Papers by Mingchen Li

9 papers
Harmful Factuality: LLMs Correcting What They Shouldn’t (2026.findings-eacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are trained for factual accuracy, but can conflict with the critical demand for source fidelity.
Approach: They propose a reproducible framework to elicit and measure HFH using controlled entity-level perturbations and strategic entity selection.
Outcome: The proposed framework reduces HFH rates by 50% across summarization, rephrasing, and QA tasks.
Data Interpreter: An LLM Agent for Data Science (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) excel in various domains but face challenges when applied to data science workflows due to their complex, multi-stage nature.
Approach: They propose a hierarchical graph-based agent that represents complexity and a progressive strategy for step-by-step verification, refinement, and consistent context management.
Outcome: The proposed agent surpasses state-of-the-art baselines on the MATH dataset and performs better on InfiAgent-DABench.
Semantic Structure Based Query Graph Prediction for Question Answering over Knowledge Graph (2022.coling-1)

Copied to clipboard

Challenge: Existing approaches for query graph generation ignore the semantic structure of a question . Existing methods ignore the structure of the question, resulting in noisy query graph candidates.
Approach: They propose to build query graphs from natural language questions to predict semantic structure of a question.
Outcome: The proposed method can predict the semantic structure of a question using six semantic structures from common questions in KGQA.
A Hierarchical N-Gram Framework for Zero-Shot Link Prediction (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to zero-shot link prediction use textual features of relations as auxiliary information to improve the encoded representation.
Approach: They propose a Hierarchical N-gram framework for Zero-Shot Link Prediction that leverages character n-gram information for ZSLP.
Outcome: The proposed method achieves state-of-the-art on two standard ZSLP datasets.
Efficient and Effective Internal Memory Retrieval for LLM-Based Healthcare Prediction (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to ground large language models in external knowledge are limited by hallucinations and a lack of granular medical context.
Approach: They propose a framework that replaces external retrieval with internal, key-based knowledge access by encoding clinical information directly into the model’s parameter space.
Outcome: The proposed framework achieves state-of-the-art performance across four benchmark healthcare outcome prediction datasets.
RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs in Medicine (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for retrieving medical textual knowledge Graphs struggle to perform well, a study finds . existing methods struggle to provide accurate answers to complex questions, he says .
Approach: They synthesize user queries integrating diverse topological structures, relational information, and complex textual descriptions.
Outcome: a new dataset for medical textual knowledge graphs shows that existing methods struggle to perform well . main bottlenecks lie in the scarcity of existing medical TKGs and the limited expressiveness of their topological structures .
DP-GTR: Differentially Private Prompt Protection via Group Text Rewriting (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for prompt privacy focus on document-level rewriting, neglecting rich, multi-granular representations of text.
Approach: a framework that leverages local differential privacy and composition theorem via group text rewriting is proposed . the framework is compatible with existing rewrite techniques and is publicly available at anonymous.4open.science for reproducibility.
Outcome: DP-GTR is the first framework to integrate document-level and word-level information while exploiting in-context learning to improve privacy and utility.
Knowledge Graph Pooling and Unpooling for Concept Abstraction (2025.coling-main)

Copied to clipboard

Challenge: Knowledge graph embedding (KGE) aims to embed entities and relations as vectors in a continuous space.
Approach: They propose a framework with KG Pooling and unpooling and Contrastive Learning to abstract and encode latent concepts for better KG prediction.
Outcome: The proposed framework outperforms baselines on link prediction task.
VenusFactory: An Integrated System for Protein Engineering with Data Retrieval and Language Model Fine-Tuning (2025.acl-demo)

Copied to clipboard

Challenge: Pre-trained protein language models have been used in protein engineering, but their adoption is limited due to data collection, task benchmarking, and application challenges.
Approach: They propose a versatile engine that integrates biological data retrieval, standardized task benchmarking, and modular fine-tuning of PLMs.
Outcome: The proposed engine integrates biological data retrieval, task benchmarking, and modular fine-tuning of PLMs.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations