Unverified50% confidenceFactExact time
Beam search aims to generate the candidate sequence with the highest probability, whereas MBR decoding selects the candidate with the minimum expected translation error.
1
Sources
50%
Confidence
Long-term
Relevance
8/22/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMulti-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.62% similarUnverifiedReranking uses a Cross-Encoder model to score candidate documents retrieved in the initial retrieval pairwise, then fine-ranks the Top-K to feed into the LLM.60% similarVerified混合检索（Hybrid Search）将向量检索与BM25关键词检索的结果通过RRF（倒数排名融合）等算法合并，兼顾语义理解与精确匹配60% similarUnverifiedTop-K检索是从向量数据库中取相似度最高的前K个片段作为候选内容60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/786973API
curl https://kongchang.com/api/v1/knowledge/claims/786973MCP
get_claim(id=786973)