3 papers
cs.CL2026
CompactRAG: Reducing LLM Calls and Token Overhead in Multi-Hop Question Answering
Hao Yang, Zhiyu Yang, Xupeng Zhang +3
Retrieval-augmented generation (RAG) has become a key paradigm for knowledge-intensive question answering. However, existing multi-hop RAG systems remain inefficient, as they alter…
cs.CL2025
Why Stop at One Error? Benchmarking LLMs as Data Science Code Debuggers for Multi-Hop and Multi-Bug Errors
Zhiyu Yang, Shuo Wang, Yukun Yan +1
LLMs are transforming software development, yet current code generation and code repair benchmarks mainly assess syntactic and functional correctness in simple, single-error cases.…
cs.CL2025
Rethinking the Chain-of-Thought: The Roles of In-Context Learning and Pre-trained Priors
Hao Yang, Zhiyu Yang, Yunjie Zhang +2
Chain-of-Thought reasoning has emerged as a pivotal methodology for enhancing model inference capabilities. Despite growing interest in Chain-of-Thought reasoning, its underlying m…