5 papers · 1 filter
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…
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…
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.…
MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization
Zhiyu Yang, Zihan Zhou, Shuo Wang +10
Scientific data visualization plays a crucial role in research by enabling the direct display of complex information and assisting researchers in identifying implicit patterns. Des…
UltraLink: An Open-Source Knowledge-Enhanced Multilingual Supervised Fine-tuning Dataset
Haoyu Wang, Shuo Wang, Yukun Yan +9
Open-source large language models (LLMs) have gained significant strength across diverse fields. Nevertheless, the majority of studies primarily concentrate on English, with only l…