註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

cv usk
@cv_usk
AI / Software Research Notes AI Agent, LLMOps, MLOps, Software Architecture 投稿は個人の意見です。
加入 May 2026
286 正在關注    474 粉絲
The weak link in RAG may be the retriever, not the generator. This paper proposes finding evidence by navigating documents instead of searching an index. Title: Retriever-Free Retrieval: Navigating Documents with Decision Models URL: DecisionRAG organizes the corpus as a tree and lets a decision model (Jev) judge many candidates at once, expanding only the top branches. No task-specific training and no first-stage retriever. Three highlights: 🧭 Shared context makes scores comparable Candidates are judged together, so a plausible one scores lower when a clearly better one is present. On MultiDoc2Dial, scoring passages together instead of page by page lifts R@1 from 36.7% to 44.4%. 🌲 Navigation that scales logarithmically With a branching factor of 100, 10^9 passages need about five stages, roughly one second. On Natural Questions, keeping about 15% of clusters matches scoring all pages at about one-fifth of the cost. ⚡ On par or better than GPT-5 reranking, faster and cheaper Natural Questions Hit@1 is 65.4 vs. 60.8 for GPT-5 reranking. Latency is 0.68-1.76 s vs. 11.8-15.0 s. Pruning is irreversible, though, and quality depends on the hierarchy. It reframes retrieval as exploration rather than reranking. #RAG# #InformationRetrieval#
顯示更多