Unverified50% confidenceFactExact time
Information gain originates from decision theory and refers to the degree to which a test can reduce uncertainty about diagnostic hypotheses.
1
Sources
50%
Confidence
Long-term
Relevance
10/25/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDenser relevance judgments reduce the probability that correct results retrieved by a model are mistakenly judged as irrelevant, thereby improving evaluation reliability.77% similarUnverifiedThe potential benefits of decoupling judgment from execution include reducing main model token consumption, lowering average response latency, and making decision logic easier to audit and debug.77% similarUnverified丰富的上下文信息能收窄模型输出概率分布并减少幻觉，这一现象被称为「知识锚定效应」75% similarUnverifiedUsing disagreements among multiple models as an uncertainty signal is a low-cost, automatable means of quality diagnosis.73% similarUnverified结构化、上下文丰富的提示不仅提升模型输出质量，也能显著降低安全分类器的误触发率72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1097670API
curl https://kongchang.com/api/v1/knowledge/claims/1097670MCP
get_claim(id=1097670)