arXiv (All)
open access
Entropy Regularization: A Free Correction to Cross-Entropy for Verified Demonstrations
Large language models are often post-trained on expert demonstrations using cross-entropy (CE), even when the downstream objective is not to imitate the demonstrated solution but to produce any output accepted by a verifier. This mismatch is seen in verifiable domains with multiple correct solutions
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Learning to Solve, Forgetting to Retain: Correct-Set Turnover in RLVR#1131563
- Visual sensitivity is not claim retractability: persistence-aware credit assignment for multimodal reinforcement learning#1131773
- Convex Density Constraints for Computing Plausible Counterfactual Explanations#779200
- AEGIS: Anchor-Enforced Gradient Isolation for Knowledge-Preserving Vision-Language-Action Fine-Tuning#1156330
- Reinforcing Consistency in Video MLLMs with Structured Rewards#629964
Record · ID 1104771
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive