Papers by Junjie Zhang

FinToolSyn: A forward synthesis Framework for Financial Tool-Use Dialogue Data with Dynamic Tool Retrieval (2026.findings-acl)

Challenge:	Current multimodal large language models (MLLMs) show limited understanding of dental images.
Approach:	They propose a dental-specialized multimodal large language model trained via staged multimodal alignment and reinforcement learning.
Outcome:	The proposed model outperforms state-of-the-art models on disease classification and dental VQA tasks.

Copied to clipboard

Caishuang Huang, Yang Qiao, Rongyu Zhang, Junjie Ye, Pu Lu, null Wuwenxi, Meng Zhou, Xiku Du, Qi Zhang, Tao Gui, Xuanjing Huang

From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection (2025.naacl-long)

Challenge:	Existing data synthesis methods rely on static tools to generate queries . this approach fails to capture the implicit, event-driven nature of real-world needs .
Approach:	They propose a forward synthesis framework to generate high-quality financial dialogues . they construct a repository of 43,066 tools and synthesize over 148k dialogue instances .
Outcome:	Experiments show that models trained on FinToolSyn achieve a 21.06% improvement . the framework is designed to generate high-quality financial dialogues .

Copied to clipboard

Rupeng Zhang, Haowei Wang, Junjie Wang, Mingyang Li, Yuekai Huang, Dandan Wang, Qing Wang

AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments (2026.acl-long)

Challenge:	Toolcalling has changed Large Language Model (LLM) applications by integrating external tools, but it also introduces new security vulnerabilities, particularly in the tool scheduling mechanisms of LLM, which have not been extensively studied.
Approach:	They propose a framework that exploits vulnerabilities in Large Language Models through adversarial tool injection to execute privacy theft, launch denial-of-service attacks, and manipulate business competition.
Outcome:	The proposed framework exploits vulnerabilities in LLM tool-calling systems through adversarial tool injection.

Copied to clipboard

Zhiheng Xi, Dingwen Yang, Jiaqi Liu, Jixuan Huang, Honglin Guo, Baodai Huang, Tinggang Chen, Qi Zhang, Zhonghang Lu, Chenyu Liu, Jiajun Sun, Jiazheng Zhang, Dingwei Zhu, Xin Guo, Junzhe Wang, Zhihao Zhang, Yuming Yang, Junjie Ye, Minghe Gao, Dongrui Liu, Jiaming Ji, Guohao Li, Tao Gui, Qi Zhang, Xuanjing Huang

Decorrelate Irrelevant, Purify Relevant: Overcome Textual Spurious Correlations from a Feature Perspective (2022.coling-1)

Challenge:	Existing benchmarks evaluate agents in simplified, idealized settings, relying on pre-packaged tool interfaces, overlooking critical steps, and assume inputs are clean and fully specified.
Approach:	They propose a framework that evaluates language agents in simplified, idealized settings . they show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 .
Outcome:	Experiments on 15 proprietary and open-source models show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 .

Copied to clipboard

Shihan Dou, Rui Zheng, Ting Wu, SongYang Gao, Junjie Shan, Qi Zhang, Yueming Wu, Xuanjing Huang

Causal Intervention Improves Implicit Sentiment Analysis (2022.coling-1)

Challenge:	Existing methods to debiase samples with biased features obstructs the model in learning from non-biased parts of the samples.
Approach:	They propose to eliminate spurious correlations in a fine-grained manner from a feature space perspective by using Random Fourier Features and weighted re-sampling to decorrelate dependencies between features.
Outcome:	The proposed method eliminates spurious correlations in a fine-grained manner from a feature space perspective.

Copied to clipboard

Siyin Wang, Jie Zhou, Changzhi Sun, Junjie Ye, Tao Gui, Qi Zhang, Xuanjing Huang

Sentiment Analysis

Challenge:	Existing neural models struggle with implicit sentiment analysis because they latch onto spurious correlations, resulting in poor generalization and robustness.
Approach:	They propose a CausaL intervention model for implicit sEntiment ANalysis using instrumental variable to eliminate confounding causal effects and extract the pure causal effect between sentence and sentiment.
Outcome:	The proposed model extracts the pure causal effect between sentence and sentiment using instrumental variable.

ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models (2024.emnlp-main)

Copied to clipboard

Yuxiang Zhang, Jing Chen, Junjie Wang, Yaxin Liu, Cheng Yang, Chufan Shi, Xinyu Zhu, Zihao Lin, Hanwen Wan, Yujiu Yang, Tetsuya Sakai, Tian Feng, Hayato Yamana

Improving Discriminative Capability of Reward Models in RLHF Using Contrastive Learning (2024.emnlp-main)

Challenge:	Currently, tool-augmented large language models (LLMs) only achieve total scores of 45.3 and 37.0, respectively, on a scale of 100.
Approach:	They propose a multi-level diagnostic process to assess the LLM's hallucinations through two perspectives: depth and breadth.
Outcome:	The proposed diagnostic process assesses the hallucinations of large language models through two perspectives: depth and breadth.

Copied to clipboard

Lu Chen, Rui Zheng, Binghai Wang, Senjie Jin, Caishuang Huang, Junjie Ye, Zhihao Zhang, Yuhao Zhou, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang

Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs (2024.findings-emnlp)

Challenge:	Current methods rely on ranking losses to teach reward model to assess preferences, but they are susceptible to noise and ambiguous data, often failing to deeply understand human intentions.
Approach:	They propose a method that incorporates contrastive learning into the reward modeling process to enhance generalization and stabilize the reinforcement learning training process.
Outcome:	The proposed method enhances generalization of the reward model, stabilizes the reinforcement learning training process, and improves the final alignment with human preferences.

Copied to clipboard

Junjie Wang, Mingyang Chen, Binbin Hu, Dan Yang, Ziqi Liu, Yue Shen, Peng Wei, Zhiqiang Zhang, Jinjie Gu, Jun Zhou, Jeff Pan, Wen Zhang, Huajun Chen

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

Challenge:	Recent studies have attempted to enhance the performance of large language models (LLMs) in complex question-answering (QA) tasks by combining step-wise planning with external retrieval.
Approach:	They propose a framework for enhancing LLMs’ planning capabilities by using planning data derived from knowledge graphs (KGs).
Outcome:	The proposed framework improves LLMs’ planning capabilities by using knowledge graphs (KGs) the proposed framework is compared with existing frameworks on multiple datasets and shows that it is effective for large language models.

Copied to clipboard

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

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

RATE-Nav: Region-Aware Termination Enhancement for Zero-shot Object Navigation with Vision-Language Models (2025.findings-acl)

Copied to clipboard

Junjie Li, Nan Zhang, Xiaoyang Qu, Kai Lu, Guokuan Li, Jiguang Wan, Jianzong Wang

TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities (2024.emnlp-main)

Challenge:	Object navigation is a fundamental task in embodied artificial intelligence.
Approach:	They propose a region-aware Termination-Enhanced method that incorporates visual language models and exploration rates to enable efficient termination.
Outcome:	The proposed method achieves a success rate of 67.8% and an SPL of 31.3% on the HM3D dataset.

Copied to clipboard

Ming Zhang, Caishuang Huang, Yilong Wu, Shichun Liu, Huiyuan Zheng, Yurui Dong, Yujiong Shen, Shihan Dou, Jun Zhao, Junjie Ye, Qi Zhang, Tao Gui, Xuanjing Huang

S2G-RAG: Structured Sufficiency and Gap Judging for Iterative Retrieval-Augmented QA (2026.acl-long)

Challenge:	Current datasets cater to user-led systems and are limited to predefined specific scenarios and slots.
Approach:	They propose to use a Chinese dialogue dataset to train a model that authentically simulates human-computer dialogues in 30 popular life service scenarios.
Outcome:	The proposed model achieves a joint accuracy of 75.09% in out-of-domain evaluations . it also achieves notable abilities in slot filling and questioning .

Copied to clipboard

Minghan Li, Junjie Zou, Xinxuan Lv, Chao Zhang, Guodong Zhou

Question Answering

Challenge:	Retrieval-augmented generation grounds language models in external evidence, but multi-hop question answering remains difficult . iterative pipelines must control what to retrieve next and when evidence is adequate.
Approach:	They propose an iterative framework with an explicit controller, S2G-Judge . they map structured gap items into the next retrieval query to produce stable retrieval trajectories .
Outcome:	Experiments on TriviaQA, HotpotQA, and 2WikiMultiHopQA show that S2G-RAG improves multi-hop QA performance and robustness under multi-turn retrieval.

JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs (2025.acl-long)

Copied to clipboard

Junjie Chu, Yugeng Liu, Ziqing Yang, Xinyue Shen, Michael Backes, Yang Zhang

Improving Relation Extraction with Relational Paraphrase Sentences (2020.coling-main)

Challenge:	Large language models (LLMs) have been used to mitigate misuse and to align with human values.
Approach:	They propose to use large-scale evaluations of various jailbreak attacks to identify key patterns and test them under eight advanced defenses.
Outcome:	The proposed attacks achieve high success rates but are easy to mitigate by defenses.

Copied to clipboard

Junjie Yu, Tong Zhu, Wenliang Chen, Wei Zhang, Min Zhang

ArchiDocGen: Multi-Agent Framework for Expository Document Generation in the Architectural Industry (2025.acl-industry)

Challenge:	Existing annotated data is expensive and non-scalable, limiting performance of relation extraction models.
Approach:	They propose to enrich relation expressions by relational paraphrase sentences by annotating human-annotated data.
Outcome:	The proposed model improves performance even on a strong baseline.

Copied to clipboard

Junjie Jiang, Haodong Wu, Yongqi Zhang, Songyue Guo, Bingcen Liu, Caleb Chen Cao, Ruizhe Shao, Chao Guan, Peng Xu, Lei Chen

Text Generation

Challenge:	drafting method statements is labor-intensive and time-consuming . traditional methods involve using static templates filled in manually by engineers .
Approach:	They propose a framework that automates method statement generation by using multi-agent collaboration.
Outcome:	The proposed framework achieves 4.38 ContentScore, excelling in specialization, completeness, organization, and clarity.

AdapterDistillation: Non-Destructive Task Composition with Knowledge Distillation (2023.emnlp-industry)

Copied to clipboard

Junjie Wang, Yicheng Chen, Wangshu Zhang, Sen Hu, Teng Xu, Jing Zheng

Green & Sustainable NLP

Challenge:	Recent work on learning from multiple tasks has shown that adding an extra fusion layer to implement knowledge composition is non-scalable for some applications.
Approach:	They propose a two-stage knowledge distillation algorithm to extract task specific knowledge by using local data to train a student adapter.
Outcome:	Experiments on frequently asked question retrieval in task-oriented dialog systems validate the efficiency of AdapterDistillation.

Multi-Task Reinforcement Learning for Enhanced Multimodal LLM-as-a-Judge (2026.acl-industry)

Copied to clipboard

Junjie Wu, Xuan Kan, Zihao He, Shunwen Tan, Bo Pan, Kaitai Zhang

A Survey of Post-Training Scaling in Large Language Models (2025.acl-long)

Challenge:	Existing MLLMs are optimized for single-task scenarios and struggle to generalize to diverse contexts.
Approach:	They propose a framework that integrates multitask reinforcement learning and generalization capabilities of MLLMs to optimize the judge model across multiple tasks.
Outcome:	The proposed framework outperforms baseline models in judgment consistency and correlation with human preferences.

Copied to clipboard

Hanyu Lai, Xiao Liu, Junjie Gao, Jiale Cheng, Zehan Qi, Yifan Xu, Shuntian Yao, Dan Zhang, Jinhua Du, Zhenyu Hou, Xin Lv, Minlie Huang, Yuxiao Dong, Jie Tang

MENTOR: Efficient Autoregressive Image Generation with Balanced Multimodal Control (2026.findings-acl)

Challenge:	Large language models (LLMs) have demonstrated proficiency in understanding and generating human natural languages.
Approach:	They propose a framework for scaling large language models using supervised fine-tuning, RLxF and test-time compute methodologies.
Outcome:	The proposed model can be used to understand and generate human natural languages.

Copied to clipboard

Haozhe Zhao, Zefan Cai, Shuzheng Si, Liang Chen, Jiuxiang Gu, Wen Xiao, Minjia Zhang, Junjie Hu

AuriSRec: Adversarial User Intention Learning in Sequential Recommendation (2024.findings-emnlp)

Challenge:	Recent text-to-image models achieve impressive visual quality but still face challenges in precise controllability, balancing multimodal inputs, and high training cost for multimodal image generation.
Approach:	They propose an autoregressive framework with a two-stage training paradigm for controllable multimodal image generation.
Outcome:	Extensive experiments on DreamBench++ and DreamBech show that the proposed framework achieves a strong balance between textual and visual guidance for controllable image generation.

Copied to clipboard

Junjie Zhang, Ruobing Xie, Wenqi Sun, Leyu Lin, Xin Zhao, Ji-Rong Wen

Table-LLM-Specialist: Language Model Specialists for Tables using Iterative Fine-tuning (2025.emnlp-main)

Challenge:	Existing work focuses on capturing user implicit preferences from historical interactions and matching them with the next behavior, instead of predicting user explicit intentions.
Approach:	They propose an adversarial user intention learning approach for sequential recommendaiton . the approach explicitly predicts user current intentions by taking historical reviews as inputs .
Outcome:	The proposed approach explicitly predicts user intentions by inferring their decision-making process as explained in target reviews.

Copied to clipboard

Junjie Xing, Yeye He, Mengyu Zhou, Haoyu Dong, Shi Han, Dongmei Zhang, Surajit Chaudhuri

MegaPairs: Massive Data Synthesis for Universal Multimodal Retrieval (2025.acl-long)

Challenge:	Language models such as GPT and Llama have shown remarkable ability on diverse natural language tasks, yet their performance on complex table tasks is suboptimal.
Approach:	They propose a generator-validator paradigm to iteratively generate-then-validate training data from language models to fine-tune stronger Table-Specialist models that can specialize in a given task, without using manually-labeled data.
Outcome:	The proposed model outperforms vanilla language models on diverse table tasks and can match or surpass GPT-4 level quality.

Copied to clipboard

Junjie Zhou, Yongping Xiong, Zheng Liu, Ze Liu, Shitao Xiao, Yueze Wang, Bo Zhao, Chen Jason Zhang, Defu Lian

Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective (2022.emnlp-main)

Challenge:	despite the growing demand for multimodal retrieval, there is a lack of training data.
Approach:	They propose a data synthesis method that leverages vision language models and open-domain images to generate high-quality data.
Outcome:	The proposed method outperforms baseline models on 70 more datasets and can scale up.

Copied to clipboard

Ping Yang, Junjie Wang, Ruyi Gan, Xinyu Zhu, Lin Zhang, Ziwei Wu, Xinyu Gao, Jiaxing Zhang, Tetsuya Sakai

Low-Resource NLP

Challenge:	Existing approaches to zero-shot learning are format-agnostic and can address new learning tasks without additional training.
Approach:	They propose a new paradigm for zero-shot learning that is format agnostic and compatible with any format and applicable to a list of language tasks.
Outcome:	The proposed model shows state-of-the-art performance on several benchmarks and produces satisfactory results on tasks such as text classification and commonsense reasoning.

MulDimIF: A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models (2026.findings-acl)

Copied to clipboard

Junjie Ye, Caishuang Huang, Zhuohan Chen, Wenjie Fu, Chenyuan Yang, Leyi Yang, Yilong Wu, Peng Wang, Meng Zhou, Xiaolong Yang, Tao Gui, Qi Zhang, Zhongchao Shi, Jianping Fan, Xuanjing Huang

APIRecX: Cross-Library API Recommendation via Pre-Trained Language Model (2021.emnlp-main)

Challenge:	Existing research has focused on constraint categories, offering little guidance for improving instruction following abilities.
Approach:	They propose a multi-dimensional constraint framework that allows for instruction following . they construct 9,106 code-verifiable samples and evaluate 18 LLMs .
Outcome:	The proposed framework improves instruction following performance without compromising general performance.

Copied to clipboard

Yuning Kang, Zan Wang, Hongyu Zhang, Junjie Chen, Hanmo You

Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and Languages for Open Named Entity Recognition (2025.coling-main)

Challenge:	API recommendation tools can help programmers use APIs by recommending which APIs to be used next given the APIs that have been written.
Approach:	They propose a cross-library API recommendation approach that uses BPE to split API calls in each sequence and pre-train a GPT based language model.
Outcome:	The proposed APIRecX can recommend APIs that are previously regarded as OOV . it can migrate knowledge of existing libraries to a new library and recommend API that is previously viewed as OVO .

Copied to clipboard

Yuming Yang, Wantong Zhao, Caishuang Huang, Junjie Ye, Xiao Wang, Huiyuan Zheng, Yang Nan, Yuran Wang, Xueying Xu, Kaixin Huang, Yunke Zhang, Tao Gui, Qi Zhang, Xuanjing Huang

Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric (2025.acl-long)

Challenge:	Current Large Language Models struggle with complex entity taxonomies in open domains and lack NER capabilities.
Approach:	They propose a dataset to guide LLMs' generalization in Open NER under a universal entity taxonomy.
Outcome:	The proposed model outperforms GPT-4 in 3 out-of-domain benchmarks across 15 datasets and 6 languages.

Copied to clipboard

Yuming Yang, Yang Nan, Junjie Ye, Shihan Dou, Xiao Wang, Shuo Li, Huijie Lv, Tao Gui, Qi Zhang, Xuanjing Huang

QFinZero: A Unified Financial Toolchain for LLM-Based Trading Agents (2026.acl-demo)

Challenge:	Existing studies have explored various diversity-aware data selection methods to construct high-quality datasets and enhance model performance.
Approach:	They propose to use data diversity to measure instruction tuning of large language models.
Outcome:	The proposed diversity metric outperforms existing methods on simulated and real-world data and shows that it captures diversity variations and achieves a 0.97 correlation with instruction tuning.

Copied to clipboard

Haochen Luo, Yifan LI, Ho Tin Ko, An Binh Minh, Junjie Xu, Tang Pok Hin, Wang Chak Wong, Gao Yuan, Zhengzhao Lai, Yuan Zhang, Chen Liu

Information Retrieval

Challenge:	Existing trading systems rely on fragmented and task-specific APIs, resulting in inconsistent schemas and limited reproducibility.
Approach:	They propose a unified trading environment for large language model (LLM) agents that standardizes three core capabilities . they argue that such a standardized trading environment is essential for scalable research on LLM-based financial agents.
Outcome:	The proposed trading environment reduces engineering overhead and supports reproducible evaluation through comprehensive logging and deterministic replay.

PHMOSpell: Phonological and Morphological Knowledge Guided Chinese Spelling Check (2021.acl-long)

Copied to clipboard

Li Huang, Junjie Li, Weiwei Jiang, Zhiyu Zhang, Minchuan Chen, Shaojun Wang, Jing Xiao

Syntactic Text Processing

Challenge:	False gram and phonological errors make Chinese spelling check difficult . a novel end-to-end trainable model outperforms existing methods .
Approach:	They propose a trainable Chinese spelling check model that integrates phonological and visual information into a pre-trained language model.
Outcome:	The proposed model outperforms existing state-of-the-art models on three benchmarks.

RethinkingTMSC: An Empirical Study for Target-Oriented Multimodal Sentiment Classification (2023.findings-emnlp)

Copied to clipboard

Junjie Ye, Jie Zhou, Junfeng Tian, Rui Wang, Qi Zhang, Tao Gui, Xuanjing Huang

Information Retrieval

Challenge:	Recent studies have shown that current TMSC systems rely on textual information, and the progress in tackling this task has slowed down.
Approach:	They propose to integrate both visual and textual information to improve the performance of TMSC by considering multimodal information.
Outcome:	The proposed model integrates both visual and textual information to improve performance.

FocusLLM: Precise Understanding of Long Context by Dynamic Condensing (2025.acl-long)

Copied to clipboard

Zhenyu Li, Yike Zhang, Tengyu Pan, Yutao Sun, Zhichao Duan, Junjie Fang, Rong Han, Zixuan Wang, Jianyong Wang

Challenge:	Existing context condensing methods cannot accurately understand the full context, as there is a considerable amount of information loss in the condensed process.
Approach:	They propose a framework to extend the fixed context length of any decoder-only LLM by distilling crucial information from long sequences.
Outcome:	The proposed framework extends the fixed context length of any decoder-only LLM, allowing it to focus on relevant information from very long sequences.

All Information is Valuable: Question Matching over Full Information Transmission Network (2022.findings-naacl)

Copied to clipboard

Le Qi, Yu Zhang, Qingyu Yin, Guidong Zheng, Wen Junjie, Jinlong Li, Ting Liu

ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages (2024.acl-long)

Challenge:	Existing methods for question matching only transmit one kind of information while failing to utilize both kinds of information simultaneously.
Approach:	They propose a question matching network that can transmit both representation and interactive information together in a simultaneous fashion.
Outcome:	The proposed approach outperforms strong baseline models on two standard benchmarks.

Copied to clipboard

Junjie Ye, Sixian Li, Guanyu Li, Caishuang Huang, Songyang Gao, Yilong Wu, Qi Zhang, Tao Gui, Xuanjing Huang

The Stochastic Parrot on LLM’s Shoulder: A Summative Assessment of Physical Concept Understanding (2025.naacl-long)

Challenge:	Existing research focuses on enhancing LLMs capabilities through tool utilization.
Approach:	They propose a framework to investigate safety issues in large language models in tool learning . they propose malicious queries and jailbreak attacks in the input stage .
Outcome:	The proposed framework investigates six safety scenarios for LLMs in tool learning . the data will be released upon acceptance of the proposed framework .

Copied to clipboard

Mo Yu, Lemao Liu, Junjie Wu, Tsz Ting Chung, Shunchi Zhang, Jiangnan Li, Dit-Yan Yeung, Jie Zhou

Challenge:	Recent years have witnessed remarkable advancements in large language models (LLMs) many researchers argue that LLMs may not * Equal contribution.
Approach:	They propose a task that summarises the memorization issue by using grid inputs that abstractly describe physical phenomena.
Outcome:	The proposed task alleviates the memorization issue by using grid-format inputs that abstractly describe physical phenomena.

Vulnerability of Text-to-Image Models to Prompt Template Stealing: A Differential Evolution Approach (2025.findings-acl)

Copied to clipboard

Yurong Wu, Fangwen Mu, Qiuhong Zhang, Jinjing Zhao, Xinrun Xu, Lingrui Mei, Yang Wu, Lin Shi, Junjie Wang, Zhiming Ding, Yiwei Wang

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use (2025.findings-emnlp)

Challenge:	Prompt trading has emerged as a significant intellectual property concern in recent years, where vendors entice users by showcasing sample images before selling prompt templates that can generate similar images.
Approach:	They propose a prompt-stealing benchmark consisting of 50 templates and 450 images organized into Easy and Hard difficulty levels.
Outcome:	The proposed method outperforms baseline methods with an average improvement of over 10%.

Copied to clipboard

Junjie Ye, Yilong Wu, Sixian Li, Yuming Yang, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang, Peng Wang, Zhongchao Shi, Jianping Fan, Zhengyin Du

ERCThinker: Fast-Slow Thinking for Emotion Recognition in Conversation (2026.acl-long)

Challenge:	a new approach to training large language models (LLMs) overlooks task-specific characteristics in tool use, leading to performance bottlenecks.
Approach:	They propose a task-feature-based framework that mitigates the effects of suboptimal training data . they use a dataset to train large-scale LLMs and a reward mechanism tailored to error categories .
Outcome:	The proposed framework matches or surpasses open- and closed-source LLMs in tool-use performance using only 1,217 training data points.

Copied to clipboard

Yumeng Fu, Weitao Huang, Junjie Wu, Hao Teng, Shouduo Shang, Meishan Zhang, Bingquan Liu

UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive Perspective (2023.acl-long)

Challenge:	Existing methods for ERC lack interpretability and shallow semantics capture deep semantics.
Approach:	They propose a Fast-Slow thinking framework for Emotion Recognition in Conversation . they use fine-grained emotion reasoning chains to capture deep semantics .
Outcome:	The proposed framework achieves state-of-the-art in explanation and judgment on a benchmark dataset.

Copied to clipboard

Yang Ping, JunYu Lu, Ruyi Gan, Junjie Wang, Yuxiang Zhang, Pingjian Zhang, Jiaxing Zhang

ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios (2025.coling-main)

Challenge:	Existing approaches for information extraction (IE) are limited by the number of subtasks and the isolation of the subtask.
Approach:	They propose a new paradigm for universal information extraction that is compatible with any schema format and applicable to a list of IE tasks.
Outcome:	The proposed framework outperforms generative universal IE models on 14 benchmarks with the supervised setting and the state-of-the-art performance in low-resource scenarios.

Copied to clipboard

Junjie Ye, Guanyu Li, SongYang Gao, Caishuang Huang, Yilong Wu, Sixian Li, Xiaoran Fan, Shihan Dou, Tao Ji, Qi Zhang, Tao Gui, Xuanjing Huang

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

Challenge:	Existing evaluations of tool learning focus on validation of tools for large language models with expected outcomes, but this focus ignores the complex capabilities required for LLMs to effectively use tools.
Approach:	They propose a fine-grained system for evaluation of large language models’ tool learning capabilities in authentic scenarios.
Outcome:	The proposed system examines seven real-world scenarios, analyzing five dimensions crucial to LLMs in tool learning: format alignment, intent comprehension, behavior planning, tool selection, and answer organization.

Copied to clipboard

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

TempParaphraser: “Heating Up” Text to Evade AI-Text Detection through Paraphrasing (2025.emnlp-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

Junjie Huang, Ruiquan Zhang, Jinsong Su, Yidong Chen

Text Generation

Challenge:	Existing detectors that perform well on benchmark datasets have weaknesses that can be exploited to manipulate AI-text.
Approach:	They propose a framework that simulates high-temperature sampling effects through multiple normal-temperaturing generations, effectively evading detection.
Outcome:	The proposed framework reduces detector accuracy by an average of 82.5% while preserving high text quality.

Supervised Optimism Correction: Be Confident When LLMs Are Sure (2025.findings-acl)

Copied to clipboard

Junjie Zhang, Rushuai Yang, Shunyu Liu, Ting-En Lin, Fei Huang, Yi Chen, Yongbin Li, Dacheng Tao

RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning (2024.emnlp-main)

Challenge:	Recent advances in Large Language Models (LLMs) have demonstrated remarkable success across diverse tasks such as instruction following, code generation, and medical diagnosis.
Approach:	They propose a supervised fine-tuning-based auxiliary loss for Q-value estimations during supervised refinement.
Outcome:	The proposed method outperforms beam search on GSM8K, MATH, and GAOKAO on reasoning benchmarks.

Copied to clipboard

Junjie Ye, Yilong Wu, Songyang Gao, Caishuang Huang, Sixian Li, Guanyu Li, Xiaoran Fan, Qi Zhang, Tao Gui, Xuanjing Huang

Entity Relation Extraction as Dependency Parsing in Visually Rich Documents (2021.emnlp-main)

Challenge:	Current research emphasizes LLMs’ capacity to utilize tools in well-structured environments while overlooking their stability when confronted with the inevitable noise of the real world.
Approach:	They propose a multi-level benchmark to evaluate the robustness of large language models in tool learning by establishing five external environments with varying levels of noise.
Outcome:	The proposed model outperforms the GPT-4 model in tool learning in three critical phases: tool selection, parameter identification, and content filling.

Copied to clipboard

Yue Zhang, Zhang Bo, Rui Wang, Junjie Cao, Chen Li, Zuyi Bao

Syntactic Text Processing

Challenge:	Existing studies on key information extraction from visually rich documents focus on labeling the text within bounding boxes, while relations between words are unexplored.
Approach:	They propose to use a dependency parsing model to extract semantic entities from visually rich documents by combining entity labeling and relation extraction tasks.
Outcome:	The proposed model achieves 65.96% F1 score on the FUNSD dataset.

Adaptive Multi-Task Transfer Learning for Chinese Word Segmentation in Medical Text (C18-1)

Copied to clipboard

Junjie Xing, Kenny Zhu, Shaodian Zhang

StepCoder: Improving Code Generation with Reinforcement Learning from Compiler Feedback (2024.acl-long)

Challenge:	Chinese word segmentation (CWS) tools face a performance drop when dealing with domain text . domain-specific CWS requires extremely high annotation cost due to ambiguity caused by domain terms and writing style .
Approach:	They propose to exploit domain-invariant knowledge from high resource to low resource domains to build Chinese word segmentation models.
Outcome:	The proposed model achieves higher accuracy than single-task CWS and other transfer learning baselines . the model is based on domain-invariant knowledge from high resource to low resource domains based in the biomedical domain .

Copied to clipboard

Shihan Dou, Yan Liu, Haoxiang Jia, Enyu Zhou, Limao Xiong, Junjie Shan, Caishuang Huang, Xiao Wang, Xiaoran Fan, Zhiheng Xi, Yuhao Zhou, Tao Ji, Rui Zheng, Qi Zhang, Tao Gui, Xuanjing Huang

Programming Languages in NLP

Challenge:	Existing work integrates reinforcement learning with compiler feedback to enhance code generation quality but the long code generated by LLMs makes RL exploration ineffective.
Approach:	They propose a framework that integrates reinforcement learning and compiler feedback to enhance code generation quality.
Outcome:	The proposed framework outperforms state-of-the-art approaches in corresponding benchmarks and integrates reinforcement learning with compiler feedback to improve code generation quality.

Field Embedding: A Unified Grain-Based Framework for Word Representation (2021.naacl-main)

Copied to clipboard

Junjie Luo, Xi Chen, Jichao Sun, Yuejia Xiang, Ningyu Zhang, Xiang Wan

Representation Learning

Challenge:	Current methods focus on learning word embeddings while linguistic information is discarded after the learning.
Approach:	They propose a framework field embedding to jointly learn word and grain embedds by incorporating morphological, phonetic, and syntactical linguistic fields.
Outcome:	The proposed framework integrates morphological, phonetic, and syntactical linguistic fields to learn word embeddings and grain embedds.

Solving Math Word Problems via Cooperative Reasoning induced Language Models (2023.acl-long)

Copied to clipboard

Xinyu Zhu, Junjie Wang, Lin Zhang, Yuxiang Zhang, Yongfeng Huang, Ruyi Gan, Jiaxing Zhang, Yujiu Yang

LaERC-S: Improving LLM-based Emotion Recognition in Conversation with Speaker Characteristics (2025.coling-main)

Challenge:	Large-scale pre-trained language models (PLMs) can be used to solve math word problems, but they lack fast adaptivity as humans.
Approach:	They propose a cooperative reasoning-induced PLM for solving the math word problem . they use system 1 as the generator and system 2 as the verifier to generate reasoning paths .
Outcome:	The proposed model improves on several mathematical reasoning datasets and achieves 9.6% improvement over baselines.

Copied to clipboard

Yumeng Fu, Junjie Wu, Zhongjie Wang, Meishan Zhang, Lili Shan, Yulin Wu, Bingquan Liu

Sentiment Analysis

Challenge:	Emotion recognition in conversation (ERC) is a task of discerning human emotions for each utterance within a conversation.
Approach:	They propose a framework that uses large language models to analyze speaker characteristics . they use two-stage learning to make the models reason speaker characteristics and track emotion of the speaker .
Outcome:	The proposed framework outperforms existing methods on three benchmark datasets.

Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels (2025.emnlp-main)

Copied to clipboard

Junjie Ye, Yuming Yang, Yang Nan, Shuo Li, Qi Zhang, Tao Gui, Xuanjing Huang, Peng Wang, Zhongchao Shi, Jianping Fan

VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training (2026.acl-long)

Challenge:	Large language models (LLMs) acquire substantial world knowledge during pretraining, which is further shaped by post-training techniques such as supervised fine-tuning (SFT).
Approach:	They evaluate closed-book question answering (CBQA) performance across five LLMs from the LLaMA-2 and LLama-3 families and examine the impact of supervised fine-tuning on model knowledge.
Outcome:	The proposed model performance is 14% worse than models fine-tuned on 1,920 samples and 12% worse on 240 samples.

Copied to clipboard

Dingwei Zhu, Shihan Dou, Zhiheng Xi, Senjie Jin, Guoqiang Zhang, Jiazheng Zhang, Junjie Ye, Mingxu Chai, Enyu Zhou, Ming Zhang, Yuhui Wang, Caishuang Huang, Chenhao Huang, Yunke Zhang, Yuran Wang, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang

Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm Perspective (2025.acl-long)

Challenge:	Reinforcement Learning (RL) in real-world environments often suffers from ambiguous or incomplete supervision.
Approach:	They propose a framework that enhances value modeling for robust RL in LLM post-training by integrating auxiliary losses guided by entropy and perplexity from a frozen language model and variational information bottleneck.
Outcome:	The proposed framework outperforms baselines on multi-turn dialogue, math reasoning, and science QA with rule-based and model-based rewards.

Copied to clipboard

Yiyao Yu, Yuxiang Zhang, Dongdong Zhang, Xiao Liang, Hengyuan Zhang, Xingxing Zhang, Mahmoud Khademi, Hany Hassan Awadalla, Junjie Wang, Yujiu Yang, Furu Wei

Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments (2026.findings-acl)

Challenge:	Existing work shows that LLMs rely on single-paradigm reasoning that limits their effectiveness across diverse tasks.
Approach:	They propose a new framework that integrates multiple reasoning paradigms to enable synergistic collaboration.
Outcome:	The proposed model outperforms current SOTA models in theorem proving tasks and the MATH benchmark in arithmetic tasks.

Copied to clipboard

Junjie Ye, Changhao Jiang, Zhengyin Du, Yufei Xu, Xuesong Yao, Zhiheng Xi, Xiaoran Fan, Qi Zhang, Tao Gui, Xuanjing Huang, Jiecao Chen

AndroidGen: Building an Android Language Agent under Data Scarcity (2025.acl-long)

Challenge:	Currently, there are no efficient reinforcement learning (RL) frameworks specifically designed for tool use.
Approach:	They propose an automated environment construction pipeline that incorporates scenario decomposition, document generation, function integration, complexity scaling, and localized deployment to enable high-quality training environments without external tools.
Outcome:	The proposed framework significantly improves the models’ tool-use performance without degrading their general capabilities.

Copied to clipboard

Hanyu Lai, Junjie Gao, Xiao Liu, Yifan Xu, Shudan Zhang, Yuxiao Dong, Jie Tang

JoPR: Joint Emotion Perception and Reasoning for Conversational Emotion Recognition (2026.acl-long)

Challenge:	Existing LLMs lack high-quality data sources and lack robust data filtration strategies.
Approach:	They develop a framework to enhance the capabilities of LLM-based agents under data scarcity.
Outcome:	The proposed framework improves the capabilities of LLM-based agents under data scarcity.

Copied to clipboard

Yumeng Fu, Weitao Huang, Junjie Wu, Hao Teng, Meishan Zhang, Bingquan Liu

REO-Relevance, Extraness, Omission: A Fine-grained Evaluation for Image Captioning (D19-1)

Challenge:	Existing methods for ERC lack human-like emotion reasoning and discrimination between similar emotions.
Approach:	They propose a multi-dimension curriculum with long CoT fine-tuning to clone human-like emotion reasoning for conversational emotion recognition.
Outcome:	The proposed model outperforms existing methods on three widely used datasets and shows that it is more intuitive and more accurate.

Copied to clipboard

Ming Jiang, Junjie Hu, Qiuyuan Huang, Lei Zhang, Jana Diesner, Jianfeng Gao

SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis (2025.findings-emnlp)

Challenge:	Existing metrics for image captioning evaluation provide an overall quality score, which is difficult to infer specific description errors.
Approach:	They propose a fine-grained evaluation method REO for automatically measuring the performance of image captioning systems.
Outcome:	The proposed method achieves higher consistency with human judgments and provides more intuitive evaluation results than other metrics.

Copied to clipboard

Shuang Sun, Huatong Song, Yuhao Wang, Ruiyang Ren, Jinhao Jiang, Junjie Zhang, Fei Bai, Jia Deng, Xin Zhao, Zheng Liu, Lei Fang, Zhongyuan Wang, Ji-Rong Wen

ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use (2025.acl-long)

Challenge:	Existing approaches to deep search training lack high-quality training trajectories, prohibitive computational costs and lack of high-fidelity training data.
Approach:	They propose a framework that synthesizes high-quality training data by simulating real user interactions in live web search environments.
Outcome:	The proposed framework synthesizes high-quality training data by simulating user interactions in live web search environments.

Copied to clipboard

Junjie Ye, Zhengyin Du, Xuesong Yao, Weijian Lin, Yufei Xu, Zehui Chen, Zaiyuan Wang, Sining Zhu, Zhiheng Xi, Siyu Yuan, Tao Gui, Qi Zhang, Xuanjing Huang, Jiecao Chen

Any Information Is Just Worth One Single Screenshot: Unifying Search With Visualized Information Retrieval (2025.acl-long)

Challenge:	Effective evaluation of multi-hop tool use is critical for analyzing the understanding, reasoning, and function-calling capabilities of large language models.
Approach:	They propose a dataset that provides rigorous evaluation of multi-hop tool use.
Outcome:	The proposed model achieves 49.04% accuracy across five model families.

Copied to clipboard

Zheng Liu, Ze Liu, Zhengyang Liang, Junjie Zhou, Shitao Xiao, Chao Gao, Chen Jason Zhang, Defu Lian

Graph-R1: Incentivizing the Zero-Shot Graph Learning Capability in LLMs via Explicit Reasoning (2025.emnlp-main)

Challenge:	Existing multimodal retrieval models are lacking in visual representations of multimodal data.
Approach:	They propose a visualized information retrieval paradigm where multimodal information is represented by a unified visual format called Screenshots for various retrieval applications.
Outcome:	The proposed model is based on a large dataset of screenshots from diverse sources . it is compared with existing models and lays a solid foundation for the new model .

Copied to clipboard

Yicong Wu, Guangyue Lu, Yuan Zuo, Huarong Zhang, Junjie Wu

HiTIN: Hierarchy-aware Tree Isomorphism Network for Hierarchical Text Classification (2023.acl-long)

Challenge:	Recent advances in Large Reasoning Models (LLMs) provide a zero-shot alternative via explicit, long chain-of-thought reasoning.
Approach:	They propose a GNN-free approach that reformulates graph tasks as textual reasoning problems solved by LRMs.
Outcome:	The proposed approach outperforms state-of-the-art baselines in zero-shot settings, producing interpretable and effective predictions.

Copied to clipboard

He Zhu, Chong Zhang, Junjie Huang, Junran Wu, Ke Xu

A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code (2026.findings-acl)

Challenge:	Existing dual-encoder methods in HTC achieve weak performance gains with huge memory overheads and their structure encoders heavily rely on domain knowledge.
Approach:	They propose a hierarchy-aware tree isomorphism network to enhance the text representations with only syntactic information of the label hierarchy.
Outcome:	The proposed model could boost the performance of hierarchical text classification without prior statistics or label semantics without prior data.

Copied to clipboard

Keke Lian, Wang Bin, Lei Zhang, Libo Chen, Junjie Wang, Ziming Zhao, Yujiu Yang, Miaoqian Lin, Haotong Duan, Haoran Zhao, Shuang Liao, Mingda Guo, Quan Jiazheng, Yilu Zhong, Chenhao He, Chen Zichuan, Jie Wu, Haoling Li, Zhaoxuan Li, Jiongchi Yu, Hui LI, Dong Zhang

Programming Languages in NLP

Challenge:	Existing security evaluation benchmarks lack relevance to real-world AI programming tasks . current LLMs struggle with secure coding, research shows .
Approach:	They propose a repository-level evaluation benchmark to assess security of AI-generated code.
Outcome:	The proposed framework mirrors real-world AI programming tasks and offers valuable insights into the state of AI code generation.

HoLLMwood: Unleashing the Creativity of Large Language Models in Screenwriting via Role Playing (2024.findings-emnlp)

Copied to clipboard

Jing Chen, Xinyu Zhu, Cheng Yang, Chufan Shi, Yadong Xi, Yuxiang Zhang, Junjie Wang, Jiashu Pu, Tian Feng, Yujiu Yang, Rongsheng Zhang

Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models (2024.emnlp-main)

Challenge:	Generative AI has demonstrated unprecedented creativity in the field of computer vision, yet such phenomena have not been observed in the realm of literary creation.
Approach:	They propose a framework for unleashing the creativity of large language models (LLMs) they assign LLMs to different roles involved in real-world scenario, they write .
Outcome:	The proposed framework outperforms baselines in terms of coherence, relevance, interestingness and overall quality on automatically generated screenplays.

Copied to clipboard

Junjie Chu, Zeyang Sha, Michael Backes, Yang Zhang

Beyond Scaling: Measuring and Predicting the Upper Bound of Knowledge Retention in Language Model Pre-Training (2026.acl-long)

Challenge:	Existing GPT models allow users to interact with them for multiple rounds to optimize the task execution.
Approach:	They propose a conversation reconstruction attack targeting the contents of previous conversations between GPT models and benign users, i.e., the benign users’ input contents during their interaction with GPT.
Outcome:	The proposed attacks demonstrate that GPT-4's defense mechanisms are ineffective against these attacks.

Copied to clipboard

Changhao Jiang, Ming Zhang, Yifei Cao, Junjie Ye, Xiaoran Fan, Shihan Dou, Zhiheng Xi, Jiajun Sun, Yi Dong, Yujiong Shen, Jingqi Tong, Baoyu Fan, Tao Gui, Qi Zhang, Xuanjing Huang

Towards Accurate and Consistent Evaluation: A Dataset for Distantly-Supervised Relation Extraction (2020.coling-main)

Challenge:	Existing methods to predict performance of large language models are lacking . authors propose a size-dependent mutual information predictor for closed-book question answering accuracy .
Approach:	They propose a size-dependent mutual information predictor that integrates knowledge frequency, knowledge specificity, and model size to forecast closed-book question answering accuracy.
Outcome:	The proposed method outperforms baseline models and achieves R2 > 0.7 in predicting QA accuracy without additional training.

Copied to clipboard

Tong Zhu, Haitao Wang, Junjie Yu, Xiabing Zhou, Wenliang Chen, Wei Zhang, Min Zhang

Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models (2025.findings-emnlp)

Challenge:	Distant Supervision (DS) generates large-scale annotated data but has wrong labels that result in incorrect evaluation scores during testing.
Approach:	They build a dataset using DS-generated data as training data and hire annotators to label test data.
Outcome:	The proposed dataset NYTH has a much larger test set and performs more accurate and consistent evaluation.

Copied to clipboard

Junjie Xiong, Changjia Zhu, Shuhang Lin, Chong Zhang, Yongfeng Zhang, Yao Liu, Lingyao Li