This paper proposes four guidelines and two novel data ordering methods (STR and SAW) to systematically optimize data organization, significantly enhancing the stability and performance of LLM trainin…

SkillPager is a novel two-stage framework that efficiently selects minimal, execution-sufficient context from large procedural skill documents by leveraging typed semantic nodes, significantly reducin…

The paper introduces a novel, training-free method to automatically generate fine-grained evaluation rubrics for LLM-as-a-Judge, and further proposes an iterative fine-tuning strategy that significant…

The paper introduces Chunk-Level Guided Generation, a training-free method that uses an off-the-shelf large language model (LLM) as a process scorer to guide small model generation, achieving performa…

This study systematically analyzes strategies for creating reliable multilingual LLMs-as-a-judge, finding that fine-tuning smaller models with in-domain data is effective, while zero-shot evaluation w…

CoHyDE introduces an iterative co-training framework that jointly optimizes an LLM rewriter and a dense encoder, significantly improving tool retrieval accuracy for LLM agents, especially on vague que…

The paper proposes InSemRAG, an enhanced RAG framework that improves retrieval accuracy and knowledge integrity by incorporating intent-aware retrieval and semantics-preserving chunking, achieving sta…

The paper introduces LongJudgeBench, a new benchmark designed to evaluate the reliability of LLM judges specifically for complex, long-form output evaluation, revealing significant instability gaps in…

The paper introduces SkillBrew, a multi-objective framework that treats skill bank curation as a constrained optimization problem to build efficient and well-curated skill repositories for LLM agents.

The paper introduces an LLM-based pipeline that tags learning resources with structured competencies, achieving strong performance while providing traceable evidence and leveraging graph constraints.

The paper proposes DART, a test-time adaptation method that enhances zero-resource dense retrieval reranking by adaptively tuning a bilinear scoring matrix using pseudo-positive and pseudo-negative ex…

SIRIUS-SQL introduces a robust multi-candidate text-to-SQL system that addresses weaknesses in candidate generation, error handling, and selection, achieving state-of-the-art performance on complex be…

The paper proposes a graph-constrained approach to scale multi-hop training data by decoupling path discovery from path verbalization, significantly expanding the usable corpus size for LLMs.

The paper introduces a robust four-stage NLP framework that uses schema-constrained LLMs and ESCO vocabulary to accurately extract and align educational competencies with labor market demands, quantif…

This paper proposes CompRank, a token-efficient reranking framework for large language models that reduces redundant computation and achieves strong reranking performance.

The paper introduces HRBench, a unified and comprehensive evaluation framework for systematically benchmarking and comparing various thinking-mode switching strategies in hybrid-reasoning LLMs.

LongTraceRL addresses long-context reasoning challenges by generating highly challenging training data and introducing a fine-grained rubric reward, significantly improving evidence-grounded reasoning…

This study systematically evaluates a wide range of chunking methods for Retrieval-Augmented Generation (RAG) to assess their effectiveness and highlight the overlooked challenges associated with chun…