long)

Challenge:	Current researches on sentiment classification are shifting from improving model performance to interpretability.
Approach:	They propose a new tree form capable of interpreting sentiment composition in a principled way.
Outcome:	The proposed tree can explain sentiment composition in a principled way.

Copied to clipboard

Chenhao Wang, Pengfei Cao, Zhuoran Jin, Yubo Chen, Daojian Zeng, Kang Liu, Jun Zhao

Green & Sustainable NLP

Challenge:	Large Language Models (LLMs) have impressive capabilities in comprehending human language and vast parametric knowledge obtained from large corpora.
Approach:	They propose a multi-level benchmark for free text model editing to bridge the gap . they categorize probe queries into three levels of generalization .
Outcome:	The proposed method improves the generalization performance of large langugae models.

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

Copied to clipboard

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

Robustness in NLP

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

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

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 .

UniICL: An Efficient ICL Framework Unifying Compression, Selection, and Generation (2025.acl-long)

Copied to clipboard

Jun Gao, Qi Lv, Zili Wang, Tianxiang Wu, Ziqiang Cao, Wenjie Li

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

Challenge:	Existing methods to improve reasoning abilities of Large Language Models (LLMs) have limitations due to excessive growth in context length, causing large hardware burden.
Approach:	They propose a novel Unified ICL framework that unifies demonstration compression, demonstration selection, and final response generation.
Outcome:	The proposed framework unifies demonstration compression, demonstration selection, and final response generation.

Copied to clipboard

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

HyperCore: Hyperbolic and Co-graph Representation for Automatic ICD Coding (2020.acl-main)

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

Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao, Shengping Liu, Weifeng Chong

Whispers that Shake Foundations: Analyzing and Mitigating False Premise Hallucinations in Large Language Models (2024.emnlp-main)

Challenge:	Existing methods for ICD coding ignore Code Hierarchy and Code Co-occurrence . cost of manual coding estimated to be $25 billion per year in the US .
Approach:	They propose a hyperbolic representation method to leverage the code hierarchy and a graph convolutional network to utilize the code co-occurrence.
Outcome:	The proposed model outperforms state-of-the-art methods on two widely used datasets.

Copied to clipboard

Hongbang Yuan, Pengfei Cao, Zhuoran Jin, Yubo Chen, Daojian Zeng, Kang Liu, Jun Zhao

LINKED: Eliciting, Filtering and Integrating Knowledge in Large Language Model for Commonsense Reasoning (2024.findings-emnlp)

Challenge:	Large language models generate hallucinated text when confronted with false premise questions . authors propose a method to mitigate false premises hallucinosity .
Approach:	They propose a method to constrain false premise attention heads during the model inference process.
Outcome:	The proposed method improves performance by constraining false premise attention heads . it yields a notable increase of nearly 20% of model performance .

Copied to clipboard

Jiachun Li, Pengfei Cao, Chenhao Wang, Zhuoran Jin, Yubo Chen, Kang Liu, Xiaojian Jiang, Jiexin Xu, Jun Zhao

DiffusionSL: Sequence Labeling via Tag Diffusion Process (2023.findings-emnlp)

Challenge:	Large language models (LLMs) often exhibit poor performance on knowledge-intensive tasks, such as commonsense reasoning.
Approach:	They propose a method to elicit, filter and integrate knowledge in large language models (LINKED) they propose 'reward model' to filter out noisy knowledge and 'take marginal consistent reasoning module'
Outcome:	The proposed method outperforms SOTA baselines on two commonsense reasoning tasks.

Copied to clipboard

Ziyang Huang, Pengfei Cao, Jun Zhao, Kang Liu

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

Challenge:	Sequence Labeling (SL) is a long-standing field of natural language processing.
Approach:	They propose a framework that utilizes a conditional discrete diffusion model for generating discrete tag data.
Outcome:	The proposed framework outperforms gpt-3.5-turbo on multiple benchmark datasets and tasks.

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

SHARP: Self-adaptive Harmful Category-aware Prompt Generation for Black-box Jailbreaking (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

Yingjie Xue, Xingyou Xia, Jun Zhang, Yunbo Cao, Dengpan Ye, Guotong Geng, Fei Li

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

Challenge:	Existing methods for jailbreak ignore the semantic differences between categories of harmful questions, leading to inconsistent success rates and reduced overall attack effectiveness.
Approach:	They propose a category-aware jailbreak framework that incorporates the semantic category of harmful questions into prompt generation.
Outcome:	The proposed framework improves attack success rates and category alignment and achieves better cross-category robustness compared to the state-of-the-art (SOTA) baselines.

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 .

ZhuJiu: A Multi-dimensional, Multi-faceted Chinese Benchmark for Large Language Models (2023.emnlp-demo)

Copied to clipboard

Baoli Zhang, Haining Xie, Pengfan Du, Junhao Chen, Pengfei Cao, Yubo Chen, Shengping Liu, Kang Liu, Jun Zhao

Learning How to Remember: A Meta-Cognitive Management Method for Structured and Transferable Agent Memory (2026.findings-acl)

Challenge:	Various types of LLMs have recently been rapidly developing, such as Llama2 and ChatGLM2 .
Approach:	They propose a benchmark that comprehensively evaluates LLMs across 7 ability dimensions covering 51 tasks.
Outcome:	The proposed benchmarks are comprehensive and systematic, with a high level of accuracy and authority.

Copied to clipboard

Sirui Liang, Pengfei Cao, Jian Zhao, Wenhao Teng, Xiangwen Liao, Jun Zhao, Kang Liu

Challenge:	Existing approaches store memory in fixed representations and reuse it at a single or implicit level of abstraction, which limits generalization and often leads to negative transfer when distribution shift.
Approach:	They propose a Meta-Cognitive Memory Abstraction method which decouples task execution from memory management by combining a frozen task model with a learned memory copilot.
Outcome:	Experiments on ALFWorld, ScienceWorld, and BabyAI show that the proposed method improves performance, out-of-distribution generalization, and cross-task transfer over several baselines.

Improving Empathetic Response Generation by Recognizing Emotion Cause in Conversations (2021.findings-emnlp)

Copied to clipboard

Jun Gao, Yuhan Liu, Haolin Deng, Wei Wang, Yu Cao, Jiachen Du, Ruifeng Xu

RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling (2020.emnlp-main)

Challenge:	Existing approaches to empathetic response generation ignore the emotion cause . existing dialogue systems lack emotion understanding and empathy .
Approach:	They propose a framework that integrates emotion cause information into empathetic response generation by predicting context emotion labels and sequence of emotion cause-oriented labels.
Outcome:	The proposed framework improves empathetic response generation by incorporating emotion cause information into the model.

Copied to clipboard

Jun Quan, Shian Zhang, Qian Cao, Zizhong Li, Deyi Xiong

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement (2025.findings-acl)

Challenge:	RiSAWOZ contains 11.2K human-to-human (H2H) multi-turn semantically annotated dialogues spanning over 12 domains . despite of substantial progress made, there are challenges in creating challenging datasets in terms of size, multiple domains, semantic annotations and complexity.
Approach:	They propose a large-scale multi-domain Chinese Wizard-of-Oz dataset with rich semantic annotations that captures discourse phenomena for task-oriented dialogue modeling.
Outcome:	The proposed dataset contains 11.2K human-to-human (H2H) multi-turn semantically annotated dialogues with more than 150K utterances spanning over 12 domains.

Copied to clipboard

Peng Ding, Jun Kuang, ZongYu Wang, Xuezhi Cao, Xunliang Cai, Jiajun Chen, Shujian Huang

Challenge:	Large Language Models (LLMs) have demonstrated impressive capabilities across various tasks but are vulnerable to meticulously crafted jailbreak attacks.
Approach:	They propose a training-free defense strategy to align LLMs’ strong safety discrimination performance with their relatively weaker safety generation ability.
Outcome:	The proposed strategy achieves an average 99% success rate against numerous complex and covert jailbreak methods while maintaining helpfulness on general benchmarks.

ZhuJiu-Knowledge: A Fairer Platform for Evaluating Multiple Knowledge Types in Large Language Models (2024.naacl-demo)

Copied to clipboard

Pengfan Du, Sirui Liang, Baoli Zhang, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

The Bidirectional Process Reward Model (2026.acl-long)

Challenge:	evaluating the knowledge of large language models (LLMs) is crucial, and rapid advancement in large language modeling has heightened the importance of model evaluations.
Approach:	They propose a fairer benchmark for evaluating multiple knowledge types of LLMs by focusing on commonsense knowledge, world knowledge, and language knowledge.
Outcome:	The proposed framework evaluates 14 current mainstream LLMs and provides a detailed discussion and analysis of their results.

Copied to clipboard

Lingyin Zhang, Jun Gao, Xiaoxue Ren, Ziqiang Cao

Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Insights from Multi-Agent Collaboration (2024.findings-emnlp)

Challenge:	Process reward models (PRMs) assign fine-grained scores to intermediate reasoning steps within a solution trajectory.
Approach:	They propose a bidirectional evaluation paradigm that integrates a parallel evaluation stream alongside the L2R evaluation scheme and a gating mechanism to fuse the reward scores.
Outcome:	The proposed model surpasses unidirectional baselines in multiple benchmarks, LLM objectives and sampling policies.

Copied to clipboard

Weikang Yuan, Junjie Cao, Zhuoren Jiang, Yangyang Kang, Jun Lin, Kaisong Song, Tianqianjin Lin, Pengwei Yan, Changlong Sun, Xiaozhong Liu

LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification (2021.acl-long)

Challenge:	Existing studies have found that when LLMs are given criminal facts and legal rules, then asked whether cases constitute a certain charge, they struggle to understand legal theories and perform basic legal reasoning tasks.
Approach:	They propose a task to assess LLMs' understanding of legal theories and reasoning capabilities by using a novel framework: Multi-Agent framework for improving complex legal reasoning capability.
Outcome:	The proposed framework improves LLMs' understanding of legal theories and reasoning abilities in real-world scenarios.

Copied to clipboard

Xinyu Zuo, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao, Weihua Peng, Yuguang Chen

Geoparsing: Diagram Parsing for Plane and Solid Geometry with a Unified Formal Language (2026.findings-acl)

Challenge:	Existing methods for event causality identification (ECI) rely on annotated training data.
Approach:	They propose a method to augment training data for event causality identification by iteratively generating new examples and classifying event causalities in a dual learning framework.
Outcome:	The proposed method outperforms existing methods on EventStoryLine and Causal-TimeBank.

Copied to clipboard

Peijie Wang, Ming-Liang Zhang, Jun Cao, Chao Deng, Dekang Ran, Pi Bu, Hongda Sun, Xuan Zhang, Yingyao Wang, Jun Song, Bo Zheng, Fei Yin, Cheng-Lin Liu

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

Challenge:	Recent advances in Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across various vision reasoning tasks.
Approach:	They propose a unified formal language that integrates plane and solid geometry, comprehensively covering geometric structures and semantic relations.
Outcome:	The proposed language achieves state-of-the-art parsing performance and significantly boosts MLLMs’ capabilities for downstream geometry reasoning tasks.

Copied to clipboard

Cao Liu, Shizhu He, Kang Liu, Jun Zhao

Text Generation

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.

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

Copied to clipboard

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

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

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

Copied to clipboard

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

Augmenting Reasoning Capabilities of LLMs with Graph Structures in Knowledge Base Question Answering (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

Yuhang Tian, Dandan Song, Zhijing Wu, Changzhi Zhou, Hao Wang, Jun Yang, Jing Xu, Ruanmin Cao, HaoYu Wang

KBioXLM: A Knowledge-anchored Biomedical Multilingual Pretrained Language Model (2023.findings-emnlp)

Challenge:	Recent work uses Large Language Models (LLMs) for semantic parsing to address Knowledge Base Question Answering tasks.
Approach:	They propose a framework that augments reasoning capabilities of LLMs with Graph Structures in Knowledge Base Question Answering to retrieve question-related graph structures.
Outcome:	The proposed framework outperforms existing methods on GrailQA and WebQSP under the few-shot setting.

Copied to clipboard

Lei Geng, Xu Yan, Ziqiang Cao, Juntao Li, Wenjie Li, Sujian Li, Xinjie Zhou, Yang Yang, Jun Zhang

Multilinguality

Challenge:	Existing models for multilingual biomedical training are monolingual, resulting in limited cross-lingual capability.
Approach:	They propose a model that transforms a multilingual biomedical corpus into a biomedically domain using a knowledge-anchored approach.
Outcome:	The proposed model outperforms monolingual and multilingual models in cross-lingual scenarios.

Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models (2024.emnlp-main)

Copied to clipboard

Tianyi Men, Pengfei Cao, Zhuoran Jin, Yubo Chen, Kang Liu, Jun Zhao

Clinical-Coder: Assigning Interpretable ICD-10 Codes to Chinese Clinical Notes (2020.acl-demos)

Challenge:	Recent studies have shown that large language models may possess preliminary planning capabilities.
Approach:	They examine the look-ahead planning mechanism in large language models from the perspectives of information flow and internal representations.
Outcome:	The proposed model can decode the decision from the output of MHSA in the middle layers at the last token.

Copied to clipboard

Pengfei Cao, Chenwei Yan, Xiangling Fu, Yubo Chen, Kang Liu, Jun Zhao, Shengping Liu, Weifeng Chong

Bridging the Domain Gaps in Context Representations for k-Nearest Neighbor Neural Machine Translation (2023.acl-long)

Challenge:	Existing methods of automatic coding prediction have been successful, but the interpretability of predicted codes is a challenge.
Approach:	They propose an online system that can predict ICD codes for Chinese clinical notes by using a Dilated Convolutional Attention network with N-gram Matching mechanism.
Outcome:	The proposed system is able to provide supporting information in clinical decision making.

Copied to clipboard

Zhiwei Cao, Baosong Yang, Huan Lin, Suhang Wu, Xiangpeng Wei, Dayiheng Liu, Jun Xie, Min Zhang, Jinsong Su

Machine Translation

Challenge:	Existing methods to improve k-Nearest neighbor machine translation (kNN-MT) are based on the ability to non-parametrically adapt to new domains.
Approach:	They propose a method to boost the datastore retrieval of k-Nearest neighbor machine translation by reconstructing the original datastore.
Outcome:	The proposed method boosts the retrieval and translation quality of k-Nearest neighbor machine translation by reconstructing the original datastore.

Reinforcing Agentic Search Via Reward Density Optimization (2026.acl-long)

Copied to clipboard

Kun Luo, Hongjin Qian, Zheng Liu, Ziyi Xia, Shitao Xiao, Zhao Cao, Siqi Bao, Jun Zhao, Kang Liu

DiffChat: Learning to Chat with Text-to-Image Synthesis Models for Interactive Image Creation (2024.findings-acl)

Challenge:	Reinforcement Learning with Verifiable Rewards (RLVR) is a promising approach for enhancing agentic search, but its performance is often hindered by reward sparsity .
Approach:	They propose a new research problem to improve the reward obtained per unit of exploration cost by using a system that decomposes long-horizon tasks into intermediate objectives and assigns process-level rewards to provide denser learning signals.
Outcome:	The proposed framework outperforms strong baselines on several agentic search benchmarks and achieves comparable performance to that of advanced proprietary models.

Copied to clipboard

Jiapeng Wang, Chengyu Wang, Tingfeng Cao, Jun Huang, Lianwen Jin

Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulness (2025.findings-acl)

Challenge:	a novel method to align Large Language Models to "chat" with prompt-as-input Text-to-Image Synthesis models is proposed . a user-specified instruction can be used to create a high quality image .
Approach:	They propose a method to align Large Language Models to "chat" with prompt-as-input Text-to-Image Synthesis models for interactive image creation.
Outcome:	The proposed method can exhibit superior performance than baseline models and strong competitors based on automatic and human evaluations.

Copied to clipboard

Jiachun Li, Pengfei Cao, Yubo Chen, Jiexin Xu, Huaijun Li, Xiaojian Jiang, Kang Liu, Jun Zhao

Challenge:	Chain-of-thought (CoT) prompting demonstrates varying performance under different reasoning tasks.
Approach:	They propose to recall extra information from the question to enhance CoT generation and evaluate CoTs based on their information gain.
Outcome:	The proposed method improves both the faithfulness and effectiveness of CoT and evaluates it based on their information gain.

Meeseeks: A Feedback-Driven, Iterative Self-Correction Benchmark evaluating LLMs’ Instruction Following Capability (2026.findings-acl)

Copied to clipboard

Jiaming Wang, Yunke Zhao, Peng Ding, Jun Kuang, Yibin Shen, Zhe Tang, Yilin Jin, ZongYu Wang, Xiaoyu Li, Xuezhi Cao

Incremental Event Detection via Knowledge Consolidation Networks (2020.emnlp-main)

Challenge:	Existing models lack the ability to adhere to instructions, resulting in suboptimal performance.
Approach:	They propose an automated iterative instruction-following benchmark with integrated feedback mechanism.
Outcome:	The proposed benchmark identifies erroneous components in model responses and provides feedback accurately.

Copied to clipboard

Pengfei Cao, Yubo Chen, Jun Zhao, Taifeng Wang

LeCoDe: A Benchmark Dataset for Interactive Legal Consultation Dialogue Evaluation (2026.acl-long)

Challenge:	Existing approaches to event detection require a fixed set of pre-defined event types . existing methods cannot handle semantic ambiguity and training data imbalance problems .
Approach:	They propose a Knowledge Consolidation Network to address these issues . they propose to use a prototype enhanced retrospection and hierarchical distillation to mitigate the adverse effects of semantic ambiguity and class imbalance.
Outcome:	The proposed method outperforms the state-of-the-art model by 19% and 13.4% of whole F1 score on ACE and TAC benchmarks.

Copied to clipboard

Weikang Yuan, Kaisong Song, Zhuoren Jiang, Junjie Cao, Yujie Zhang, Jun Lin, Kun Kuang, Ji Zhang, Xiaozhong Liu

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

Challenge:	Current systems for legal consultation are insufficient to handle the knowledge-intensive nature of real-world consultations.
Approach:	They propose a multi-turn benchmark dataset to evaluate LLMs in legal consultation settings.
Outcome:	The proposed framework assesses LLMs’ consultation capabilities in terms of (1) clarification capability and (2) professional advice quality.

Copied to clipboard

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

MIE: A Medical Information Extractor towards Medical Dialogues (2020.acl-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

Yuanzhe Zhang, Zhongtao Jiang, Tao Zhang, Shiwan Liu, Jiarun Cao, Kang Liu, Shengping Liu, Jun Zhao

Complex Event Schema Induction with Knowledge-Enriched Diffusion Model (2023.findings-emnlp)

Challenge:	EMRs are important but many doctors suffer from writing them, which is time-consuming and tedious.
Approach:	They propose an automatic conversion of medical dialogues to EMRs using a window-sliding style . they propose a medical information extractor (MIE) that extracts medical information from medical dialogue .
Outcome:	The proposed model extracts medical information from doctor-patient dialogues.

Copied to clipboard

Yupu Hao, Pengfei Cao, Yubo Chen, Kang Liu, Jiexin Xu, Huaijun Li, Xiaojian Jiang, Jun Zhao

Challenge:	Existing studies on event schema induction have been hindered by errors and data quality issues.
Approach:	They propose a knowledge-enriched discrete diffusion model that distills event scenario knowledge from LLMs.
Outcome:	The proposed model achieves outstanding performance across evaluation metrics.

A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily (2024.naacl-long)

Copied to clipboard

Peng Ding, Jun Kuang, Dan Ma, Xuezhi Cao, Yunsen Xian, Jiajun Chen, Shujian Huang

Knowledge-Enriched Event Causality Identification via Latent Structure Induction Networks (2021.acl-long)

Challenge:	Existing methods for generating 'jailbreaks' suffer from manual design or require optimization on other white-box models, which compromises either generalization or efficiency.
Approach:	They propose a framework that leverages LLMs to generate effective jailbreak prompts and a generalized framework that can be used to generate prompts.
Outcome:	The proposed framework improves the attack success rate while reducing the time cost compared to baselines.

Copied to clipboard

Pengfei Cao, Xinyu Zuo, Yubo Chen, Kang Liu, Jun Zhao, Yuguang Chen, Weihua Peng

Structured Data in NLP

Challenge:	Existing methods for identifying causal relations of events are limited . Existing approaches cannot handle well the problem, especially in the condition of lacking training data.
Approach:	They propose a Latent Structure Induction Network to integrate external structural knowledge into a causality reasoning task.
Outcome:	The proposed approach outperforms existing state-of-the-art methods on two widely used datasets.

Automatic ICD Coding via Interactive Shared Representation Networks with Self-distillation Mechanism (2021.acl-long)

Copied to clipboard

Tong Zhou, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao, Kun Niu, Weifeng Chong, Shengping Liu

RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment (2025.findings-acl)

Challenge:	Existing methods for ICD coding ignore the long-tail of code frequency or noisy clinical notes.
Approach:	They propose to use an interactive shared representation network to model code co-occurrences while focusing on the clinical note's noteworthy part and extract valuable information through a self-distillation learning mechanism to solve the long-tail problem.
Outcome:	The proposed model reduces the long-tail of code frequency and noise in clinical notes and extracts valuable information through a self-distillation learning mechanism.

Copied to clipboard

Zhuoran Jin, Hongbang Yuan, Tianyi Men, Pengfei Cao, Yubo Chen, Jiexin Xu, Huaijun Li, Xiaojian Jiang, Kang Liu, Jun Zhao

DTELS: Towards Dynamic Granularity of Timeline Summarization (2025.naacl-long)

Challenge:	Existing retrieval augmented language models often overlook effective alignment with human preferences.
Approach:	They propose a benchmark to evaluate RMs in retrieval augmented language models . they incorporate 18 RAG subsets, six retrievers, and 24 RALMs to increase diversity .
Outcome:	The proposed benchmark combines 18 RAG subsets, six retrievers, and 24 RALMs to increase diversity of data sources.

Copied to clipboard

Chenlong Zhang, Tong Zhou, Pengfei Cao, Zhuoran Jin, Yubo Chen, Kang Liu, Jun Zhao

Summarization

Challenge:	Existing timeline summarizations lack flexibility to meet diverse granularity needs . a fine-grained timeline showing the technical details is preferred for news topics .
Approach:	They propose a new paradigm to construct adaptive timelines based on user instructions or requirements.
Outcome:	The proposed timelines are informative and granularly consistent, but they struggle to generate consistent timelines.

From Signal Degradation to Computation Collapse: Uncovering the Two Failure Modes of LLM Quantization (2026.findings-acl)

Copied to clipboard

Chenxi Zhou, Pengfei Cao, Jiang Li, Bohan Yu, Jinyu Ye, Jun Zhao, Kang Liu

Challenge:	Existing research on PTQ spans three primary directions.
Approach:	They conduct a systematic analysis of post-training quantization failures using PTQ . they show that targeted repair can mitigate Signal Degradation but remains ineffective for Computation Collapse .
Outcome:	The proposed method mitigates Signal Degradation but remains ineffective for Computation Collapse.

Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning (2026.acl-long)

Copied to clipboard

Tianyi Men, Zhuoran Jin, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

Challenge:	Multimodal web agents are cost-efficient and privacy-preserving, but suffer from weak planning and limited cross-website generalization.
Approach:	They propose a method which autonomously explores environments to discover experiences and utilizes hindsight experience to synthesize strictly aligned, high-level training data.
Outcome:	The proposed method outperforms Qwen2.5-VL-32B model on real-world benchmarks and demonstrates that mastering low-level atomic skills does not guarantee high-level planning competence.

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

Copied to clipboard

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

Task-Stratified Knowledge Scaling Laws for Post-Training Quantized Large Language Models (2026.findings-acl)

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

Chenxi Zhou, Pengfei Cao, Jiang Li, Bohan Yu, Jinyu Ye, Jun Zhao, Kang Liu

InstructoR: Instructing Unsupervised Conversational Dense Retrieval with Large Language Models (2023.findings-emnlp)

Challenge:	Existing scaling laws focus on general performance, overlooking crucial fine-grained factors and how quantization differentially impacts diverse knowledge capabilities.
Approach:	They propose a framework that unifies model size, bit-width, and fine-grained factors into memorization, application, and reasoning.
Outcome:	The proposed framework shows strong fit and cross-architecture consistency on 293 different PTQ configurations.

Copied to clipboard

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

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

Challenge:	Existing methods for conversational retrieval only fine-tune on limited supervised data, making it difficult for the retriever to fully grasp the entire conversation.
Approach:	They propose a method to instruct unsupervised conversational dense retrieval with large language models (LLMs) they use supervised data to discover the user's query intent from the conversation context .
Outcome:	The proposed method can bring significant improvements across various ad-hoc retrievers, surpassing the current state-of-the-art method.

Copied to clipboard

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

Cracking Factual Knowledge: A Comprehensive Analysis of Degenerate Knowledge Neurons in Large Language Models (2025.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

Yuheng Chen, Pengfei Cao, Yubo Chen, Yining Wang, Shengping Liu, Kang Liu, Jun Zhao

Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing (2025.acl-long)

Challenge:	Large language models (LLMs) are believed to store extensive factual knowledge, yet the mechanisms of knowledge storage in LLMs remain largely unexplored.
Approach:	They propose that some multi-layer perceptron neurons can store "knowledge".
Outcome:	The proposed model can store "knowledge" in multi-layer perceptron neurons, but not redundancy.

Copied to clipboard

Jiakuan Xie, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

Challenge:	Existing knowledge editing algorithms are prone to generating original knowledge . despite the fact that many models achieve near-perfect performance, superficial editing remains a challenge .
Approach:	They propose to use "superficial editing" to describe the phenomenon . they investigate the internal mechanisms of the attention module and their corresponding left singular vectors .
Outcome:	The proposed method can modify specific knowledge in a pretrained large language model while ensuring that unrelated knowledge remains unaffected.

Lightweight Haar Wavelet Subband Pruning for LLMs (2026.findings-acl)

Copied to clipboard

Jiang Li, Pengfei Cao, Chenxi Zhou, Tian Lan, Xiangdong Su, Kang Liu, Jun Zhao, Guanglai Gao

Challenge:	Large language models (LLMs) have impressive performance but require computational and memory resources.
Approach:	They propose a post-training framework that uses a Haar wavelet transform to prune weights.
Outcome:	The proposed pruning framework reduces pruning time and computational costs by removing less important weights while preserving model architecture.

A Good Neighbor, A Found Treasure: Mining Treasured Neighbors for Knowledge Graph Entity Typing (2022.emnlp-main)

Copied to clipboard

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

Structured Data in NLP

Challenge:	Existing methods to infer missing types for knowledge graphs only leverage one-hop neighbor information of the central entity, ignoring multi-hop neighbors that can provide valuable clues for inference.
Approach:	They propose a method to infer missing types for knowledge graph entities by using neighbor information and co-occurrence relations between types.
Outcome:	The proposed method significantly outperforms existing state-of-the-art methods on two widely used datasets.

Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statement (2021.findings-acl)

Copied to clipboard

Xinyu Zuo, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao, Weihua Peng, Yuguang Chen

Representation Learning

Challenge:	Existing methods for event causality identification (ECI) rely on labeled data, but the scale of annotated datasets is limited.
Approach:	They propose a self-supervised framework to learn context-specific causal patterns from external causal statements and adopt a contrastive transfer strategy to incorporate the learned context- specific causal patterns into the target ECI model.
Outcome:	The proposed method significantly outperforms existing methods on EventSto-ryLine and Causal-TimeBank (+2.0 and +3.4 points on F1 value respectively).

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

M2Edit: Locate and Edit Multi-Granularity Knowledge in Multimodal Large Language Model (2025.emnlp-main)

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

Yang Zhou, Pengfei Cao, Yubo Chen, Qingbin Liu, Dianbo Sui, Xi Chen, Kang Liu, Jun Zhao

Conjoin after Decompose: Improving Few-Shot Performance of Named Entity Recognition (2024.lrec-main)

Challenge:	Existing knowledge editing methods for MLLMs lack multi-granularity knowledge . existing knowledge editing approaches lack multimodality knowledge and generalize to multimodal data.
Approach:	They propose a multimodal knowledge editing method which integrates key knowledge layers within MLLMs and collaboratively edits them.
Outcome:	The proposed method improves visual generality performance on knowledge data of different granularities.

Copied to clipboard

Chengcheng Han, Renyu Zhu, Jun Kuang, Fengjiao Chen, Xiang Li, Ming Gao, Xuezhi Cao, Yunsen Xian

Generative Calibration for In-context Learning (2023.findings-emnlp)

Challenge:	Existing prompt-based NER models fail to detect entity boundaries, causing performance degradation.
Approach:	They propose a model which consists of a BART encoder and a parabiotic decoder and propose ' boundary expansion strategy' to enhance the model's capability in entity type classification.
Outcome:	The proposed model can achieve significant performance gains over state-of-the-art models.

Copied to clipboard

Zhongtao Jiang, Yuanzhe Zhang, Cao Liu, Jun Zhao, Kang Liu

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

Challenge:	In-context learning is one of the most exciting features of large language models . performance is sensitive to various configurations of the prompt, such as the choice or order of the training examples.
Approach:	They propose to calibrate the in-context predictive distribution by adjusting the label marginal . they find that the proposed method outperforms the ICL and state-of-the-art calibration methods .
Outcome:	The proposed method outperforms state-of-the-art methods by 27% absolute in macro-F1.

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.

Speed Up Your Code: Progressive Code Acceleration Through Bidirectional Tree Editing (2025.acl-long)

Copied to clipboard

Longhui Zhang, Jiahao Wang, Meishan Zhang, GaoXiong Cao, Ensheng Shi, Mayuchi Mayuchi, Jun Yu, Honghai Liu, Jing Li, Min Zhang

Programming Languages in NLP

Challenge:	Existing training methods, such as direct instruction fine-tuning, overlook hierarchical relationships among acceleration patterns.
Approach:	They propose a new training paradigm that uses bidirectional tree editing and progressive code acceleration learning to improve LLMs’ CA capabilities.
Outcome:	The proposed training paradigm outperforms prompt-enhanced GPT-4 and current training-based methods on average across five programming languages.

Adversarial Transfer Learning for Chinese Named Entity Recognition with Self-Attention Mechanism (D18-1)

Copied to clipboard

Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao, Shengping Liu

Robustness in NLP

Challenge:	Existing methods for named entity recognition (NER) do not exploit word boundary information from CWS or cannot filter the specific information of CWS.
Approach:	They propose to exploit task-shared boundary information to make full use of Chinese NER task and Chinese word segmentation (CWS) .
Outcome:	The proposed model significantly outperforms other state-of-the-art methods on two widely used datasets.

Evaluating Personalized Tool-Augmented LLMs from the Perspectives of Personalization and Proactivity (2025.acl-long)

Copied to clipboard

Yupu Hao, Pengfei Cao, Zhuoran Jin, Huanxuan Liao, Yubo Chen, Kang Liu, Jun Zhao

Challenge:	Personalized tool utilization is essential for aligning large language models (LLMs) with user preference in interaction scenarios with various tools.
Approach:	They propose a key-point-based LLM evaluation method that mitigates biases by manually annotating key points for each test case and providing them to LLM as the reference.
Outcome:	The proposed method mitigates biases in the LLM-as-a-judge system by manually annotating key points for each test case and providing them to LLM as the reference.

Leros: Learning Explicit Reasoning on Synthesized Data for Commonsense Question Answering (2024.lrec-main)

Copied to clipboard

Chenhao Wang, Pengfei Cao, Jiachun Li, Yubo Chen, Kang Liu, Xiaojian Jiang, Jiexin Xu, Li Qiuxia, Jun Zhao

BeautifulPrompt: Towards Automatic Prompt Engineering for Text-to-Image Synthesis (2023.emnlp-industry)

Challenge:	Recent work shows large language models can generate useful rationales for commonsense question answering (CQA) however, the cost of deployment and further tuning is relatively expensive for the large models.
Approach:	They propose a framework that leverages both knowledge graphs and large language models to synthesize rationale-augmented CQA data.
Outcome:	The proposed model can generate useful rationales on unseen CQA benchmarks.

Copied to clipboard

Tingfeng Cao, Chengyu Wang, Bingyan Liu, Ziheng Wu, Jinhui Zhu, Jun Huang

Mobile-R1: Towards Interactive Capability for VLM-Based Mobile Agent via Systematic Training (2026.acl-long)

Challenge:	Recent text-to-image models require multiple passes of prompt engineering by humans to produce satisfactory results for real-world applications.
Approach:	They propose a deep generative model to generate high-quality prompts from raw descriptions using visual feedback.
Outcome:	The proposed model produces high-quality prompts from simple raw descriptions . it can be integrated to a cloud-native AI platform to provide better image generation service in the cloud.

Copied to clipboard

Jihao Gu, Qihang Ai, Yingyao Wang, Pi Bu, Jingxuan Xing, Yue Cao, Zekun Zhu, Wei Jiang, Ziming Wang, Yingxiu Zhao, Ming-Liang Zhang, Jun Song, Yuning Jiang, Bo Zheng

Representative Demonstration Selection for In-Context Learning with Two-Stage Determinantal Point Process (2023.emnlp-main)

Challenge:	Existing approaches to training agents for visual-language models trap them in local optima, hindering exploration and error correction with the environment.
Approach:	They propose a hierarchical training recipe that bridges atomic action execution and strategic task completion.
Outcome:	The proposed training recipe bridges atomic action execution and strategic task completion.

Copied to clipboard

Zhao Yang, Yuanzhe Zhang, Dianbo Sui, Cao Liu, Jun Zhao, Kang Liu

Learning Kernel-Smoothed Machine Translation with Retrieved Examples (2021.emnlp-main)

Challenge:	Existing methods tend to select different demonstrations for each test instance, which is time-consuming and poses limitations in practical scenarios.
Approach:	They propose to select a representative subset of in-context demonstrations that can prompt different test instances in a specific task.
Outcome:	The proposed method can be used to generate representative in-context demonstrations.

Copied to clipboard

Qingnan Jiang, Mingxuan Wang, Jun Cao, Shanbo Cheng, Shujian Huang, Lei Li

Machine Translation

Challenge:	Existing methods to update deployed models are prone to overfit . however, non-parametric methods are liable to over-fit the retrieved examples .
Approach:	They propose to learn Kernel-Smoothed Translation with Example Retrieval (KSTER) this approach allows users to adapt models to emerging cases without retraining .
Outcome:	The proposed approach achieves 1.1 to 1.5 BLEU scores over existing methods without retraining . the proposed model is released on https://github.com/jiangqn/KSTER.

The Knowledge Microscope: Features as Better Analytical Lenses than Neurons (2025.acl-long)

Copied to clipboard

Yuheng Chen, Pengfei Cao, Kang Liu, Jun Zhao