Papers by Jinpeng Li

Add-One-In: Incremental Sample Selection for Large Language Models via a Choice-Based Greedy Paradigm (2025.emnlp-main)

Challenge:	Existing studies focus on introducing salient word information to general text summarization framework to guide selection of key content in radiology findings.
Approach:	They propose a method for automatic impression generation using word graphs and a Word Graph guided Summarization model to capture critical words and their relations.
Outcome:	The proposed method is validated on two datasets, OPENI and MIMIC-CXR.

Copied to clipboard

Zhuo Li, Yuhao Du, Xiaoqi Jiao, Steven Y. Guo, Yuege Feng, Xiang Wan, Anningzhe Gao, Jinpeng Hu

Language Models

Challenge:	Existing studies focus on individual quality and do not assess the value of training data.
Approach:	They propose a choice-based sample selection framework that evaluates sample quality . they use LLMs to evaluate the value of each option during the selection process .
Outcome:	The proposed model outperforms the full dataset and recent studies on a larger medical dataset.

Graph Enhanced Contrastive Learning for Radiology Findings Summarization (2022.acl-long)

Copied to clipboard

Jinpeng Hu, Zhuo Li, Zhihong Chen, Zhen Li, Xiang Wan, Tsung-Hui Chang

DialoGPS: Dialogue Path Sampling in Continuous Semantic Space for Data Augmentation in Multi-Turn Conversations (2023.acl-long)

Challenge:	Existing methods for automating impression generation have limited the relationship between extra knowledge and the original findings.
Approach:	They propose a framework for automating impression generation that exploits extra knowledge and original findings . they propose combining key words and their relations to extract critical information .
Outcome:	The proposed framework exploits extra knowledge and the original findings in an integrated way . the state-of-the-art results on two datasets confirm the effectiveness of the proposed method .

Copied to clipboard

Ang Lv, Jinpeng Li, Yuhan Chen, Gao Xing, Ji Zhang, Rui Yan

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

Challenge:	a context leads to various responses, and a response answers multiple contexts.
Approach:	They propose a method that augments open-domain dialogue generation from a many-to-many perspective.
Outcome:	The proposed method can augment open-domain dialogue generation tasks with automatic and human evaluation.

Copied to clipboard

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

Revisiting De-Identification of Electronic Medical Records: Evaluation of Within- and Cross-Hospital Generalization (2023.emnlp-main)

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

Yiyang Liu, Jinpeng Li, Enwei Zhu

Challenge:	De-identification is a natural language processing task to detect and remove the protected health information (PHI) from electronic medical records (EMRs).
Approach:	They propose a de-identification dataset comprising EMRs from three hospitals in China and use it to establish a benchmark for evaluating both within- and cross-hospital generalization.
Outcome:	The proposed model with almost perfect within-hospital performance struggles when transferred across hospitals.

Beyond Fully Random Masking: Attention-Guided Denoising and Optimization for Diffusion Language Models (2026.acl-long)

Copied to clipboard

Jia Deng, Junyi Li, Xin Zhao, Jinpeng Wang, Hongyu Lu, Ji-Rong Wen

Language Models

Challenge:	Existing methods for full-attention dLLMs rely on random masking strategies that overlook intrinsic token dependencies.
Approach:	They propose an attention-guided denoising and optimization framework that aligns training and optimization with attention-derived dependencies.
Outcome:	The proposed framework outperforms state-of-the-art methods on mathematical and coding benchmarks.

Tears or Cheers? Benchmarking LLMs via Culturally Elicited Distinct Affective Responses (2026.acl-long)

Copied to clipboard

Chongyuan Dai, Yaling Shen, Zihan Gao, Jia Li, Yishun Jiang, Yaxiong Wang, Liu Liu, Zongyuan Ge, Jinpeng Hu

Sentiment Analysis

Challenge:	Culture is a fundamental determinant of human affective processing and affective perceptions are often limited by declarative knowledge or established societal customs.
Approach:	They propose a multimodal benchmark that leverages LLM-generated provisional labels to isolate cross-cultural emotional distinctions.
Outcome:	The proposed benchmark captures cross-cultural emotional distinctions and derives reliable ground-truth annotations through human evaluation.

Multilingual Generation in Abstractive Summarization: A Comparative Study (2024.lrec-main)

Copied to clipboard

Jinpeng Li, Jiaze Chen, Huadong Chen, Dongyan Zhao, Rui Yan

Text Generation

Challenge:	Existing models for multilingual generation lack thorough analysis due to extensive linguistic diversity.
Approach:	They propose to classify multilingual generation methodologies into three categories based on their underlying modeling principles . they introduce an automatic metric to mitigate spurious correlations associated with language mixing .
Outcome:	The proposed model improves in high-resource, low-resourced, and zero-shot scenarios.

SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning (2025.emnlp-main)

Copied to clipboard

Yicheng Ji, Jun Zhang, Heming Xia, Jinpeng Chen, Lidan Shou, Gang Chen, Huan Li

Self-Instructed Derived Prompt Generation Meets In-Context Learning: Unlocking New Potential of Black-Box LLMs (2025.acl-long)

Challenge:	Video large language models (Vid-LLMs) rely on dense video token representations and require substantial memory and computational overhead in both prefilling and decoding.
Approach:	They propose a training-free speculative decoding framework that prunes up to 90% of video tokens to enable efficient speculation without sacrificing accuracy.
Outcome:	The proposed framework achieves 2.68 speedup on LLaVA-OneVision-72B and 2.11 speed up on Qwen2.5-VL-32B.

Copied to clipboard

Zhuo Li, Yuhao Du, Jinpeng Hu, Xiang Wan, Anningzhe Gao

Dialogue Summarization with Static-Dynamic Structure Fusion Graph (2023.acl-long)

Challenge:	Existing prompt refinement methods suffer from semantic inconsistencies and fail to maintain users’ real intent.
Approach:	They propose a self-instructed in-context learning framework that generates reliable derived prompts while keeping semantic consistency with original prompts.
Outcome:	The proposed framework generates better derived prompts and significantly enhances LLMs’ ability to deliver more effective responses.

Copied to clipboard

Shen Gao, Xin Cheng, Mingzhe Li, Xiuying Chen, Jinpeng Li, Dongyan Zhao, Rui Yan

StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason (2026.acl-long)

Challenge:	Dialogue summarization is a challenging task since it has dynamic interaction nature and inconsistent information flow among various speakers.
Approach:	They propose a Static-Dynamic graph-based Dialogue Summarization model which fuses prior knowledge from human expertise and adaptively learns the graph structure in an end-to-end learning fashion.
Outcome:	The proposed model can help people capture the highlights of a semi-structured and multi-participant dialogue without reviewing the complex dialogue context.

Copied to clipboard

Kaiyi Zhang, Ang Lv, Jinpeng Li, Yongbo Wang, Feng Wang, Haoyuan hu, Rui Yan

Responsible & Trustworthy NLP

Challenge:	Reinforcement learning with verifiable rewards (RLVR) approaches face two challenges: the near-miss reward problem and exploration stagnation.
Approach:	They propose an algorithm that partitions valid reasoning chains into reasoning steps using multi-level stepwise hints.
Outcome:	The proposed method outperforms competing RLVR enhancement methods across six mathematical benchmarks and two out-of-domain benchmarks.

BOLT: Benchmarking Open-World Learning for Text Classification (2026.findings-acl)

Copied to clipboard

Chuan Qin, Xi Chen, Jinpeng Li, Hengshu Zhu

Information Extraction & Text Mining

Challenge:	Existing benchmarks focus on out-of-distribution (OOD) detection while overlooking broader challenges such as the discovery of novel categories.
Approach:	They propose a unified Benchmark and evaluation toolkit supporting Open-world learning for text classification.
Outcome:	The proposed methods overfit training distributions and struggle to generalize to unseen classes.

GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement (2025.acl-long)

Copied to clipboard

Yifan Yang, Zheshu Song, Jianheng Zhuo, Mingyu Cui, Jinpeng Li, Bo Yang, Yexing Du, Ziyang Ma, Xunying Liu, Ziyuan Wang, Ke Li, Shuai Fan, Kai Yu, Wei-Qiang Zhang, Guoguo Chen, Xie Chen

Stylized Dialogue Generation with Feature-Guided Knowledge Augmentation (2023.findings-emnlp)

Challenge:	GigaSpeech 2 is a large-scale, multi-domain, multilingual speech recognition corpus for low-resource languages.
Approach:	They propose a large-scale, multi-domain, multilingual speech recognition corpus for low-resource languages and an automated pipeline for data crawling, transcription, and label refinement.
Outcome:	The proposed corpus reduces the word error rate for Thai, Indonesian, and Vietnamese on a realistic YouTube test set by 25% to 40% compared to Whisper large-v3.

Copied to clipboard

Jinpeng Li, Zekai Zhang, Xiuying Chen, Dongyan Zhao, Rui Yan

E-Bench: Towards Evaluating the Ease-of-Use of Large Language Models (2025.coling-main)

Challenge:	Existing methods synthesize pseudo data through back translation but lack guidance on target style features.
Approach:	They propose a knowledge-augmented stylized dialogue generation model with a feature-guided style knowledge selection module that utilizes context and response features.
Outcome:	The proposed model produces a satisfactory performance on two public benchmarks on both semantic and stylized levels.

Copied to clipboard

Zhenyu Zhang, Bingguang Hao, Jinpeng Li, Zekai Zhang, Dongyan Zhao

Language Models

Challenge:	E-Bench is a framework for easy-to-use research on large language models.
Approach:	They propose to evaluate the ease-of-use of large language models and construct an E-Bench . they simulate human use from synonymous and typographical perturbations .
Outcome:	The proposed model is able to resist synonymous expressions and typos and improves performance.

Improved Policy Optimization for Mixture-of-Experts Models: Importance Sampling and Rewarding from an Expert-Centric Perspective (2026.findings-acl)

Copied to clipboard

Yining Qian, Jinpeng Li, Fei Mi, Lifeng Shang, Xiang Zhang

Challenge:	Existing approaches to reinforcement learning (RL) suffer from training instability . existing approaches often ignore token-specific discrepancies in expert assignments .
Approach:	They propose to introduce expert-level importance sampling to reduce complexity of RL . they propose to leverage expert-centric granularity to ensure a rigorous alignment between reward signals and policy updates.
Outcome:	The proposed method outperforms strong baselines across reasoning tasks.

KG-RAG: Enhancing GUI Agent Decision-Making via Knowledge Graph-Driven Retrieval-Augmented Generation (2025.emnlp-main)

Copied to clipboard

Ziyi Guan, Jason Chun Lok Li, Zhijian Hou, Pingping Zhang, Donglai Xu, Yuzhi Zhao, Mengyang Wu, Jinpeng Chen, Thanh-Toan Nguyen, Pengfei Xian, Wenao Ma, Shengchao Qin, Graziano Chesi, Ngai Wong

GenDis: Generative-Discriminative Dual-View Co-Training for Generalized Category Discovery (2026.acl-long)

Challenge:	Recent advances in GUI agents have limited app-specific knowledge of complex mobile tasks.
Approach:	They propose a Knowledge Graph-driven Retrieval-Augmented Generation framework that transforms fragmented UTGs into structured vector databases for efficient real-time retrieval.
Outcome:	The proposed framework outperforms existing methods in a 75.8% success rate and 84.6% decision accuracy test across mobile apps.

Copied to clipboard

Xi Chen, Chuan Qin, Jinpeng Li, Shasha Hu, Chao Wang, Hengshu Zhu, Hui Xiong

Challenge:	Existing methods rely on one-hot discriminative supervision, leading to overfitting on seen classes and poor generalization to unseen ones.
Approach:	They propose a Generative–Discriminative Dual-View Co-Training framework that unifies discriminative classification and semantic label generation within an LLM.
Outcome:	The proposed framework outperforms existing methods on five benchmarks on the generalized category discovery (GCD) task.

Boundary Smoothing for Named Entity Recognition (2022.acl-long)

Copied to clipboard

Enwei Zhu, Jinpeng Li

Information Extraction & Text Mining

Challenge:	Named entity recognition models often encounter over-confidence issues . boundary smoothing is a method that re-assigns entity probabilities from annotated spans to the surrounding ones .
Approach:	They propose a method for regularizing entity probabilities from annotated spans to the surrounding ones.
Outcome:	The proposed method achieves better than or competitive with previous state-of-the-art systems on well-known benchmarks.

COSIGN: Contextual Facts Guided Generation for Knowledge Graph Completion (2024.naacl-long)

Copied to clipboard

Jinpeng Li, Hang Yu, Xiangfeng Luo, Qian Liu

Structured Data in NLP

Challenge:	Existing methods for knowledge graph completion (KGC) are limited in generality and scalability due to poor contextual facts.
Approach:	They propose a contextual facts collector and contextual facts organizer to enhance the inference ability of GM-based methods for various KGC tasks.
Outcome:	The proposed model outperforms state-of-the-art methods in terms of performance.

Envisioning Future from the Past: Hierarchical Duality Learning for Multi-Turn Dialogue Generation (2023.acl-long)

Copied to clipboard

Ang Lv, Jinpeng Li, Shufang Xie, Rui Yan

APLOT: Robust Reward Modeling via Adaptive Preference Learning with Optimal Transport (2025.emnlp-main)

Challenge:	Existing approaches to generate high quality responses rely on future text .
Approach:	They propose a hierarchical duality learning for dialogue to simulate human cognitive ability . they utilize hierarchically dualities at token hierarchy and utterance hierarchy to simulate duality .
Outcome:	The proposed model can generate high quality responses that connect both previous and follow-up dialogues.

Copied to clipboard

Zhuo Li, Yuege Feng, Dandan Guo, Jinpeng Hu, Anningzhe Gao, Xiang Wan

Robustness in NLP

Challenge:	Experimental results show that RLHF improves performance of Large Language Models . BT-based RMs struggle to distinguish between similar preference responses .
Approach:	They propose to enhance BT-based reward models by using an adaptive margin mechanism . they use semantic similarity and reward-predicted reward differences to adjust focus .
Outcome:	Experimental results show that the proposed method outperforms existing methods in both in-distribution and OOD settings.

VSTAR: A Video-grounded Dialogue Dataset for Situated Semantic Understanding with Scene and Topic Transitions (2023.acl-long)

Copied to clipboard

Yuxuan Wang, Zilong Zheng, Xueliang Zhao, Jinpeng Li, Yueqian Wang, Dongyan Zhao

Deep Span Representations for Named Entity Recognition (2023.findings-acl)

Challenge:	Existing benchmarks for video-grounded dialogues neglect the intrinsic attributes of multimodal dialogues, such as scene and topic transitions.
Approach:	They propose to use a large scale video-grounded scene&topic AwaRe dialogue dataset to study video-based dialogue understanding.
Outcome:	The proposed dataset shows that multimodal information and segments are important in video-grounded dialogue understanding and generation.

Copied to clipboard

Enwei Zhu, Yiyang Liu, Jinpeng Li

Psyche-R1: Towards Reliable Psychological LLMs through Unified Empathy, Expertise, and Reasoning (2026.acl-long)

Challenge:	Existing span-based NER systems shallowly aggregate token representations to span representations, causing performance degradations.
Approach:	They propose a method that shallowly aggregates token representations to span representations . DSpERT produces span representation of deep semantics with weight initialization .
Outcome:	The proposed model performs better than or competitive with state-of-the-art systems on six NER benchmarks.

Copied to clipboard

Chongyuan Dai, Jinpeng Hu, Hongchang Shi, Zhuo Li, Dan Guo, Xun Yang, Meng Wang

See the Forest for the Trees: Loosely Speculative Decoding via Visual-Semantic Guidance for Efficient Inference of Video LLMs (2026.acl-long)

Challenge:	Recent reasoning-augmented LLMs have demonstrated impressive capabilities across a wide range of domains owing to their exceptional text understanding capabilities.
Approach:	They propose a Chinese psychological LLM that integrates empathy, psychological expertise, and reasoning.
Outcome:	The proposed model produces over 75k high-quality psychological questions paired with detailed rationales, generated through and iterative prompt-rationale optimization procedure, along with 73k empathetic dialogues.

Copied to clipboard

Yicheng Ji, Jun Zhang, Jinpeng Chen, Cong Wang, Lidan Shou, Gang Chen, Huan Li