Retrieval-Feedback-Driven Distillation and Preference Alignment for Efficient LLM-based Query Expansion

Documenti analoghi

• Automatic In-Domain Exemplar Construction and LLM-Based Refinement of Multi-LLM Expansions for Query Expansion
  di: Li, Minghan, et al.
  Pubblicazione: (2026)
• GLIER: Generative Legal Inference and Evidence Ranking for Legal Case Retrieval
  di: Li, Minghan, et al.
  Pubblicazione: (2026)
• S2G-RAG: Structured Sufficiency and Gap Judging for Iterative Retrieval-Augmented QA
  di: Li, Minghan, et al.
  Pubblicazione: (2026)
• Can Query Expansion Improve Generalization of Strong Cross-Encoder Rankers?
  di: Li, Minghan, et al.
  Pubblicazione: (2023)
• Clue-RAG: Towards Accurate and Cost-Efficient Graph-based RAG via Multi-Partite Graph and Query-Driven Iterative Retrieval
  di: Su, Yaodong, et al.
  Pubblicazione: (2025)