7 papers
When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors
Yuqing Yang, Qi Zhu, Zhen Han +5
While large language models (LLMs) perform well on table tasks, they still make data referencing errors (DREs), i.e., incorrectly citing or omitting table values, despite understan…
EpiBench: Benchmarking Multi-turn Research Workflows for Multimodal Agents
Xuan Dong, Huanyang Zheng, Tianhao Niu +7
Scientific research follows multi-turn, multi-step workflows that require proactively searching the literature, consulting figures and tables, and integrating evidence across paper…
Train Less, Learn More: Adaptive Efficient Rollout Optimization for Group-Based Reinforcement Learning
Zhi Zhang, Zhen Han, Costas Mavromatis +9
Reinforcement learning (RL) plays a central role in large language model (LLM) post-training. Among existing approaches, Group Relative Policy Optimization (GRPO) is widely used, e…
SQL-Trail: Multi-Turn Reinforcement Learning with Interleaved Feedback for Text-to-SQL
Harper Hua, Zhen Han, Zhengyuan Shen +9
While large language models (LLMs) have substantially improved Text-to-SQL generation, a pronounced gap remains between AI systems and human experts on challenging benchmarks such…
BYOKG-RAG: Multi-Strategy Graph Retrieval for Knowledge Graph Question Answering
Costas Mavromatis, Soji Adeshina, Vassilis N. Ioannidis +6
Knowledge graph question answering (KGQA) presents significant challenges due to the structural and semantic variations across input graphs. Existing works rely on Large Language M…
Hierarchical Lexical Graph for Enhanced Multi-Hop Retrieval
Abdellah Ghassel, Ian Robinson, Gabriel Tanase +6
Retrieval-Augmented Generation (RAG) grounds large language models in external evidence, yet it still falters when answers must be pieced together across semantically distant docum…