arXiv (All)
open access
Length Penalties Make Chain-of-Thought Less Monitorable
Recent work trains reasoning models with length penalties to curb overthinking and cut inference cost. We show that these penalties make the chain of thought less monitorable. A length-compressed model still lets misleading hints steer its answers, but it less often verbalizes their influence. We tr
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 Ideate for Scientific Impact#1077729
- Apertures, Draw, and Syntax: Remodeling Attention#703573
- Expectational v. Instrumental Reasoning: What Statistics Contributes to Practical Reasoning#167317
- Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation Enforcement#1050426
- Inferring to the Best Explanation from Uncertain Evidence#75890
Record · ID 1050911
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