collaborators

27 papers

cs.AI2026

Slides2MindMap: Reconstructing Cognitively Efficient Knowledge Hierarchies from Lecture Slides

Yuzhi Wang, Rongjun Ye, Shengyuan Chen +5

Generating mind maps from lecture slides can help learners efficiently assimilate fragmented knowledge, promising substantial benefits for intelligent education. However, dedicated…

cs.CL2026

Zero-Mem: Zero-Token Memory Operations for LLM Agents

Yilin Xiao, Zhehan Zhu, Yujing Zhang +8

LLM agents need memory to act consistently over long interactions, yet many systems use additional LLM calls to operate that memory. Generating intermediate records and mediating t…

cs.CL2026

ErrorLLM: Modeling SQL Errors for Text-to-SQL Refinement

Zijin Hong, Hao Chen, Zheng Yuan +6

Despite the remarkable performance of large language models (LLMs) in text-to-SQL (SQL generation), correctly producing SQL queries remains challenging during initial generation. T…

cs.CL2026

Benchmarking LLMs' Mathematical Reasoning with Unseen Random Variables Questions

Zijin Hong, Hao Wu, Su Dong +8

Recent studies have raised significant concerns regarding the reliability of current mathematics benchmarks, highlighting issues such as simplistic design and potential data contam…

cs.CL2026

MoG: Mixture of Experts for Graph-based Retrieval-Augmented Generation

Zheng Yuan, Chuang Zhou, Linhao Luo +4

Retrieval-augmented generation is intensively studied to ground large language models on external evidence. However, retrieving from a unified knowledge base could inevitably intro…

cs.CL2026

LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reasoning

Zerui Chen, Qinggang Zhang, Zhishang Xiang +5

Graph-based Retrieval-Augmented Generation (GraphRAG) advances flat document retrieval by structuring knowledge as relational graphs, enabling more coherent and effective reasoning…