Papers by Kun Zhou

Domain Adaptive Dialog Generation via Meta Learning (P19-1)

Challenge:	Large pre-trained Vision-Language Models (VLMs) have revolutionized downstream vision-language tasks including classification, object detection, and segmentation.
Approach:	They propose to search for text prompts at the word level rather than optimizing continuous textual embeddings to boost adversarial robustness.
Outcome:	Experiments show that the proposed method outperforms hand-engineered prompts with average gains of +4.9% and +5.8%.

Copied to clipboard

Kun Qian, Zhou Yu

HSDreport: Heart Sound Diagnosis with Echocardiography Reports (2024.findings-emnlp)

Challenge:	Existing methods to adapt dialog data to new domains with limited resources are expensive . a domain adaptive dialog system model learns from multiple rich-resource tasks and adapts to new tasks with minimal training samples.
Approach:	They propose a domain adaptive dialog generation method based on meta-learning . they train a dialog system model using multiple rich-resource single-domain dialog data .
Outcome:	The proposed method can learn a competitive dialog system on a new domain with minimal training examples.

Copied to clipboard

Zihan Zhao, Pingjie Wang, Liudan Zhao, Yuchen Yang, Ya Zhang, Kun Sun, Xin Sun, Xin Zhou, Yu Wang, Yanfeng Wang

Challenge:	Existing methods for heart sound diagnosis are limited to a few fixed categories and do not utilize echocardiography reports, the gold standard in the diagnosis of related diseases.
Approach:	They propose a benchmark that mandates the direct utilization of heart sounds obtained from auscultation to predict echocardiography reports.
Outcome:	The proposed method outperforms existing methods and existing multimodal LLMs in detecting key abnormalities in heart sounds.

Backdoor Collapse: Eliminating Unknown Threats Via Known Backdoor Aggregation In Language Models (2026.acl-long)

Copied to clipboard

Liang Lin, Miao Yu, Moayad Aloqaily, Zhenhong Zhou, Kun Wang, Linsey Pang, Prakhar Mehrotra, Qingsong Wen

Enhancing Adversarial Transferability in Visual-Language Pre-training Models via Local Shuffle and Sample-based Attack (2025.findings-naacl)

Challenge:	Existing defenses rely on impractical assumptions about trigger settings to mitigate backdoor attacks . a recent study found that small amounts of training data can systematically induce harmful behaviors in large language models.
Approach:	They propose a backdoor defense framework that requires no prior knowledge of trigger settings . they use a two-stage process to aggregate backdoor representations and fine-tune recovery .
Outcome:	The proposed defense reduces the average Attack Success Rate to 4.41% across multiple benchmarks . the proposed framework generalizes across different types of backdoors, confirming its robustness in practical deployment scenarios.

Copied to clipboard

Xin Liu, Aoyang Zhou, Kun He

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference (2025.findings-acl)

Challenge:	Visual-Language Pre-training (VLP) models are vulnerable to adversarial examples . previous studies have focused on improving adversariality of models .
Approach:	They propose a local shuffle and sample-based attack that randomly shufts one of the local image blocks and generates adversarial images and samples around them.
Outcome:	The proposed attack outperforms other advanced attacks on Large Vision-Language Models and outperformed previous attacks on Visual-Langue Pre-training models.

Copied to clipboard

Ping Gong, Jiawei Yi, Shengnan Wang, Juncheng Zhang, Zewen Jin, Ouxiang Zhou, Ruibo Liu, Guanbin Xu, Youhui Bai, Bowen Ye, Kun Yuan, Tong Yang, Gong Zhang, Renhai Chen, Feng Wu, Cheng Li

Green & Sustainable NLP

Challenge:	Existing top-k attention methods struggle to strike a balance between efficiency and accuracy.
Approach:	They propose a top-k attention approach that integrates low-overhead techniques into the Top-k Attention process to achieve 7.2 speedup compared to vanilla full attention.
Outcome:	The proposed approach achieves 7.2 speedup compared to current top-k attention methods while maintaining model accuracy.

Text Embedding as Treatment: A Meta Causal Approach for Robust Sentiment Classification (2026.findings-acl)

Copied to clipboard

Fengxiang Cheng, Chuan Zhou, Xiang Li, Haoxuan Li, Wen-li Wang, Jinkun Chen, Mingming Gong, Kun Zhang

Information Extraction & Text Mining

Challenge:	Existing methods for sentiment classification use binary treatment of words . Existing approaches limit generalizability to novel words and low-frequency words if there is a word in a sentence that is not treated .
Approach:	They propose a meta-causal approach that uses a single training task to identify causal words for arbitrary words.
Outcome:	The proposed method reduces the spurious correlation between word treatment and sentiment classification by removing words with low treatment effects from a pre-trained language model.

Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models (2026.acl-long)

Copied to clipboard

Yanbin Yin, Kun Zhou, Zhen Wang, Xiangdong Zhang, Yifei Shao, Shibo Hao, Yi Gu, Jieyuan Liu, Somanshu Singla, Tianyang Liu, Eric P. Xing, Zhengzhong Liu, Haojian Jin, Zhiting Hu

TexSmart: A System for Enhanced Natural Language Understanding (2021.acl-demo)

Challenge:	closed-ended question-based benchmarks struggle with saturation as newer models emerge . crowd-sourced leaderboards rely on costly and slow human judges .
Approach:	They propose a framework that leverages collective intelligence from all large language models to evaluate each other.
Outcome:	a new framework enables a democratic, pairwise evaluation of all large language models . it achieves 97% correlation with human judgements, while significantly reducing the cost.

Copied to clipboard

Lemao Liu, Haisong Zhang, Haiyun Jiang, Yangming Li, Enbo Zhao, Kun Xu, Linfeng Song, Suncong Zheng, Botong Zhou, Dick Zhu, Xiao Feng, Tao Chen, Tao Yang, Dong Yu, Feng Zhang, ZhanHui Kang, Shuming Shi

Information Extraction & Text Mining

Challenge:	TexSmart supports fine-grained named entity recognition (NER) Large-scale fine-granular entity types are expected to provide richer semantic information for downstream NLP applications.
Approach:	They introduce TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities.
Outcome:	The proposed system supports fine-grained named entity recognition (NER) and enhanced semantic analysis functions.

C-World: A Computer Use Agent Environment Creator (2026.acl-long)

Copied to clipboard

Ziqiao Xi, Shuang Liang, Qi Liu, Jiaqing Zhang, Letian Peng, Fang Nan, Meshal Nayim, Tianhui Zhang, Rishika Mundada, Lianhui Qin, Biwei Huang, Kun Zhou

Challenge:	C-World enables users to build agent environments on demand.
Approach:	They propose a system that enables users to build agent environments on demand.
Outcome:	The proposed system outperforms baselines on 119k samples and achieves Spearman = 0.883 ranking correlation with real execution.

Diffusion-NAT: Self-Prompting Discrete Diffusion for Non-Autoregressive Text Generation (2024.eacl-long)

Copied to clipboard

Kun Zhou, Yifan Li, Xin Zhao, Ji-Rong Wen

A Unified Framework for Synaesthesia Analysis (2023.findings-emnlp)

Challenge:	Existing non-autoregressive (NAR) text-to-text generation methods are unable to generate coherent and fluent texts due to discrete nature of text.
Approach:	They propose to integrate discrete diffusion models (DDM) into NAR text-to-text generation and integrate BART to improve the performance.
Outcome:	The proposed method outperforms competing methods and surpasses autoregressive methods on 7 datasets.

Copied to clipboard

Kun Sheng, Zhongqing Wang, Qingqing Zhao, Xiaotong Jiang, Guodong Zhou

Cognitive Modeling

Challenge:	Synaesthesia is a cognitive phenomenon structuring human thought and action, which makes understanding it challenging.
Approach:	They propose a framework for annotating synaesthetic elements and exploring their relationship . they propose to include sensory modalities, cues and stimuli in the framework .
Outcome:	The proposed framework yields state-of-the-art results, demonstrating its effectiveness.

Debiased Contrastive Learning of Unsupervised Sentence Representations (2022.acl-long)

Copied to clipboard

Kun Zhou, Beichen Zhang, Xin Zhao, Ji-Rong Wen

Enhancing Chain-of-Thought Reasoning via Neuron Activation Differential Analysis (2025.emnlp-main)

Challenge:	Recent studies have shown that contrastive learning improves pre-trained language models to derive high-quality sentence representations.
Approach:	They propose a framework to punish false negatives and generate noise-based negatives to guarantee the uniformity of the representation space.
Outcome:	The proposed framework improves pre-trained language models while pushing apart irrelevant negatives to guarantee the uniformity of the representation space.

Copied to clipboard

Yiru Tang, Kun Zhou, Yingqian Min, Xin Zhao, Jing Sha, Zhichao Sheng, Shijin Wang

Evaluating Object Hallucination in Large Vision-Language Models (2023.emnlp-main)

Challenge:	Existing studies focus on optimizing external components of CoT, but lack internal explanations for the quality of the model's outputs.
Approach:	They propose an efficient method to identify reasoning-critical neurons by analyzing their activation patterns under reasoning chains of varying quality.
Outcome:	The proposed method shows that neurons in the feed-forward layers are critical in the generation of high-quality reasoning chains.

Copied to clipboard

Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Xin Zhao, Ji-Rong Wen

CommonLID: Re-evaluating State-of-the-Art Language Identification Performance on Web Data (2026.acl-long)

Challenge:	Large vision-language models (LVLMs) suffer from object hallucinations, i.e., they tend to generate objects inconsistent with the target images in the descriptions.
Approach:	They propose to integrate powerful large vision-language models (LVLMs) they propose a polling-based query method to evaluate object hallucination .
Outcome:	The proposed model can evaluate object hallucination in a more stable and flexible way.

Copied to clipboard

Pedro Ortiz Suarez, Laurie Burchell, Catherine Arnett, Rafael Mosquera, Sara Hincapié Monsalve, Thom Vaughan, Damian Stewart, Malte Ostendorff, Idris Abdulmumin, Vukosi Marivate, Shamsuddeen Hassan Muhammad, Atnafu Lambebo Tonja, Hend Al-Khalifa, Nadia Ghezaiel Hammouda, Verrah Akinyi Otiende, Tack Hwa Wong, Jakhongir Saydaliev, Melika Nobakhtian, Muhammad Ravi Shulthan Habibi, Chalamalasetti Kranti, Carol Muchemi, Khang Nguyen, Faisal Muhammad Adam, Luis Frentzen Salim, Reem Alqifari, Cynthia Jayne Amol, Joseph Marvin Imperial, Ilker Kesen, Ahmad Mustafid, Pavel Stepachev, Leshem Choshen, David Anugraha, Hamada Nayel, Seid Muhie Yimam, Vallerie Alexandra Putra, My Chiffon Nguyen, Azmine Toushik Wasi, Gouthami Vadithya, Rob Van Der Goot, Lanwenn ar C’horr, Karan Dua, Andrew Yates, Mithil Bangera, Yeshil Bangera, Hitesh Laxmichand Patel, Shu Okabe, Fenal Ashokbhai Ilasariya, Dmitry Gaynullin, Genta Indra Winata, Yiyuan Li, Juan Pablo Martínez, Amit Agarwal, Ikhlasul Akmal Hanif, Raia Abu Ahmad, Esther Adenuga, Filbert Aurelian Tjiaranata, Weerayut Buaphet, Michael Anugraha, Sowmya Vajjala, Benjamin L Rice, Azril Hafizi Amirudin, Jesujoba Oluwadara Alabi, Srikant Panda, Yassine Toughrai, Bruhan Kyomuhendo, Daniel Ruffinelli, null Akshata, Manuel Goulão, Ej Zhou, Ingrid Gabriela Franco Ramirez, Cristina Aggazzotti, Konstantin Dobler, Jun Kevin, Quentin Pagès, Nicholas Andrews, Nuhu Ibrahim, Mattes Ruckdeschel, Amr Keleg, Mike Zhang, Casper Rufaro Muziri, Saron Samuel, Sotaro Takeshita, Kun Kerdthaisong, Luca Foppiano, Rasul Dent, Tommaso Green, Ahmad Mustapha Wali, Kamohelo Makaaka, Vicky Feliren, Inshirah Idris, Hande Celikkanat, Abdulhamid Abubakar, Jean Maillard, Benoît Sagot, Thibault Clérice, Kenton Murray, Sarah K. K. Luger

Text Classification

Challenge:	Language identification (LID) is a fundamental step in curating multilingual corpora.
Approach:	They introduce CommonLID, a community-driven, human-annotated LID benchmark for the web domain, covering 109 languages.
Outcome:	The proposed benchmark covers 109 languages and shows that existing evaluations overestimate accuracy for many languages in the web domain.

StructGPT: A General Framework for Large Language Model to Reason over Structured Data (2023.emnlp-main)

Copied to clipboard

Jinhao Jiang, Kun Zhou, Zican Dong, Keming Ye, Xin Zhao, Ji-Rong Wen

DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing (2026.findings-acl)

Challenge:	Experiments conducted on three types of structured data show that StructGPT greatly improves the performance of LLMs.
Approach:	They propose an iterative Reading-then-Reasoning framework to solve question answering tasks based on structured data.
Outcome:	The proposed framework improves the reasoning ability of large language models over structured data under the few-shot and zero-shot settings.

Copied to clipboard

Hongzhi Zhang, Yuanze Hu, Tinghai Zhang, Jia Fu, Tao Wang, Junwei Jing, Zhaoxin Fan, Wei Bi, Ruiming Tang, Han Li, Guorui Zhou, Kun Gai

Information Retrieval

Challenge:	Large Language Models (LLMs) are evolving towards autonomous agents . retrieval capabilities are well-benchmarked, but post-retrieval synthesis is under-evaluated due to open-ended writing.
Approach:	They propose a benchmark to evaluate information consolidation capabilities using survey papers as gold standards.
Outcome:	The proposed benchmark analyzes the post-retrieval synthesis stage of large language models . it leverages high-quality survey papers as gold standards and reverse-engineers research requests . the proposed benchmark outperforms single-turn generation and reduces hallucinations .

From Graph to Word Bag: Introducing Domain Knowledge to Confusing Charge Prediction (2024.lrec-main)

Copied to clipboard

Ang Li, Qiangchao Chen, Yiquan Wu, Xiang Zhou, Kun Kuang, Fei Wu, Ming Cai

Structured Data in NLP

Challenge:	Existing charge prediction methods have shown impressive performance, but they face significant challenges when dealing with confusing charges, such as Snatch and Robbery.
Approach:	They propose a novel approach which introduces domain knowledge regarding constituent elements to guide the model in making judgments on confusing charges, much like a judge’s reasoning process.
Outcome:	The proposed approach maintains exceptional performance in imbalanced label distributions.

CR-GIS: Improving Conversational Recommendation via Goal-aware Interest Sequence Modeling (2022.coling-1)

Copied to clipboard

Jinfeng Zhou, Bo Wang, Zhitong Yang, Dongming Zhao, Kun Huang, Ruifang He, Yuexian Hou

Small Pre-trained Language Models Can be Fine-tuned as Large Models via Over-Parameterization (2023.acl-long)

Challenge:	Existing methods to determine a goal item by sequentially tracking users’ interests ignore the rich goal-aware implicit interest sequence patterns in a dialog.
Approach:	They propose to model goal-aware implicit user interest sequence patterns in a dialog and a hierarchical Star Transformer to guide multi-turn utterances generation.
Outcome:	The proposed framework achieves more accurate recommendations with more fluent and coherent dialog utterances.

Copied to clipboard

Ze-Feng Gao, Kun Zhou, Peiyu Liu, Wayne Xin Zhao, Ji-Rong Wen

Learn with Noisy Data via Unsupervised Loss Correction for Weakly Supervised Reading Comprehension (2020.coling-main)

Challenge:	Large pre-trained language models (PLMs) have shown remarkable performance in various natural language processing tasks, outperforming small PLMs by a large margin.
Approach:	They propose to scale up parameters of pre-trained language models only during fine-tuning to benefit from over-parameterization.
Outcome:	The proposed approach can significantly boost the fine-tuning performance of small PLMs and even help small PDMs outperform 3 parameterized larger ones.

Copied to clipboard

Xuemiao Zhang, Kun Zhou, Sirui Wang, Fuzheng Zhang, Zhongyuan Wang, Junfei Liu

Sparse Black-Box Multimodal Attack for Vision-Language Adversary Generation (2023.findings-emnlp)

Challenge:	Existing approaches to filter noise for machine reading comprehension (MRC) are difficult to control and introduce noisy data.
Approach:	They propose a hierarchical loss correction strategy to avoid fitting noise and enhance clean supervision signals by using an unsupervisedly fitted Gaussian mixture model and a hard bootstrapping loss method.
Outcome:	The proposed methods can help improve models significantly on weakly supervised machine reading comprehension datasets.

Copied to clipboard

Zhen Yu, Zhou Qin, Zhenhua Chen, Meihui Lian, Haojun Fu, Weigao Wen, Hui Xue, Kun He

KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph (2025.acl-long)

Challenge:	Existing adversarial attacks using imperceptible perturbations are challenging to simulate . e-commerce product restrictions and hate speech monitoring are examples of such attacks .
Approach:	They propose a black-box adversarial attack that leverages sparse perturbations to simulate adversarials exhibited by illegal merchants in the black- box scenario.
Outcome:	The proposed method outperforms existing attacks and unimodal attacks by treating images and text in discrete space and outperforming existing models.

Copied to clipboard

Jinhao Jiang, Kun Zhou, Xin Zhao, Yang Song, Chen Zhu, Hengshu Zhu, Ji-Rong Wen

Knowledge Representation

Challenge:	Existing methods to design the interaction strategy between large language models and knowledge graphs (KGs) are not effective for large language model (LLM)s to solve complex tasks due to the large volume and structured format of KG data.
Approach:	They propose an LLM-based agent framework that enables small LLMs to actively make decisions over knowledge graphs.
Outcome:	The proposed framework outperforms existing methods on in-domain and out-domain datasets using 10K samples.

KRLS: Improving End-to-End Response Generation in Task Oriented Dialog with Reinforced Keywords Learning (2023.emnlp-main)

Copied to clipboard

Xiao Yu, Qingyang Wu, Kun Qian, Zhou Yu

Mem2ActBench: A Benchmark for Evaluating Long-Term Memory Utilization in Task-Oriented Autonomous Agents (2026.acl-long)

Challenge:	Task-oriented dialogs (TOD) require a model to generate a response that optimizes for task-related metrics.
Approach:	They propose a faster generation procedure that samples from independent next-word distributions and introduce a fine-grained reward function to help the model focus on learning key information in a dialog.
Outcome:	The proposed algorithm achieves state-of-the-art performance on an offline task with 15% training time reduction compared to a standard RL algorithm using auto-regressive generation.

Copied to clipboard

Yiting Shen, Kun Li, Wei Zhou, Songlin Hu

Challenge:	Existing benchmarks focus on direct queries for a factual answer, but fail to evaluate the more crucial capability of actively applying memory to execute tasks.
Approach:	They propose a benchmark to evaluate whether agents can proactively leverage long-term memory to execute tool-based actions by selecting appropriate tools and grounding their parameters.
Outcome:	The proposed benchmarks show that 91.3% of tasks are memory-dependent . the benchmarks simulate persistent assistant usage, where users mention the same topic across long, interrupted interactions and expect previously established preferences and task states to be implicitly applied.

Hybrid Self-evolving Structured Memory for Computer-Use Agents (2026.findings-acl)

Copied to clipboard

Sibo Zhu, Wenyi WU, Kun Zhou, Stephen Wang, Biwei Huang

MeaeQ: Mount Model Extraction Attacks with Efficient Queries (2023.emnlp-main)

Challenge:	despite advances in vision–language models, real-world computer-use tasks remain challenging due to long-horizon workflows, diverse interfaces, and frequent intermediate errors.
Approach:	They propose a graph-based memory that couples discrete symbolic nodes with continuous trajectory embeddings.
Outcome:	The proposed system outperforms closed-source models in Qwen2.5-VL-7B and Gemini2.5-Pro-Vision on desktop and mobile platforms.

Copied to clipboard

Chengwei Dai, Minxuan Lv, Kun Li, Wei Zhou

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

Challenge:	Recent studies focus on limited-query budget settings and adopt random sampling or active learning-based sampling strategies on publicly available, unannotated data sources.
Approach:	They propose a model extraction attack with efficient Queries that uses a zero-shot sequence inference classifier to filter task-relevant data from a public text corpus instead of a problem domain-specific dataset.
Outcome:	The proposed method achieves higher similarity to the victim model than baselines while requiring fewer queries.

Copied to clipboard

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

DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent (2025.findings-emnlp)

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

Copied to clipboard

Pengyu Zhu, Zhenhong Zhou, Yuanhe Zhang, Shilinlu Yan, Kun Wang, Sen Su

DATA-CUBE: Data Curriculum for Instruction-based Sentence Representation Learning (2024.findings-acl)

Challenge:	a new method for detecting advanced backdoors is proposed to bypass safety audits.
Approach:	They propose a backdoor implantation strategy that introduces dynamic encryption to bypass safety audits.
Outcome:	The proposed method achieves an attack success rate approaching 100% while maintaining a detection rate of 0%.

Copied to clipboard

Yingqian Min, Kun Zhou, Dawei Gao, Xin Zhao, He Hu, Yaliang Li

Improve Student’s Reasoning Generalizability through Cascading Decomposed CoTs Distillation (2024.emnlp-main)

Challenge:	Existing methods to improve sentence representation learning (SRL) ignore the potential interference problems across tasks and instances.
Approach:	They propose a multi-task instruction tuning method that arranges the order of multi- task data for training to minimize interference risks.
Outcome:	The proposed method can boost the performance of state-of-the-art methods.

Copied to clipboard

Chengwei Dai, Kun Li, Wei Zhou, Songlin Hu

Beyond the Last Frame: Process-aware Evaluation for Generative Video Reasoning (2026.acl-long)

Challenge:	Existing studies have tried to distill these capabilities into smaller language models (SLMs) however, these capabilities are often associated with more parameters, which is not practical to emergent in smaller models.
Approach:	They propose to decompose the traditional single-step learning process into two cascaded learning steps by restructuring the training objectives and concatenating the question with the rationale as input.
Outcome:	Extensive experiments show that the proposed method improves reasoning generalizability and diversity of the model.

Copied to clipboard

Yifan Li, YuKai Gu, Yingqian Min, Zikang Liu, Yifan Du, Kun Zhou, Min Yang, Xin Zhao, Minghui Qiu

RSA-Bench: Benchmarking Audio Large Models in Real-World Acoustic Scenarios (2026.findings-acl)

Challenge:	Existing evaluation frameworks often rely on single-frame assessments, which can lead to outcome-hacking.
Approach:	They propose a process-aware evaluation paradigm that uses a hierarchical rubric to evaluate the validity of the intermediate steps and the final result.
Outcome:	The proposed model achieves POC@1.0 only about 20% and exhibits significant outcome-hacking.

Copied to clipboard

Yibo Zhang, Kaiwen Luo, Liang Lin, Shilinlu Yan, Jin Wang, Yaoqi Guo, Yitian Chen, Yalan Qin, Zhenhong Zhou, Kun Wang, Li Sun

AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving (2025.findings-emnlp)

Challenge:	Existing evaluations rely on synthetic Gaussian noise or simplistic single-source interference, failing to capture the intricate, multi-layered acoustic dynamics that characterize authentic physical environments.
Approach:	They propose a robustness benchmark to stress-test Audio Large Models (ALLMs) using high-fidelity auditory scene simulations.
Outcome:	The proposed model performs well on a wide range of tasks, including automatic speech recognition, speech translation, and audio-based reasoning.

Copied to clipboard

Kangan Qian, Sicong Jiang, Yang Zhong, Ziang Luo, Zilin Huang, Tianze Zhu, Kun Jiang, Mengmeng Yang, Zheng Fu, Jinyu Miao, Yining Shi, He Zhe Lim, Li Liu, Tianbao Zhou, Hongyi Wang, Huang Yu, Yifei Hu, Guang Li, Guang Chen, Hao Ye, Lijun Sun, Diange Yang

LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild (2024.findings-acl)

Challenge:	Vision-Language Models struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning.
Approach:	AgentThink integrates Chain-of-Thought reasoning with dynamic, agent-style tool invocation for autonomous driving tasks.
Outcome:	Experiments on the DriveLMM-o1 benchmark show AgentThink significantly boosts overall reasoning scores by 53.91% and enhances answer accuracy by 33.54% .

Copied to clipboard

Ziyu Zhao, Leilei Gan, Guoyin Wang, Wangchunshu Zhou, Hongxia Yang, Kun Kuang, Fei Wu

Great~Truths~are ~Always ~Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models (2022.findings-naacl)

Challenge:	Low-Rank Adaptation (LoRA) is an effective yet efficient solution for fine-tuning large language models.
Approach:	They propose a low-rank Adaptation framework that retrieves and composes multiple LoRAs according to input prompts.
Outcome:	Experimental results show that LoraRetriever outperforms baselines in terms of performance and versatility.

Copied to clipboard

Jinhao Jiang, Kun Zhou, Ji-Rong Wen, Xin Zhao

Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models (2021.emnlp-main)

Challenge:	Existing approaches to enhance pre-trained language models (PTMs) with a knowledge-aware graph neural network (GNN) encoder that models a commonsense knowledge graph (CSKG) can't explain how external knowledge resources improve the reasoning capacity of PTMs.
Approach:	They propose to use relation features from CSKGs to enhance the reasoning capacity of pre-trained language models (PTMs) by encoding a commonsense knowledge graph (CSKG)
Outcome:	The proposed approach reduces the parameters for encoding CSKGs and improves on five benchmarks.

Copied to clipboard

Kun Zhou, Wayne Xin Zhao, Sirui Wang, Fuzheng Zhang, Wei Wu, Ji-Rong Wen

Control Image Captioning Spatially and Temporally (2021.acl-long)

Challenge:	Recent studies have shown that powerful pre-trained language models can be fooled by small perturbations or intentional attacks.
Approach:	They propose a framework for fine-tuning PLMs using a masked language model and Gaussian noise to augment semantically relevant examples with sufficient diversity.
Outcome:	The proposed framework improves the robustness of pre-trained language models and alleviates performance degradation under adversarial attacks.

Copied to clipboard

Kun Yan, Lei Ji, Huaishao Luo, Ming Zhou, Nan Duan, Shuai Ma

Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs (2024.acl-long)

Challenge:	Existing methods to generate image captions with user intention are still under exploration.
Approach:	They propose a model that connects Contrastive constraints and Attention Guidance in a loop manner and engages explicit spatial and temporal constraints to the generating process.
Outcome:	The proposed model improves performance on a trace-controlled image captioning task.

Copied to clipboard

Bilgehan Sel, Priya Shanmugasundaram, Mohammad Kachuee, Kun Zhou, Ruoxi Jia, Ming Jin

Database Search Results Disambiguation for Task-Oriented Dialog Systems (2022.naacl-main)

Challenge:	Large Language Models (LLMs) have shown remarkable capabilities in tasks such as summarization, arithmetic reasoning, and question answering.
Approach:	They propose a framework that explores decisions’ consequences from multiple stakeholder perspectives and a SKIG framework to enhance moral reasoning in large language models.
Outcome:	The proposed framework exhibits marked improvements compared to baselines across different language models and benchmarks.

Copied to clipboard

Kun Qian, Satwik Kottur, Ahmad Beirami, Shahin Shayandeh, Paul Crook, Alborz Geramifard, Zhou Yu, Chinnadhurai Sankar

Information Retrieval

Challenge:	Task-oriented dialog systems can't handle multiplesearch results when querying a database due to the lack of such scenarios in existing datasets.
Approach:	They propose a task that focuses on disambiguating database search results by synthetically generating turns through a pre-defined grammar and collecting human paraphrases for a subset.
Outcome:	The proposed task improves performance on DSR-disambiguation even in the absence of in-domain data, suggesting it can be learned as a universal dialog skill.

CRSLab: An Open-Source Toolkit for Building Conversational Recommender System (2021.acl-demo)

Copied to clipboard

Kun Zhou, Xiaolei Wang, Yuanhang Zhou, Chenzhan Shang, Yuan Cheng, Wayne Xin Zhao, Yaliang Li, Ji-Rong Wen

Capture the Key in Reasoning to Enhance CoT Distillation Generalization (2025.acl-long)

Challenge:	Existing studies on conversational recommender systems lack a unified and standardized implementation or comparison.
Approach:	They propose to use a unified framework and highly-decoupled modules to develop CRSs.
Outcome:	The proposed framework collects 6 commonly used human-annotated CRS datasets and implements 19 models that include advanced techniques such as graph neural networks and pre-training models.

Copied to clipboard

Chengwei Dai, Kun Li, Wei Zhou, Songlin Hu

DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI (2024.findings-eacl)

Challenge:	Existing distillation methods for Large Language Models (LLMs) focus on fine-tuning student SLMs on correct data, resulting in students struggling to learn the key instead of analyzing mistakes according to correct solutions.
Approach:	They propose a method that exposes key reasoning steps rather than simple fine-tuning students' CoTs data by using a set of prompts with similar reasoning paths but divergent conclusions.
Outcome:	The proposed method improves student SLMs' ability to learn key reasoning steps rather than fine-tuning them on teacher data.

Copied to clipboard

Jianguo Zhang, Kun Qian, Zhiwei Liu, Shelby Heinecke, Rui Meng, Ye Liu, Zhou Yu, Huan Wang, Silvio Savarese, Caiming Xiong

TIU-Bench: A Benchmark for Evaluating Large Multimodal Models on Text-rich Image Understanding (2025.findings-emnlp)

Challenge:	DialogStudio is the largest and most diverse collection of dialogue datasets . existing datasets lack diversity and comprehensiveness, authors say .
Approach:	They introduce DialogStudio: the largest and most diverse collection of dialogue datasets . DialogStuio aggregates more than 80 diverse dialogue dataset .
Outcome:	a new dataset is created to improve the quality and diversity of dialogue datasets . DialogStudio is the largest and most diverse collection of dialogue data .

Copied to clipboard

Kun Zhang, Liqiang Niu, Zhen Cao, Fandong Meng, Jie Zhou

Reinforcement Learning on Pre-Training Data (2026.acl-long)

Challenge:	Existing text-rich image understanding benchmarks lack scale and fragmented scenarios . a new full-image structured output format is proposed to enable fine-grained evaluation of perception and reasoning capabilities.
Approach:	They propose a large-scale, multilingual benchmark that includes over 100,000 annotations and 22,000 question-answer pairs.
Outcome:	The proposed framework provides a comprehensive platform for developing and evaluating next-generation multimodal AI systems.

Copied to clipboard

Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Kun Li, Haoyuan Wu, null Wujiajia, Zihao Zheng, Chenchen Zhang, Kun Shi, Xue Gong, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang xu, Zheng Fang, Shuai LI, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bochao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Bo Zhou, Di Wang

DECOR: Improving Coherence in L2 English Writing with a Novel Benchmark for Incoherence Detection, Reasoning, and Rewriting (2024.emnlp-main)

Challenge:	Recent progress in large language models is driven by scaling of training compute through pre-training with nexttoken prediction (NTP) or post-training (RL) Pre-training using NTP enables models to acquire extensive knowledge and skills from general data, but it suffers from data inefficiency and catastrophic forgetting in continual learning settings.
Approach:	They propose to scale training compute through pre-training with next-token prediction (NTP) or post-training by scaling reinforcement learning (RL) to improve learning from general data.
Outcome:	Experiments on multiple benchmarks and models show that the proposed approach improves continual pre-training and provides a strong foundation for post-training on Qwen3-8B-Base.

Copied to clipboard

Xuanming Zhang, Anthony Diaz, Zixun Chen, Qingyang Wu, Kun Qian, Erik Voss, Zhou Yu

Text Generation

Challenge:	Existing automated writing evaluation systems only detect incoherence in writing . a recent study has found that incorporating specific reasons for incohence improves the quality of rewrites .
Approach:	They propose a benchmark that includes expert annotations for detecting incoherence in L2 English writing, identifying the underlying reasons, and rewriting the incoerent sentences.
Outcome:	The proposed benchmark improves coherence in L2 English writing by fine-tuning models . the authors find that incorporating specific reasons improves quality of rewrites .

RexUIE: A Recursive Method with Explicit Schema Instructor for Universal Information Extraction (2023.findings-emnlp)

Copied to clipboard

Chengyuan Liu, Fubang Zhao, Yangyang Kang, Jingyuan Zhang, Xiang Zhou, Changlong Sun, Kun Kuang, Fei Wu

Information Extraction & Text Mining

Challenge:	Named Entity Recognition (NER) and Relation Extraction (RE) models have limited success when extracting general schemas such as quadruples and quintuples.
Approach:	They propose a formal formulation that covers almost all extraction schemas and a Recursive Method with Explicit Schema Instructor for UIE.
Outcome:	The proposed method shows strong performance under full-shot and few-shot settings and achieves state-of-the-art results on the tasks of extracting complex schemas.

ViFT: Towards Visual Instruction-Free Fine-tuning for Large Vision-Language Models (2025.findings-emnlp)

Copied to clipboard

Zikang Liu, Kun Zhou, Xin Zhao, Dawei Gao, Yaliang Li, Ji-Rong Wen

TopKG: Target-oriented Dialog via Global Planning on Knowledge Graph (2022.coling-1)

Challenge:	Visual instruction tuning is the predominant technology in eliciting multimodal task-solving capabilities of large vision-language models.
Approach:	They propose a visual instruction-free fine-tuning framework for large vision-language models . they require only text-only instructions and image caption data during training .
Outcome:	The proposed framework is based on visual instruction tuning, but requires images as input . it can achieve state-of-the-art performance on several downstream benchmarks with less training data.

Copied to clipboard

Zhitong Yang, Bo Wang, Jinfeng Zhou, Yue Tan, Dongming Zhao, Kun Huang, Ruifang He, Yuexian Hou

How to Build User Simulators to Train RL-based Dialog Systems (D19-1)

Challenge:	Existing target-oriented dialogs take a local and greedy strategy for response generation, where global planning is absent.
Approach:	They propose a global planning method for target-oriented dialog on a commonsense knowledge graph to adjust local response generation towards the global target.
Outcome:	The proposed method can reach the target with a higher success rate, fewer turns, and more coherent responses.

Copied to clipboard

Weiyan Shi, Kun Qian, Xuewei Wang, Zhou Yu

Landmark Embedding: A Chunking-Free Embedding Method For Retrieval Augmented Long-Context Large Language Models (2024.acl-long)

Challenge:	RL-based dialog systems require interaction with the environment and obtaining real human users to interact with the system is time-consuming and labor-intensive.
Approach:	They propose a method to standardize user simulator building to compare dialog system quality using the same set of user simulators.
Outcome:	The proposed method can be used by the community to compare dialog system quality using the same set of user simulators fairly.

Copied to clipboard

Kun Luo, Zheng Liu, Shitao Xiao, Tong Zhou, Yubo Chen, Jun Zhao, Kang Liu

Deploying Multi-task Online Server with Large Language Model (2025.coling-industry)

Challenge:	Existing methods for retrieval augmentation work with chunked contexts, which leads to poor quality of semantic representation and incomplete retrieval of useful information.
Approach:	They propose a method for retrieval augmentation of long-context language modeling using landmark embedding.
Outcome:	The proposed method outperforms existing retrieval methods with a notable advantage.

Copied to clipboard

Yincen Qu, Hengyue Liu, Kun Wang, Xiangying Dai, Xiaoou Lu, Hui Zhou, Chao Ma

Extracting and Combining Abilities For Building Multi-lingual Ability-enhanced Large Language Models (2025.emnlp-main)

Challenge:	In the industry, numerous natural language processing tasks are deployed online . traditional approaches tackle each task separately by its own network and pipeline .
Approach:	They propose a three-stage multi-task learning framework for large language models . it involves task filtering, fine-tuning on high-resource tasks, and finally fine- tuning on all tasks .
Outcome:	The proposed framework reduces up to 90% of overhead while reducing latency and resource usage.

Copied to clipboard

Zhipeng Chen, Kun Zhou, Liang Song, Xin Zhao, Bingning Wang, Weipeng Chen, Ji-Rong Wen

YuLan-Mini: Pushing the Limits of Open Data-efficient Language Model (2025.acl-long)

Challenge:	Existing work relies on training with multi-lingual ability-related data, which may not be available for low-resource languages.
Approach:	They propose a multi-lingual ability-enhanced LLM that extracts language-agnostic ability-related weights from LLMs and combine them across different languages by simple addition and subtraction operations without training.
Outcome:	The proposed approach extracts language-agnostic ability-related weights from LLMs and combine them across different languages without training.

Copied to clipboard

Hu Yiwen, Huatong Song, Jie Chen, Jia Deng, Jiapeng Wang, Kun Zhou, Yutao Zhu, Jinhao Jiang, Zican Dong, Yang Lu, Xu Miao, Xin Zhao, Ji-Rong Wen

Automatic Slide Updating with User-Defined Dynamic Templates and Natural Language Instructions (2026.findings-acl)

Challenge:	prevailing pre-training approaches for large language models involve several complexities.
Approach:	They propose a low-cost training recipe and a robust optimization approach to mitigate training instability . they also propose synthesis, curriculum, and data selection pipelines to integrate data .
Outcome:	The proposed model achieves top-tier performance among models with similar parameter scale . it is comparable to industry-leading models that require significantly more data .

Copied to clipboard

Kun Zhou, Jiakai He, Wenmian Yang, Zhensheng Wang, Yiquan Zhang, Weijia Jia

Challenge:	Existing automation methods follow fixed template filling and cannot support dynamic updates for diverse, user-authored decks.
Approach:	They propose a framework that combines multimodal slide parsing, natural language instruction grounding, and tool-augmented reasoning for tables, charts, and textual conclusions.
Outcome:	The proposed framework updates content while preserving layout and style while maintaining a strong reference baseline on DynaSlide.

Precedent-Enhanced Legal Judgment Prediction with LLM and Domain-Model Collaboration (2023.emnlp-main)

Copied to clipboard

Yiquan Wu, Siying Zhou, Yifei Liu, Weiming Lu, Xiaozhong Liu, Yating Zhang, Changlong Sun, Fei Wu, Kun Kuang

Green & Sustainable NLP

Challenge:	Recent advances in deep learning have enabled a variety of techniques to be used to solve the LJP task.
Approach:	They propose a framework that leverages the strength of both LLMs and domain-specific models in the context of precedents.
Outcome:	The proposed framework leverages the strength of both LLM and domain models in the context of precedents.

SimANS: Simple Ambiguous Negatives Sampling for Dense Text Retrieval (2022.emnlp-industry)

Copied to clipboard

Kun Zhou, Yeyun Gong, Xiao Liu, Wayne Xin Zhao, Yelong Shen, Anlei Dong, Jingwen Lu, Rangan Majumder, Ji-rong Wen, Nan Duan

Information Retrieval

Challenge:	Existing methods for sapping negatives from large document pool suffer from the uninformative or false negative problem.
Approach:	They propose a method to sample negatives from a large document pool using a new sampling probability distribution.
Outcome:	The proposed method can be used to sample more ambiguous negatives on four public and one industry datasets.

CT-GAT: Cross-Task Generative Adversarial Attack based on Transferability (2023.emnlp-main)

Copied to clipboard

Minxuan Lv, Chengwei Dai, Kun Li, Wei Zhou, Songlin Hu

Unsupervised Context Rewriting for Open Domain Conversation (D19-1)

Challenge:	Neural network models are vulnerable to adversarial examples, and current methods based on adversarially transferable models rely on substitute models, which can be impractical and costly in real-world scenarios due to the unavailability of training data and the victim model’s structural details.
Approach:	They propose a novel approach that directly constructs adversarial examples by extracting transferable features across various tasks.
Outcome:	The proposed approach achieves superior attack performance with small cost on ten datasets and demonstrates that it is a novel approach.

Copied to clipboard

Kun Zhou, Kai Zhang, Yu Wu, Shujie Liu, Jingsong Yu

Text Generation

Challenge:	Existing approaches to model conversation context have drawbacks, such as lack of coreferences and long dependency.
Approach:	They propose a context rewriting method which explicitly rewrites the last utterance by considering context history.
Outcome:	The proposed method outperforms baselines in terms of rewriting quality, multi-turn response generation, and end-to-end retrieval-based chatbots.

DORA: Dynamic Optimization Prompt for Continuous Reflection of LLM-based Agent (2025.coling-main)

Copied to clipboard

Kun Li, Tingzhang Zhao, Wei Zhou, Songlin Hu

RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution (2025.emnlp-main)

Challenge:	Existing studies have shown that reflection can enhance performance, but our investigation reveals an undesirable pattern in reflection framework: effective self-reflection occurs primarily at the beginning of iterations, with subsequent attempts failing to produce further improvements.
Approach:	They propose a framework that generates task-adaptive reflection advice using an external open-source small language model.
Outcome:	The proposed framework generates task-adaptive and diverse reflection advice in MiniWoB++ and Alfworld environments.

Copied to clipboard

Jiahui Li, Lin Li, Tai-Wei Chang, Kun Kuang, Long Chen, Jun Zhou, Cheng Yang

Memformer: A Memory-Augmented Transformer for Sequence Modeling (2022.findings-aacl)

Challenge:	Experimental results demonstrate the superiority of our approach to aligning large language models with human preferences.
Approach:	They propose a method that evaluates and assigns specific credit to each token using an off-the-shelf reward model.
Outcome:	The proposed method evaluates and assigns specific credit to each token using an off-the-shelf reward model.

Copied to clipboard

Qingyang Wu, Zhenzhong Lan, Kun Qian, Jing Gu, Alborz Geramifard, Zhou Yu

Bottom-Up Synthesis of Knowledge-Grounded Task-Oriented Dialogues with Iteratively Self-Refined Prompts (2025.naacl-short)

Challenge:	Experimental results show that Memformer uses 8.1x less memory space and 3.2x faster on inference.
Approach:	They propose an efficient neural network that utilizes an external dynamic memory to encode and retrieve past information.
Outcome:	The proposed model achieves comparable performance against baselines with 8.1x less memory space and 3.2x faster on inference.

Copied to clipboard

Kun Qian, Maximillian Chen, Siyan Li, Arpit Sharma, Zhou Yu

Discovery and Reinforcement of Tool-Integrated Reasoning Chains via Rollout Trees (2026.acl-long)

Challenge:	Training conversational question-answering systems requires in-domain data, which is often scarce in practice.
Approach:	They propose a bottom-up approach where QA pairs are generated first and combined into a coherent dialogue.
Outcome:	The proposed approach produces more realistic and higher-quality dialogues compared to top-down methods.

Copied to clipboard

Kun Li, Zenan Xu, Junan Li, Zengrui Jin, Jinghao Deng, Zexuan Qiu, Bo Zhou

ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation (2025.findings-emnlp)

Challenge:	Existing approaches to augment Large Language Models (LLMs) with computational capabilities have focused on short Chain-of-thought (CoT) integrating tool-use into long CoT remains underexplored due to the scarcity of training data and the challenge of integrating it without compromising the model’s intrinsic long-chain reasoning.
Approach:	They propose a framework that enables spontaneous tool-use during long CoT reasoning without additional human annotation.
Outcome:	Experiments on AIME and GPQA-Diamond show that DART significantly outperforms existing methods, successfully harmonizing tool execution with long CoT reasoning.

Copied to clipboard

Siying Zhou, Yiquan Wu, Hui Chen, Xueyu Hu, Kun Kuang, Adam Jatowt, Chunyan Zheng, Fei Wu

Challenge:	Currently, legal claims are not being used by non-professionals.
Approach:	They construct a dataset for Chinese legal claim generation task and then use it to evaluate the generated claims.
Outcome:	The proposed dataset is the first for the Chinese legal claim generation task and will be made publicly available.

Towards Effective and Efficient Continual Pre-training of Large Language Models (2025.acl-long)

Copied to clipboard

Jie Chen, Zhipeng Chen, Jiapeng Wang, Kun Zhou, Yutao Zhu, Jinhao Jiang, Yingqian Min, Xin Zhao, Zhicheng Dou, Jiaxin Mao, Yankai Lin, Ruihua Song, Jun Xu, Xu Chen, Rui Yan, Zhewei Wei, Di Hu, Wenbing Huang, Ji-Rong Wen

CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning (2026.acl-long)

Challenge:	Continual pre-training (CPT) has been an important approach for adapting language models to specific domains or tasks.
Approach:	They propose a Continual pre-training method that can greatly improve Chinese language ability and scientific reasoning ability of LLMs.
Outcome:	The proposed method can greatly improve Chinese language ability and scientific reasoning ability of LLMs.

Copied to clipboard

Zhenpeng Su, Leiyu Pan, Minxuan Lv, Yuntao Li, Wenping Hu, Fuzheng Zhang, Kun Gai, Guorui Zhou

Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Tracking (2023.findings-eacl)

Challenge:	Existing methods for proximal policy optimization discard valuable gradient signals from low-probability tokens due to the clipping mechanism.
Approach:	They propose an algorithm that reintroduces gradients from clipped tokens in native PPO in a gentle and bounded manner.
Outcome:	The proposed algorithm outperforms strong baselines on reasoning benchmarks on different model scales.

Copied to clipboard

Derek Chen, Kun Qian, Zhou Yu

Optimizing Language Models with Fair and Stable Reward Composition in Reinforcement Learning (2024.emnlp-main)

Challenge:	Prompt-based methods with large pre-trained language models have shown impressive unaided performance across many NLP tasks.
Approach:	They propose a meta-learning scheme to stabilize the ability of the model to perform well under various prompts and introduce a saliency model to limit dialogue text length.
Outcome:	The proposed model improves on large pre-trained language models with labeled in-context exemplars and can be used to generate more exemplar queries.

Copied to clipboard

Jiahui Li, Hanlin Zhang, Fengda Zhang, Tai-Wei Chang, Kun Kuang, Long Chen, Jun Zhou

ODTQA-FoRe: An Open-Domain Tabular Question Answering Dataset for Future Data Forecasting and Reasoning (2026.findings-acl)

Challenge:	Recent research has developed algorithms for reinforcement learning from human feedback and AI-generated feedback.
Approach:	They propose a method for reinforcement learning from human feedback and AI-generated feedback that incorporates weighting, ranking, and constraining to handle disparate rewards.
Outcome:	The proposed method reduces disparity and enhances stability among rewards . empirical results show that the proposed method is efficient and straightforward .

Copied to clipboard

Zhensheng Wang, Xiaole Liu, Wenmian Yang, Kun Zhou, Yiquan Zhang, Weijia Jia

Continual Pre-training of Language Models for Math Problem Understanding with Syntax-Aware Memory Network (2022.acl-long)

Challenge:	Existing tabular question answering systems cannot perform future-oriented numerical prediction . open-domain tabular questions are a popular approach for QA tasks .
Approach:	They propose a task that covers time-series forecasting and forecast-based reasoning scenarios using real estate data.
Outcome:	The proposed framework decomposes the problem into three collaborative roles that synthesize the results to construct a precise and consistent final answer.

Copied to clipboard

Zheng Gong, Kun Zhou, Xin Zhao, Jing Sha, Shijin Wang, Ji-Rong Wen

HearSay Benchmark: Do Audio LLMs Leak What They Hear? (2026.findings-acl)

Challenge:	a fundamental challenge in modeling math problems is how to fuse semantics of textual description and formulas.
Approach:	They propose a method to continually pre-train language models for improving understanding of math problems with syntax-aware memory networks.
Outcome:	The proposed approach outperforms competitive baselines on four math tasks.

Copied to clipboard

Jin Wang, Kaiwen Luo, Liang Lin, Weiliu Wang, Yitian Chen, Moayad Aloqaily, Xuehai Tang, Zhenhong Zhou, Kun Wang, Li Sun, Qingsong Wen

Towards Topic-Guided Conversational Recommender System (2020.coling-main)

Challenge:	Recent advances in audio large language models have led to their potential privacy implications unexplored.
Approach:	They propose a benchmark to examine whether ALLMs leak user privacy through acoustic voiceprints.
Outcome:	The proposed benchmark is constructed from over 22,000 real-world audio clips.

Copied to clipboard

Kun Zhou, Yuanhang Zhou, Wayne Xin Zhao, Xiaoke Wang, Ji-Rong Wen

Improving Open-Domain Dialogue Systems via Multi-Turn Incomplete Utterance Restoration (D19-1)

Challenge:	Existing CRS datasets focus on immediate requests from users, while lack proactive guidance to the recommendation scenario.
Approach:	They propose a topic-guided conversational recommendation dataset . it incorporates topic threads to enforce natural semantic transitions towards the recommendation scenario .
Outcome:	The proposed approach is more reasonable and controllable than previous approaches.

Copied to clipboard

Zhufeng Pan, Kun Bai, Yan Wang, Lianqiang Zhou, Xiaojiang Liu

Deriving Character Logic from Storyline as Codified Decision Trees (2026.acl-long)

Challenge:	Experimental results show that restoring incomplete utterances from context improves the performance of open-domain dialogue systems.
Approach:	They propose to use a dataset to restore incomplete utterances from context . they propose to pick and combine the data to restore the incomplete .
Outcome:	The proposed model significantly boosts response quality of open-domain dialogue systems.

Copied to clipboard

Letian Peng, Kun Zhou, Longfei Yun, Yupeng Hou, Jingbo Shang

Challenge:	Existing behavioral profiles are unstructured, weakly validated, and unusable . existing models are weakly valid, leading to brittle agent behavior . Using codified decision trees, we show that CDT outperforms previous methods .
Approach:	They propose a data-driven framework that induces an executable decision structure from narrative data.
Outcome:	The proposed framework outperforms human-written profiles and prior profiles on multiple benchmarks.

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

Copied to clipboard

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

A General Knowledge Injection Framework for ICD Coding (2025.findings-acl)

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

Copied to clipboard

Xu Zhang, Kun Zhang, Wenxin Ma, Rongsheng Wang, Chenxu Wu, Yingtai Li, S Kevin Zhou

Challenge:	Existing methods to improve ICD coding focus on a single type of knowledge and design specialized modules that are complex and incompatible with each other.
Approach:	They propose a general knowledge injection framework that integrates three key types of knowledge without specialized design of additional modules.
Outcome:	The proposed framework outperforms baseline models and is comparable to models relying on extra human annotations.

DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs (2025.emnlp-main)

Copied to clipboard

Minxuan Lv, Zhenpeng Su, Leiyu Pan, Yizhe Xiong, Zijia Lin, Hui Chen, Wei Zhou, Jungong Han, Guiguang Ding, Wenwu Ou, Di Zhang, Kun Gai, Songlin Hu

ODUTQA-MDC: A Task for Open-Domain Underspecified Tabular QA with Multi-turn Dialogue-based Clarification (2026.acl-long)

Challenge:	Existing sparsification methods like pruning can lose model knowledge through parameter removal.
Approach:	They propose a novel approach that achieves sparsification by partitioning pre-trained FFN layers into computational blocks.
Outcome:	The proposed approach achieves superior performance across language modeling and downstream tasks under equivalent computational constraints.

Copied to clipboard

Zhensheng Wang, ZhanTeng Lin, Wenmian Yang, Kun Zhou, Yiquan Zhang, Weijia Jia

Chain-of-Quizzes: Pedagogy-inspired Example Selection in In-Context-Learning (2024.findings-acl)

Challenge:	Existing approaches to tabular QA are limited to closed-domain scenarios . existing approaches do not solve the core challenge of generating correct answers without user clarification .
Approach:	They propose a benchmark to tackle underspecified or uncertain queries in tabular question answering . they propose ODUTQA-MDC task and a multi-agent framework to detect ambiguities .
Outcome:	The proposed framework excels at detecting ambiguities, clarifying them through dialogue, and refining answers.

Copied to clipboard

Yiquan Wu, Anlai Zhou, Yuhang Liu, Yifei Liu, Adam Jatowt, Weiming Lu, Jun Xiao, Kun Kuang

Low-Resource NLP

Challenge:	In-context learning (ICL) is a powerful tool for enhancing large language models (LLMs) by mimicking the human learning process.
Approach:	They propose a Chain-of-Quizzes framework that uses LLMs to answer a quiz to sift 'good' examples, combine them iteratively with the increasing complexity, and utilize a final exam to gauge the combined example chains.
Outcome:	The proposed framework outperforms baseline models on diverse reasoning datasets and shows that it is scalable and can be used in future research.

ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Models (2023.findings-emnlp)

Copied to clipboard

Zhipeng Chen, Kun Zhou, Beichen Zhang, Zheng Gong, Xin Zhao, Ji-Rong Wen

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

Challenge:	Large language models (LLMs) have excellent performance in evaluation benchmarks, but struggle in complex reasoning tasks.
Approach:	They propose a tool-augmented chain-of-thought reasoning framework for chat-based LLMs . they model chain- of-thoughting reasoning as multi-turn conversations to utilize tools .
Outcome:	The proposed framework can outperform state-of-the-art models on complex reasoning tasks.

Copied to clipboard

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

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

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

Copied to clipboard

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

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

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

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

Latent Learningscape Guided In-context Learning (2024.findings-acl)

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

Anlai Zhou, Sunshine Jiang, Yifei Liu, Yiquan Wu, Kun Kuang, Jun Xiao

Legal Judgment Prediction based on Knowledge-enhanced Multi-Task and Multi-Label Text Classification (2025.naacl-long)

Challenge:	Existing methods to select demonstrations based on surface-level semantic similarities fall short of identifying the most fitting ones.
Approach:	They propose a method that characterizes latent learningscape features of demonstrations and uses them to create more effective prompts.
Outcome:	The proposed method outperforms leading models in arithmetic, commonsense, and symbolic reasoning tasks showing an average increase in scores by 7.4 percentage points.

Copied to clipboard

Ang Li, Yiquan Wu, Ming Cai, Adam Jatowt, Xiang Zhou, Weiming Lu, Changlong Sun, Fei Wu, Kun Kuang

Dynamic Simulation Framework for Disinformation Dissemination and Correction With Social Bots (2025.findings-emnlp)

Challenge:	Legal judgment prediction (LJP) is an essential task for legal AI, aiming at predicting judgments based on the facts of a case.
Approach:	They propose a knowledge-enhanced approach that incorporates 'label-level knowledge' to enhance the representation of case facts for each task and 'task-level' knowledge to improve synergy.
Outcome:	The proposed method is effective in comparison to state-of-the-art (SOTA) baselines.

Copied to clipboard

Boyu Qiao, Kun Li, Wei Zhou, Songlin Hu

LLMBox: A Comprehensive Library for Large Language Models (2024.acl-demos)

Challenge:	Current studies rely on simplistic user and network modeling and neglect dynamic behavior of bots.
Approach:	They propose a multi-agent-based framework for disinformation dissemination . it incorporates both malicious and legitimate bots and allows quantitative evaluation of correction strategies.
Outcome:	The proposed framework incorporates both malicious and legitimate bots and their controlled dynamic participation allows for quantitative analysis of correction strategies.

Copied to clipboard

Tianyi Tang, Hu Yiwen, Bingqian Li, Wenyang Luo, ZiJing Qin, Haoxiang Sun, Jiapeng Wang, Shiyi Xu, Xiaoxue Cheng, Geyang Guo, Han Peng, Bowen Zheng, Yiru Tang, Yingqian Min, Yushuo Chen, Jie Chen, Ranchi Zhao, Luran Ding, Yuhao Wang, Zican Dong, Xia Chunxuan, Junyi Li, Kun Zhou, Xin Zhao, Ji-Rong Wen

Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement Learning (2026.findings-acl)

Challenge:	a library to facilitate the development, use, and evaluation of large language models (LLMs) is presented.
Approach:	They propose a unified library to facilitate the development, use and evaluation of large language models (LLMs).
Outcome:	The proposed library is based on extensive experiments in a variety of evaluation settings.

Copied to clipboard

Zhenpeng Su, Leiyu Pan, Minxuan Lv, Tiehua Mei, Zijia Lin, Yuntao Li, Wenping Hu, Ruiming Tang, Kun Gai, Guorui Zhou

Unleashing the Native Recommendation Potential: LLM-Based Generative Recommendation via Structured Term Identifiers (2026.findings-acl)

Challenge:	Large language model post-training often adopts an off-policy training paradigm . however, the off-poliicy training model introduces distribution shifts that push the policy beyond the trust region.
Approach:	They propose to use the entropy ratio as a global metric to measure the relative change in policy exploration throughout updates.
Outcome:	Experiments show that the proposed metric improves performance across multiple benchmarks.

Copied to clipboard

Zhiyang Zhang, Junda She, Kuo Cai, Bo Chen, Shiyao Wang, Xinchen Luo, Qiang Luo, Ruiming Tang, Han Li, Kun Gai, Guorui Zhou

OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use (2025.acl-long)

Challenge:	Existing methods for constructing item identifiers face bottlenecks due to their large output space and expensive vocabulary expansion and alignment training.
Approach:	They propose to use Large Language Models to develop general-purpose, semantically-aware recommender systems that can be generalized and reusable.
Outcome:	Experiments on real-world datasets show that GRAM outperforms baselines and significantly outperformed baselines.

Copied to clipboard

Xueyu Hu, Tao Xiong, Biao Yi, Zishu Wei, Ruixuan Xiao, Yurun Chen, Jiasheng Ye, Meiling Tao, Xiangxin Zhou, Ziyu Zhao, Yuhuai Li, Shengze Xu, Shenzhi Wang, Xinchen Xu, Shuofei Qiao, Zhaokai Wang, Kun Kuang, Tieyong Zeng, Liang Wang, Jiwei Li, Yuchen Eleanor Jiang, Wangchunshu Zhou, Guoyin Wang, Keting Yin, Zhou Zhao, Hongxia Yang, Fan Wu, Shengyu Zhang, Fei Wu

ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph (2023.emnlp-main)

Challenge:	a new generation of (M)LLMs is enabling the creation of superintelligent AI assistants . OS Agents can complete tasks autonomously and have the potential to significantly enhance the lives of billions of users worldwide.
Approach:	They propose to build OS Agents that operate within operating systems' GUIs and GUIs . they examine evaluation metrics and benchmarks to identify promising directions .
Outcome:	The proposed agents are based on operating systems (OS) and operating systems frameworks.

Copied to clipboard

Jinhao Jiang, Kun Zhou, Xin Zhao, Yaliang Li, Ji-Rong Wen

What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning (2025.coling-main)

Challenge:	Question Answering over Knowledge Graph (KGQA) aims to find answer entities for natural language questions based on knowledge graphs.
Approach:	They propose a subgraph-aware self-attention mechanism to imitate the graph neural network (GNN) based module to perform multi-hop reasoning on KG.
Outcome:	The proposed method surpasses state-of-the-art models by a large margin even with fewer updated parameters and less training data.

Copied to clipboard

Yifan Du, Hangyu Guo, Kun Zhou, Wayne Xin Zhao, Jinpeng Wang, Chuyuan Wang, Mingchen Cai, Ruihua Song, Ji-Rong Wen

Visually-augmented pretrained language models for NLP tasks without images (2023.acl-long)

Challenge:	Experimental results show that visual instruction tuning improves performance of Multi-modal Large Language Models (MLLMs) to extend the application scope of Large Language Modells, a surge of work augments LLMs with vision encoders to endow the ability of multi-modal cognition and reasoning.
Approach:	They propose a systematic approach to create high-quality visual reasoning instructions using a synthesize-complicate-reformulate paradigm.
Outcome:	The proposed method improves performance of MLLMs by 27.86% and 27.60% on MME-Perception and MME Cognition.

Copied to clipboard

Hangyu Guo, Kun Zhou, Wayne Xin Zhao, Qinyu Zhang, Ji-Rong Wen

OneRec-Think: In-Text Reasoning for Generative Recommendation (2026.acl-long)

Challenge:	Existing approaches to improve pre-trained language models lack visual commonsense and semantics.
Approach:	They propose a visual-augmented approach to fine-tune pre-trained language models by using retrieved or generated images instead of relying on explicit images.
Outcome:	The proposed approach outperforms baselines on ten tasks and consistently outperformed other approaches.

Copied to clipboard

Zhanyu Liu, Shiyao Wang, Xingmei Wang, Rongzhou Zhang, Jiaxin Deng, Honghui Bao, Jinghao Zhang, Wuchao Li, PengFei Zheng, Xiangyu Wu, Yifei Hu, Qigen Hu, Xinchen Luo, Lejian Ren, Zhang Zixing, Qianqian Wang, Kuo Cai, Yunfan Wu, Hongtao Cheng, Zexuan Cheng, Lu Ren, Huanjie Wang, Yi Su, Ruiming Tang, Kun Gai, Guorui Zhou

Aligning Recommendation and Conversation via Dual Imitation (2022.emnlp-main)

Challenge:	Existing generative models lack the capacity for explicit and controllable reasoning, a key advantage of LLMs.
Approach:	They propose a framework that integrates dialogue, reasoning, and personalized recommendation.
Outcome:	Experiments across public benchmarks show state-of-the-art performance.

Copied to clipboard

Jinfeng Zhou, Bo Wang, Minlie Huang, Dongming Zhao, Kun Huang, Ruifang He, Yuexian Hou

Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint (2024.findings-acl)

Challenge:	Existing conversational recommendation systems ignore the advantage of user interest shift in connecting recommendation and conversation, leading to an ineffective loose coupling structure.
Approach:	They propose a dual imitation to explicitly align recommendation and conversation paths . they propose to generate high-quality responses with accurate recommendations and coherent explanations .
Outcome:	The proposed model outperforms the state-of-the-art models on recommendation and conversation performance with automatic, human, and novel explainability metrics.

Copied to clipboard

Zhipeng Chen, Kun Zhou, Xin Zhao, Junchen Wan, Fuzheng Zhang, Di Zhang, Ji-Rong Wen

Not Everything is All You Need: Toward Low-Redundant Optimization for Large Language Model Alignment (2024.emnlp-main)

Challenge:	Existing reinforcement learning methods do not provide fine-grained supervision for complex reasoning tasks.
Approach:	They propose a reinforcement learning method that incorporates a generative model as the reward model and a token-level supervision model for RL training.
Outcome:	Experiments on 8 tasks show the proposed method is effective .

Copied to clipboard

Zhipeng Chen, Kun Zhou, Xin Zhao, Jingyuan Wang, Ji-Rong Wen

VarBench: Robust Language Model Benchmarking Through Dynamic Variable Perturbation (2024.findings-emnlp)

Challenge:	Experimental results show that large language models are struggling to align with human preference in complex tasks and scenarios.
Approach:	They propose a low-redundant alignment method that selects the top-10% most updated parameters in LLMs for alignment training.
Outcome:	The proposed method improves on 10 datasets and shows that it is redundant . it can be used to train LLMs on QA and ECQA datasets, but it is not feasible to test it on a large dataset.

Copied to clipboard

Kun Qian, Shunji Wan, Claudia Tang, Youzhi Wang, Xuanming Zhang, Maximillian Chen, Zhou Yu

CORBA: Contagious Recursive Blocking Attacks on Multi-Agent Systems Based on Large Language Models (2026.findings-acl)

Challenge:	Recent benchmarks release only training and validation sets, keeping the test set labels closed-source.
Approach:	They propose to extract variables from each test case and define a value range for each variable.
Outcome:	The proposed method improves the accuracy of the evaluations on four datasets covering mathematical generation and multiple-choice tasks.

Copied to clipboard

Zhenhong Zhou, Zherui Li, Jie Zhang, Yuanhe Zhang, Kun Wang, Yang Liu, Qing Guo

Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models (2024.acl-long)

Challenge:	Existing security models rely on open-ended communication, but the collaborative process itself can be exploited and disrupted.
Approach:	They propose a new threat class, called Denial-of-Collaboration, which corrupts collaborative structure and transforms communication topology into self-sabotage.
Outcome:	The proposed attacks bypass conventional safety alignments that are not designed to detect behavioral or systemic attacks.

Copied to clipboard

Yuchong Sun, Che Liu, Kun Zhou, Jinwen Huang, Ruihua Song, Xin Zhao, Fuzheng Zhang, Di Zhang, Kun Gai