Papers by Jingyang Li

Make Prompt-based Black-Box Tuning Colorful: Boosting Model Generalization from Three Orthogonal Perspectives (2024.lrec-main)

Copied to clipboard

Qiushi Sun, Chengcheng Han, Nuo Chen, Renyu Zhu, Jingyang Gong, Xiang Li, Ming Gao

Language Models

Challenge:	Large language models (LLMs) have shown increasing power on NLP tasks. however, tuning these models for downstream tasks usually requires exorbitant costs.
Approach:	They propose a black-box tuning technique that optimizes task-specific prompts without accessing gradients and hidden representations.
Outcome:	The proposed method improves performance under few-shot learning scenarios.

Message Passing on Semantic-Anchor-Graphs for Fine-grained Emotion Representation Learning and Classification (2024.emnlp-main)

Copied to clipboard

Pinyi Zhang, Jingyang Chen, Junchen Shen, Zijie Zhai, Ping Li, Jie Zhang, Kai Zhang

Multimodality

Challenge:	Emotion classification is an important task with applications in education, virtual reality, and robotics.
Approach:	They propose to use token embeddings to generate a "semantic-anchor graph" using semantic anchors, sentences can be projected onto them to form a graph .
Outcome:	Empirically, the proposed system can generate meaningful semantic anchors and discriminative graph patterns for different emotion.

Repo4QA: Answering Coding Questions via Dense Retrieval on GitHub Repositories (2022.coling-1)

Copied to clipboard

Minyu Chen, Guoqiang Li, Chen Ma, Jingyang Li, Hongfei Fu

Natural Language Interfaces

Challenge:	Stack Overflow and GitHub are open source communities that are gaining popularity . developers need to raise programming questions in coding forums and navigate to GitHub repositories .
Approach:	They propose a questionrepository matching task that bridges the gap between repositories and real-world coding questions.
Outcome:	The proposed model outperforms state-of-the-art methods on coding questions and repositories . it can find suitable coding repositoriels and bridge the gap between them .

ZoomRAG: Hierarchical Random-walk Zooming across Multi-scale Information Graphs for Fast and Accurate RAG (2026.findings-acl)

Copied to clipboard

Xianming Hu, Jingyang Chen, Bin Tang, Yihe Liu, Yihong Huang, Hongbo Zhao, Nuoyi Chen, Jie Zhang, Ping Li, Kai Zhang

Structured Data in NLP

Challenge:	retrieval-augmented generation (RAG) is a powerful tool for NLP applications . but it is challenging to encode large knowledge bases as compact offline structures .
Approach:	They propose a coarse-to-fine hierarchical graph inference method that uses random walks to retrieve information from a corpus of documents.
Outcome:	The proposed method reduces offline indexing costs and accelerates retrieval.

AutoETER: Automated Entity Type Representation for Knowledge Graph Embedding (2020.findings-emnlp)

Copied to clipboard

Guanglin Niu, Bo Li, Yongfei Zhang, Shiliang Pu, Jingyang Li

Semantic Text Processing

Challenge:	Existing knowledge graphs are incomplete whether they are constructed manually or automatically, limiting the effectiveness when exploited for downstream applications.
Approach:	They propose a KGE framework with an automatic type embedding mechanism which can be easily integrated into any existing KGE model.
Outcome:	The proposed model can model and infer all the relation patterns and complex relations compared to state-of-the-art models on four datasets.

Towards Generalized Open Information Extraction (2022.findings-emnlp)

Copied to clipboard

Bowen Yu, Zhenyu Zhang, Jingyang Li, Haiyang Yu, Tingwen Sun, Jian Liu, Yongbin Li, Bin Wang

Information Extraction & Text Mining

Challenge:	Open Information Extraction (OpenIE) models are evaluated on in-domain test sets aside from the training corpus, which violates the initial task principle of domain-independence.
Approach:	They propose to generalize OpenIE over unseen target domains with different data distributions from source training domains.
Outcome:	The proposed method beats the previous methods in both in- and out-of-domain settings by 6.0% in F1 score absolutely.

Unsolvable Problem Detection: Robust Understanding Evaluation for Large Multimodal Models (2025.acl-long)

Copied to clipboard

Atsuyuki Miyai, Jingkang Yang, Jingyang Zhang, Yifei Ming, Qing Yu, Go Irie, Yixuan Li, Hai Helen Li, Ziwei Liu, Kiyoharu Aizawa

Robustness in NLP

Challenge:	Multiple-choice question answering (MCQA) is widely used to assess the understanding capability of Large Multimodal Models (LMMs).
Approach:	They propose a task to evaluate the robust understanding capability of Large Multimodal Models (LMMs) they introduce a benchmark to assess performance across various ability dimensions .
Outcome:	The proposed model can withhold answers when encountering unsolvable problems of MCQA, proving it understands the answer.

Think Earlier, Not Longer: Prompt Optimization via Reducing Unhealthy Exploration (2026.findings-acl)

Copied to clipboard

Ling-I Wu, Minyu Chen, Jingyang Li, Xi Chang, Guoqiang Li

Responsible & Trustworthy NLP

Challenge:	Existing approaches to improve reasoning performance ignore the presence of unhealthy exploration that increases token usage without contributing to effective problem-solving.
Approach:	They propose an entropy-dynamics-aware prompt optimization framework that trains a lightweight optimizer to generate concise clarifications.
Outcome:	The proposed framework reduces ambiguity-induced early-stage uncertainty while preserving the model's reasoning capabilities.

CodeEvo: Interaction-Driven Synthesis of Code-centric Data through Hybrid and Iterative Feedback (2026.acl-long)

Copied to clipboard

Qiushi Sun, Jingyang Gong, Lei Li, Qipeng Guo, Fei Yuan

Challenge:	Existing methods for generating instruction-code pairs rely on rigid heuristics and are labor-intensive.
Approach:	They propose a dual-agent architecture that integrates a Coder and a Reviewer to orchestrate the generation trajectory.
Outcome:	The proposed architecture outperforms baselines on a large-scale dataset of instruction-code pairs with stepped difficulty levels.

Structured Optimal Brain Pruning for Large Language Models (2024.emnlp-main)

Copied to clipboard

Jiateng Wei, Quan Lu, Ning Jiang, Siqi Li, Jingyang Xiang, Jun Chen, Yong Liu

Language Models

Challenge:	Existing pruning methods for Large Language Models rely on unstructured pruning or require special hardware to accelerate computation.
Approach:	They propose a retraining-free structured pruning method called SoBP . they evaluate the effectiveness of SoBP across 14 models from 3 LLM families .
Outcome:	The proposed method outperforms current state-of-the-art pruning methods on 8 datasets.

Fine-Grained Image-Text Alignment in Medical Imaging Enables Explainable Cyclic Image-Report Generation (2024.acl-long)

Copied to clipboard

Wenting Chen, Linlin Shen, Jingyang Lin, Jiebo Luo, Xiang Li, Yixuan Yuan

Responsible & Trustworthy NLP

Challenge:	Fine-grained vision-language models (VLMs) have been widely used for inter-modality local alignment between fixed patches and textual words, but they provide incomplete representations of lesions.
Approach:	They propose an Adaptive patch-word Matching model to correlate chest X-ray (CXR) image regions with words in medical reports and apply it to CXR-report generation to provide explicit explanations.
Outcome:	The proposed model correlates chest X-ray image regions with words in medical reports and provides explanations for the generation process.