DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillation

Documenti analoghi

• How Good are LLM-based Rerankers? An Empirical Analysis of State-of-the-Art Reranking Models
  di: Abdallah, Abdelrahman, et al.
  Pubblicazione: (2025)
• Wrong Answers Can Also Be Useful: PlausibleQA -- A Large-Scale QA Dataset with Answer Plausibility Scores
  di: Mozafari, Jamshid, et al.
  Pubblicazione: (2025)
• HintEval: A Comprehensive Framework for Hint Generation and Evaluation for Questions
  di: Mozafari, Jamshid, et al.
  Pubblicazione: (2025)
• Exploring Hint Generation Approaches in Open-Domain Question Answering
  di: Mozafari, Jamshid, et al.
  Pubblicazione: (2024)
• Question Difficulty Estimation for Large Language Models via Answer Plausibility Scoring
  di: Mozafari, Jamshid, et al.
  Pubblicazione: (2026)