arXiv (All)
open access
Beyond a Single Direction: Chain-of-Thought Disrupts Simple Steering of Refusal
Large reasoning models (LRMs) generate chain-of-thought (CoT) traces before producing final outputs, introducing a dynamic internal state that may complicate control mechanisms such as refusal. Unlike instruction-tuned LLMs, where refusal is mediated by a single directional subspace, refusal in larg
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
- The Gettier Intuition from South America to Asia#750240
- Breaking the Likelihood Trap: Variance-Calibrated Modulation for Large Language Model Decoding#926093
- When Upstream Messages Override Correct Answers: A Controlled Study of Multi-Agent LLM Collaboration#1132056
- From 'May' to 'Is': Certainty Distortion in Language Model Rewriting#1011128
- Interlacing the singularity, the diagram and the metaphor. Translated by Simon B. Duffy#710974
Record · ID 1142697
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