9 papers
SPEAR: Distilling Domain-Adaptive Reasoning Skeletons via Sequential Symbolic Alignment in Reinforcement Learning
Zhuochun Li, Yuelyu Ji, Yiming Zeng +1
Reinforcement learning-based knowledge distillation has the potential to transfer complex reasoning from teacher to student models, yet it currently faces a critical dilemma: resea…
Retrieval--Reasoning Processes for Multi-hop Question Answering: A Four-Axis Design Framework and Empirical Trends
Yuelyu Ji, Zhuochun Li, Rui Meng +1
Multi-hop question answering (QA) requires systems to iteratively retrieve evidence and reason across multiple hops. While recent RAG and agentic methods report strong results, the…
Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry
Zhuochun Li, Yong Zhang, Ming Li +8
Large language models (LLMs) are widely used as reference-free evaluators via prompting, but this "LLM-as-a-Judge" paradigm is costly, opaque, and sensitive to prompt design. In th…
Curriculum Guided Reinforcement Learning for Efficient Multi Hop Retrieval Augmented Generation
Yuelyu Ji, Rui Meng, Zhuochun Li +1
Retrieval-augmented generation (RAG) grounds large language models (LLMs) in up-to-date external evidence, yet existing multi-hop RAG pipelines still issue redundant subqueries, ex…
Memory-Aware and Uncertainty-Guided Retrieval for Multi-Hop Question Answering
Yuelyu Ji, Rui Meng, Zhuochun Li +1
Multi-hop question answering (QA) requires models to retrieve and reason over multiple pieces of evidence. While Retrieval-Augmented Generation (RAG) has made progress in this area…
Traffic Light or Light Traffic? Investigating Phrasal Semantics in Large Language Models
Rui Meng, Ye Liu, Lifu Tu +3
Phrases are fundamental linguistic units through which humans convey semantics. This study critically examines the capacity of API-based large language models (LLMs) to comprehend…
ReasoningRank: Teaching Student Models to Rank through Reasoning-Based Knowledge Distillation
Yuelyu Ji, Zhuochun Li, Rui Meng +1
Reranking documents based on their relevance to a given query is a critical task in information retrieval. Traditional reranking methods often lack transparency and rely on proprie…
Learning from Committee: Reasoning Distillation from a Mixture of Teachers with Peer-Review
Zhuochun Li, Yuelyu Ji, Rui Meng +1
While reasoning capabilities typically emerge in large language models (LLMs) with tens of billions of parameters, recent research focuses on improving smaller open-source models t…
RAG-RLRC-LaySum at BioLaySumm: Integrating Retrieval-Augmented Generation and Readability Control for Layman Summarization of Biomedical Texts
Yuelyu Ji, Zhuochun Li, Rui Meng +7
This paper introduces the RAG-RLRC-LaySum framework, designed to make complex biomedical research understandable to laymen through advanced Natural Language Processing (NLP) techni…