Unverified50% confidenceReleaseExact time
Microsoft released a small language model called Microsoft-Decision-1, designed specifically to return calibrated probability scores one by one for a fixed set of candidate options, rather than generating text or performing complex reasoning.
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMicrosoft Foundry's Model Router routes prompts to the most suitable language model, rather than invoking the most powerful model for every request.64% similarUnverified微软的Dafny语言用于形式化验证代码正确性63% similarUnverifiedDrex 1.5 returns a probability value for each candidate option rather than generating natural-language text61% similarVerifiedThe output of large language models is fundamentally probabilistic text generation, and a single rephrasing of a prompt can change field names, nesting levels, or enumeration values in the output without triggering compile-time or static analysis warnings.61% similarVerifiedText watermarking is a proactive scheme that makes slight, rule-based adjustments to the probability distribution of a language model during the generation of each token, causing the output text to carry a signature that can be recovered algorithmically.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/998843API
curl https://kongchang.com/api/v1/knowledge/claims/998843MCP
get_claim(id=998843)