Papers by Jian He

TransS-Driven Joint Learning Architecture for Implicit Discourse Relation Recognition (2020.acl-main)

Challenge:	Existing approaches to improve retrieval performance of large language models are limited by static knowledge.
Approach:	They propose a multimodal re-ranking framework that combines curriculum learning with fine-grained reranking and multimodal section reassessment to improve CLIP-based visual coarse-grain retrieval.
Outcome:	The proposed framework achieves state-of-the-art answer accuracy and competitive retrieval performance on InfoSeek and Enc-VQA.

Copied to clipboard

Ruifang He, Jian Wang, Fengyu Guo, Yugui Han

Challenge:	Existing approaches to implicit discourse relation recognition lack connectives as strong linguistic clues.
Approach:	They propose a transS-driven joint learning architecture to translate discourse relations in low-dimensional embedding space and exploit the semantic features of arguments to assist discourse understanding.
Outcome:	The proposed model outperforms existing systems on the Penn Discourse TreeBank.

From Pseudo-Balancing to True Specialization: Memory-Aware Routing for Mixture-of-Experts (2026.findings-acl)

Copied to clipboard

Peixuan Hou, Yunbo Hou, Bin Chen, LI He, Jian Xu, Weiping Li, Bo Zheng, Guojie Song

Green & Sustainable NLP

Challenge:	Existing methods to optimize expert-centered load balancing fail to account for pseudo-balance phenomenon . severe knowledge overlap among experts leads to redundant representations and inefficient parameter utilization .
Approach:	They propose a method that prioritizes expert utilization over semantic alignment . they use memory-aware routing to ensure expert load balancing is consistent .
Outcome:	Experimental results show that MAR improves expert specialization by 35% and accuracy by 2%-25% . MAR matches baseline performance with only half the experts .

MedForge: Interpretable Medical Deepfake Detection via Forgery-aware Reasoning (2026.acl-long)

Copied to clipboard

Zhihui Chen, Kai He, Qingyuan Lei, Bin Pu, Jian Zhang, Yuling Xu, Mengling Feng

HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference (2026.acl-long)

Challenge:	Existing defenses against forgery are inadequate for healthcare.
Approach:	They propose a large-scale benchmark for pre-hoc, evidence-grounded medical forgery detection using a doctor inspection guideline and gold edit locations.
Outcome:	Experiments show that the proposed solution can detect and explain medical scans with high fidelity and accuracy.

Copied to clipboard

Zhiyuan Shi, Qibo Qiu, null Xuefeng, Zhonglin Jiang, Li Yu, Jian Jiang, Xiaofei He, Wenxiao Wang

Information Retrieval

Challenge:	Existing static compression methods suffer from coarse-grained caching and high I/O overhead.
Approach:	They propose a training-free dynamic compression framework that uses a sparse attention mechanism to categorize attention heads based on stability and similarity.
Outcome:	The proposed framework achieves state-of-the-art performance on long-context benchmarks and accelerates decoding by up to 3 compared to the original model with a 224K context.

Enhancing Character-Level Understanding in LLMs through Token Internal Structure Learning (2025.acl-long)

Copied to clipboard

Zhu Xu, Zhiqiang Zhao, Zihan Zhang, Yuchi Liu, Quanwei Shen, Fei Liu, Yu Kuang, Jian He, Conglin Liu

Challenge:	Large language models (LLMs) use tokenization methods but often obscure internal character structures within tokens.
Approach:	They propose a method that improves models’ ability to capture character positions within tokens by training them on reverse character prediction tasks using the tokenizer’s vocabulary.
Outcome:	Experiments show that the proposed method improves position prediction accuracy in large language models, enabling more precise identification of target characters in original text.

DialMed: A Dataset for Dialogue-based Medication Recommendation (2022.coling-1)

Copied to clipboard

Zhenfeng He, Yuqiang Han, Zhenqiu Ouyang, Wei Gao, Hongxu Chen, Guandong Xu, Jian Wu

Natural Language Interfaces

Challenge:	Existing studies on medication recommendation mainly rely on EHRs, but some details of interactions between doctors and patients may be ignored or omitted in EHR.
Approach:	They propose to use medical dialogues to recommend medications with medical dialogue data . they propose to model dialogue structure and disease knowledge aware network .
Outcome:	The proposed method is a promising solution to recommend medications with medical dialogues.

PRP-Graph: Pairwise Ranking Prompting to LLMs with Graph Aggregation for Effective Text Re-ranking (2024.acl-long)

Copied to clipboard

Jian Luo, Xuanang Chen, Ben He, Le Sun

Language Models

Challenge:	Existing methods for pairing ranking prompting only output the same label for comparison results of different confidence intervals without considering the uncertainty of pairwise comparison.
Approach:	They propose a pairwise ranking prompting approach that exploits the output probabilities of target labels to capture the degree of certainty of comparison results.
Outcome:	The proposed method shows strong robustness and acceptable efficiency on the BEIR benchmark.

What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time (2026.acl-long)

Copied to clipboard

Dong Yan, Jian Liang, Yanbo Wang, Shuo Lu, Ran He, Tieniu Tan

Robustness in NLP

Challenge:	Existing TTRL methods rely on positive pseudo-labeling strategies to enhance reasoning capabilities.
Approach:	They propose a test-time reinforcement learning framework that mitigates label noise amplification by deriving pseudo-rewards from majority voting consensus.
Outcome:	The proposed framework mitigates label noise amplification by implementing selective positive pseudo-labeling and entropy-gated negative p-labeled pruning.

Table-R1: Region-based Reinforcement Learning for Table Understanding (2026.findings-acl)

Copied to clipboard

Zhenhe Wu, Jian Yang, Zhongjiang He, Changzai Pan, Jiaheng Liu, Xianjie Wu, Yu Zhao, Shuangyong Song, Yongxiang Li, Zhoujun Li, Xuelong Li

InfiMM: Advancing Multimodal Understanding with an Open-Sourced Visual Language Model (2024.findings-acl)

Challenge:	Tables are a widely used data format that poses unique challenges for language models due to their structured row-column interactions.
Approach:	They propose a region-based reinforcement learning approach that integrates region evidence into reasoning steps.
Outcome:	The proposed method outperforms baseline models on three benchmark datasets and significantly reduces the reasoning token consumption by 67.5%.

Copied to clipboard

Haogeng Liu, Quanzeng You, Yiqi Wang, Xiaotian Han, Bohan Zhai, Yongfei Liu, Wentao Chen, Yiren Jian, Yunzhe Tao, Jianbo Yuan, Ran He, Hongxia Yang

MdEval: Massively Multilingual Code Debugging (2026.findings-acl)

Challenge:	InfiMM is a multimodal large language model that adapts to complex vision-language tasks.
Approach:	They present a Multimodal Large Language Model that adapts to intricate vision-language tasks using large-scale training data and comprehensive training strategies.
Outcome:	Empirical evaluations across a variety of benchmarks underscore InfiMM’s remarkable capability in multimodal understanding.

Copied to clipboard

Shukai Liu, Linzheng Chai, Jian Yang, Jiajun Shi, He Zhu, Liran Wang, Jin Ke, Wei Zhang, Hualei Zhu, Shuyue Guo, Tao Sun, Jiaheng Liu, Yunlong Duan, Yu Hao, Liqun Yang, Guanglin Niu, Ge Zhang, Zhoujun Li

MCGA: A Multi-task Classical Chinese Literary Genre Audio Corpus (2026.findings-acl)

Challenge:	Existing benchmarks primarily focus on Python and are limited in terms of language diversity.
Approach:	They propose a multilingual debugging benchmark that includes 3.9K test samples of 20 programming languages and introduces the debug instruction corpora MdEval-Instruct by injecting bugs into the correct multilingual queries and solutions.
Outcome:	The proposed benchmark includes 3.9K test samples of 20 programming languages and covers the automated program repair task, bug localization task, and bug identification task.

Copied to clipboard

Yexing Du, Kaiyuan Liu, Bihe Zhang, Youcheng Pan, Bo Yang, Liangyu Huo, Xiyuan Zhang, Jian Xie, Daojing He, Yang Xiang, Ming Liu, Bing Qin

SEEK: Segmented Embedding of Knowledge Graphs (2020.acl-main)

Challenge:	Multimodal Large Language Models (MLLMs) have advanced Chinese Classical Studies (CCS) but the audio dimension of CCS remains underexplored due to a lack of high-quality, domain-specific audio corpora.
Approach:	They propose a 119-hour audio corpus comprising 22,000 audio samples to bridge this gap . it encompasses a diverse range of literary genres across six tasks .
Outcome:	The proposed corpus encompasses a diverse range of literary genres across six tasks: Automatic Speech Recognition (ASR), Speech-to-Text Translation (S2TT), Speech Emotion Captioning (SEC), Spoken Question Answering ( SQA), Speech Understanding (SU), and Speech Reasoning (SR).

Copied to clipboard

Wentao Xu, Shun Zheng, Liang He, Bin Shao, Jian Yin, Tie-Yan Liu

Generating Informative Conversational Response using Recurrent Knowledge-Interaction and Knowledge-Copy (2020.acl-main)

Challenge:	Existing methods for knowledge graph embedding can not make a proper trade-off between the model complexity and the model expressiveness, which makes them far from satisfactory.
Approach:	They propose a lightweight modeling framework that can achieve highly competitive relational expressiveness without increasing the model complexity.
Outcome:	The proposed framework can achieve highly competitive relational expressiveness without increasing model complexity.

Copied to clipboard

Xiexiong Lin, Weiyu Jian, Jianshan He, Taifeng Wang, Wei Chu

Dual Dynamic Memory Network for End-to-End Multi-turn Task-oriented Dialog Systems (2020.coling-main)

Challenge:	Knowledge-driven conversation approaches have attracted considerable research attention in recent years.
Approach:	They propose a method that integrates recurrent knowledge interaction among response decoding steps to incorporate appropriate knowledge.
Outcome:	The proposed method improves on two datasets Wizard-of-Wikipedia and DuConv with different knowledge formats and different languages.

Copied to clipboard

Jian Wang, Junhao Liu, Wei Bi, Xiaojiang Liu, Kejing He, Ruifeng Xu, Min Yang

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

Challenge:	Existing task-oriented dialog systems struggle to dynamically model long dialog context for interactions and effectively incorporate knowledge base (KB) information into dialog generation.
Approach:	They propose a dual dynamic memory network for multi-turn dialog generation . the model dynamically expands the dialog memory turn by turn and keeps track of dialog history .
Outcome:	The proposed model outperforms baseline models on three benchmark datasets on human evaluation and automatic evaluation.

Copied to clipboard

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

InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning (2025.findings-emnlp)

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

Copied to clipboard

Xiaotian Han, Yiren Jian, Xuefeng Hu, Haogeng Liu, Yiqi Wang, Qihang Fan, Yuang Ai, Huaibo Huang, Ran He, Zhenheng Yang, Quanzeng You

Knowledge Enhanced Pre-training for Cross-lingual Dense Retrieval (2024.lrec-main)

Challenge:	InfiMM-WebMath-40B is a dataset of interleaved image-text documents . it consists of 24 million web pages, 85 million image URLs, and 40 billion text tokens .
Approach:	InfiMM-WebMath-40B is a high-quality dataset of interleaved image-text documents . it contains 24 million web pages, 85 million image URLs, and 40 billion text tokens .
Outcome:	InfiMM-WebMath-40B is a high-quality dataset of interleaved image-text documents . it consists of 24 million web pages, 85 million image URLs, and 40 billion text tokens .

Copied to clipboard

Hang Zhang, Yeyun Gong, Dayiheng Liu, Shunyu Zhang, Xingwei He, Jiancheng Lv, Jian Guo

Metric-guided Distillation: Distilling Knowledge from the Metric to Ranker and Retriever for Generative Commonsense Reasoning (2022.emnlp-main)

Challenge:	Existing mPLMs neglect the importance of knowledge in cross-lingual dense retrieval.
Approach:	They propose a novel mPLM that leverages knowledge to learn language-agnostic semantic representations from a multilingual knowledge base and an annotation of Wiki.
Outcome:	The proposed model achieves strong multilingual and cross-lingual retrieval performance with significant improvements over existing mPLMs.

Copied to clipboard

Xingwei He, Yeyun Gong, A-Long Jin, Weizhen Qi, Hang Zhang, Jian Jiao, Bartuer Zhou, Biao Cheng, Sm Yiu, Nan Duan

Taming Text-to-Image Synthesis for Novices: User-centric Prompt Generation via Multi-turn Guidance (2025.emnlp-main)

Challenge:	Existing work on commonsense generation requires models to have relational reasoning and compositional generalization capabilities.
Approach:	They propose a metric distillation rule to distill knowledge from a standard metric to a ranker and transfer it to re-ranking a retriever.
Outcome:	The proposed method surpasses the previous SOTA.

Copied to clipboard

Yilun Liu, Minggui He, Feiyu Yao, Yuhe Ji, Shimin Tao, Jingzhou Du, Justin Li, Jian Gao, Zhang Li, Hao Yang, Boxing Chen, Osamu Yoshie

Low-Resource NLP

Challenge:	Existing solutions for text-to-image synthesis are sensitive on textual prompts, posing a challenge for novice users.
Approach:	They propose a dialogue-based TIS prompt generation model that emphasizes user experience for novice users.
Outcome:	The proposed model emphasizes user experience for novice users . it improves user-centricity score while maintaining a competitive quality of synthesized images.

CAPSTONE: Curriculum Sampling for Dense Retrieval with Document Expansion (2023.emnlp-main)

Copied to clipboard

Xingwei He, Yeyun Gong, A-Long Jin, Hang Zhang, Anlei Dong, Jian Jiao, Siu Yiu, Nan Duan

Information Retrieval

Challenge:	Experimental results show that dense retrieval models are better at obtaining query-informed representations.
Approach:	They propose a dual-encoder approach that computes latent representations of query and document independently, but inference replaces the real query with a generated one.
Outcome:	The proposed approach outperforms previous dense retrieval models on in-domain and out-of-domain datasets.

UCS-SQL: Uniting Content and Structure for Enhanced Semantic Bridging In Text-to-SQL (2025.findings-acl)

Copied to clipboard

Zhenhe Wu, Zhongqiu Li, JieZhangChinaTele JieZhangChinaTele, Zhongjiang He, Jian Yang, Yu Zhao, Ruiyu Fang, Bing Wang, Hongyan Xie, Shuangyong Song, Zhoujun Li

Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning (2026.findings-acl)

Challenge:	Existing methods overlook the challenge of effectively transforming structure information from NL to SQL.
Approach:	They propose a text-to-SQL framework that unites content and structure pipes to bridge the gap between NL and SQL.
Outcome:	The proposed framework bridges the gap between natural language questions and SQL by combining content and structure pipes.

Copied to clipboard

Yongcan Yu, Lingxiao He, Jian Liang, Kuangpu Guo, Meng Wang, Qianlong Xie, Xingxing Wang, Ran He

Reasoning

Challenge:	a framework to mitigate spurious optimization signals is proposed for test-time reinforcement learning (TTRL) Reinforcement learning with verifiable rewards (RLVR) is an effective paradigm for improving large language models on structured challenging reasoning tasks.
Approach:	They propose a framework to mitigate spurious optimization signals from label noise . they propose to use a frequency-based sampling strategy to exclude ambiguous samples .
Outcome:	The proposed framework outperforms existing TTRL baselines on three large language models across multiple mathematical reasoning benchmarks.

LaoBench: A Large-Scale Multidimensional Lao Benchmark for Large Language Models (2026.acl-long)

Copied to clipboard

Jian Gao, Richeng Xuan, Zhaolu Kang, Dingshi Liao, Wenxin Huang, Zongmou Huang, Yangdi Xu, Bowen Qin, Zheqi He, Xi Yang, null Changjinli, Yonghua Lin

Multilinguality

Challenge:	Existing SEA-focused benchmarks miss Lao-specific cultural grounding and linguistic properties.
Approach:	They propose a multi-dimensional benchmark for assessing large language models in Lao . they use open-source and held-out subsets to evaluate languages with a hybrid pipeline .
Outcome:	LaoBench is the first large-scale, high-quality, and multidimensional benchmark for assessing LLM language understanding and reasoning in Lao.

OAgents: An Empirical Study of Building Effective Agents (2025.findings-emnlp)

Copied to clipboard

He Zhu, Tianrui Qin, King Zhu, Heyuan Huang, Yeyi Guan, Jinxiang Xia, Hanhao Li, Yi Yao, Ningning Wang, Pai Liu, Tianhao Peng, Xin Gui, Li Xiaowan, Yuhui Liu, Xiangru Tang, Jian Yang, Ge Zhang, Xitong Gao, Yuchen Eleanor Jiang, Changwang Zhang, Jun Wang, Jiaheng Liu, Wangchunshu Zhou

MAXS: Meta-Adaptive Exploration with LLM Agents (2026.findings-acl)

Challenge:	a recent study shows that agent research practices are far from standard, rigorous . lack of a standard evaluation protocol makes previous works not reproducible, authors say .
Approach:	They conduct an empirical study on the GAIA benchmark to investigate agent design choices . they find that lack of a standard evaluation protocol makes previous works not reproducible .
Outcome:	The proposed framework achieves state-of-the-art performance among open-source projects.

Copied to clipboard

Jian Zhang, Zhiyuan Wang, Zhangqi Wang, Yu He, Haoran Luo, li Yuan, Lingling Zhang, Rui Mao, Qika Lin, Jun Liu

M2RC-EVAL: Massively Multilingual Repository-level Code Completion Evaluation (2025.acl-long)

Challenge:	Existing methods for inference are often myopic and have divergent reasoning paths . a meta-adaptive reasoning framework is proposed to improve the efficiency of LLM agents .
Approach:	They propose a meta-adaptive reasoning framework that integrates tool execution and reasoning planning.
Outcome:	The proposed framework outperforms existing methods in performance and inference efficiency.

Copied to clipboard

Jiaheng Liu, Ken Deng, Congnan Liu, Jian Yang, Shukai Liu, He Zhu, Peng Zhao, Linzheng Chai, Yanan Wu, JinKe JinKe, Ge Zhang, Zekun Moore Wang, Guoan Zhang, Yingshui Tan, Bangyu Xiang, Zhaoxiang Zhang, Wenbo Su, Bo Zheng

Programming Languages in NLP

Challenge:	Existing repository-level code completion benchmarks focus on a limited number of languages . existing benchmarks report overall average scores of different languages ignoring fine-grained abilities .
Approach:	They propose to use repository-level code completion benchmarks to evaluate general code intelligence abilities across languages for existing code Large Language Models.
Outcome:	The proposed benchmarks improve the code completion abilities of existing LLMs by using two types of annotations on the parsed syntax tree.

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

Copied to clipboard

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

Analyzing Uncertainty of LLM-as-a-Judge: Interval Evaluations with Conformal Prediction (2025.emnlp-main)

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

Copied to clipboard

Huanxin Sheng, Xinyi Liu, Hangfeng He, Jieyu Zhao, Jian Kang

Challenge:	Large language models (LLMs) are powerful automatic evaluators for natural language generation (NLG) tasks, but their uncertainty may limit their deployment in many applications.
Approach:	They propose a conformal prediction framework that provides a prediction interval with coverage guarantees and a midpoint-based score as a low-bias alternative to raw model score and weighted average.
Outcome:	The proposed framework provides a prediction interval with coverage guarantees and a midpoint-based score as a low-bias alternative to raw model score and weighted average.

Learning Neural Templates for Recommender Dialogue System (2021.emnlp-main)

Copied to clipboard

Zujie Liang, Huang Hu, Can Xu, Jian Miao, Yingying He, Yining Chen, Xiubo Geng, Fan Liang, Daxin Jiang

A Novel Negative Sample Generation Method for Contrastive Learning in Hierarchical Text Classification (2025.coling-main)

Challenge:	Recent advances in neural models have shown promising progress on this task, but key challenges remain .
Approach:	They propose a framework that can decouple dialogue generation from item recommendation . they use a response template generator and item selector to generate a responses template .
Outcome:	The proposed framework outperforms the state-of-the-art methods on the benchmark ReDial.

Copied to clipboard

Juncheng Zhou, Lijuan Zhang, Yachen He, Rongli Fan, Lei Zhang, Jian Wan