Unverified50% confidenceBenchmarkExact time
After keyword hints were introduced, the 1B model went from always answering asking_questions to usually selecting the correct stage, while the 4B model sometimes disagreed with the hints, which the author believes indicates the model is making its own judgment.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSemantic models answer aggregation-type questions (such as rankings and counts), while ontologies answer relationship-type questions (such as multi-hop relationship queries)71% similarUnverifiedDecision models do not generate text; instead, given an input state and a set of named questions, they return typed answers with probabilities in a single forward pass.69% similarUnverifiedThe generation chain uses the Pydantic model CitedAnswer to constrain the output structure, containing four fields: answer, citations, confidence, and needs_clarification.69% similarUnverifiedThe trained 4B-parameter model outperforms all 7B open-source math-specialized models evaluated on the counterexample generation task and remains competitive with six frontier commercial APIs.68% similarVerifiedExplicitly instructing the model via prompt to answer only based on the provided context and to respond with "I don't know" if the answer is not present can mitigate hallucination (grounding).68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1033315API
curl https://kongchang.com/api/v1/knowledge/claims/1033315MCP
get_claim(id=1033315)