Unverified50% confidenceFactExact time
LLM-IRA actively selects document pairs on which multiple retrievers' scores disagree most, asks the LLM to give a preference judgment, and then learns fusion weights for each retriever accordingly.
1
Sources
50%
Confidence
Long-term
Relevance
10/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLLM 与形式化证明系统结合主要有生成式（Generative）和搜索引导式（Search-Guided）两种范式65% similarUnverifiedMulti-query retrieval uses an LLM to automatically generate 3–5 semantically equivalent but differently phrased variant queries for the same question, retrieves results for each separately, and takes the union to improve recall.61% similarUnverifiedThis DFS method uses a multi-select pop-up window to let users check options, retaining selected branches while directly pruning unselected ones.60% similarUnverifiedMulti-route recall means simultaneously using multiple retrieval strategies (such as vector retrieval, BM25 keyword retrieval, knowledge graph retrieval, etc.) to recall candidate sets separately, then merging and deduplicating them for unified re-ranking, to compensate for the blind spots of any single retrieval method.60% similarUnverifiedThe Plan-then-Retrieve (PtR) paradigm lets the LLM first generate several abstract tool stubs (Abstract Tool Stubs) based on user intent as retrieval queries, then match real tools in the registry accordingly.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1114243API
curl https://kongchang.com/api/v1/knowledge/claims/1114243MCP
get_claim(id=1114243)