arXiv (All)
open access
When Do Models Admit They Are Wrong? Failure Disclosure Is Unstable Under Reinforcement Learning
Outcome-based reinforcement learning can produce models with similar task performance but very different ways of communicating about their mistakes. We study failure disclosure: whether a model admits that an attempted solution failed rather than staying silent or presenting it as successful. Across
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
- A Unified Mechanistic Analysis of Knowledge- and Safety-Based Refusals#820772
- Outcome Monitors: Recovery Affordances for Silent Tool Failures#471320
- Real-time cognitive-affective dynamics of failure feedback in a technology-based learning task#384297
- Real-time cognitive-affective dynamics of failure feedback in a technology-based learning task.#281111
- A Compression-Based Account of Biases Towards Simpler Explanations#276733
Record · ID 1117932
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