Unverified50% confidenceFactExact time
The outcome reward model (ORM) grants rewards only based on the correctness of the final answer; it is simple to implement but provides a sparse signal, making it hard for the model to learn correct reasoning steps from incorrect answers.
1
Sources
50%
Confidence
Long-term
Relevance
10/24/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe o-series models score each intermediate reasoning step individually using a Process Reward Model, rather than relying solely on the correctness of the final result.72% similarUnverifiedFine-tuning increases how often the model gets the answer right, not the trustworthiness of structured output; whether from a base model or a fine-tuned model, what is returned is merely a candidate answer.71% similarUnverifiedIf rewards target only final outcomes, the model tends to take shortcuts and memorize solutions for specific scenarios.70% similarUnverifiedIn LLM post-training, the model directly spews intermediate reasoning steps that should have been hidden to the user, or during RL reward computation, the reward model that should only evaluate the final answer sees the reasoning process, thereby distorting the optimization direction.69% similarUnverifiedWhen an LLM is asked to evaluate its own output, the scoring process shares the same model parameters and knowledge deficiencies as answer generation, creating circular dependence and failing to provide a verification signal independent of the answer.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1093142API
curl https://kongchang.com/api/v1/knowledge/claims/1093142MCP
get_claim(id=1093142)