Tag
ReFact proposes an adaptive fact-restatement citation framework that trains LLMs to decide when reasoning steps need contextual grounding, improving faithfulness and compactness in chain-of-thought reasoning while reducing token consumption.
This paper presents a candidate-constrained RAG system for the LongEval-RAG task at CLEF 2026, combining deterministic provenance tracking with passage retrieval, query expansion, pseudo-relevance feedback, reciprocal rank fusion, evidence reranking, and citation-aware aggregation. An ablation study of ten pipeline variants shows that a rule-based chunking pipeline with sentence-level neural selection achieves the best performance.