arXiv (All)
open access
Over-Refusal and Representation Subspaces: A Mechanistic Analysis of Task-Conditioned Refusal in Aligned LLMs
Aligned language models that are trained to refuse harmful requests also exhibit over-refusal: they decline safe instructions that seemingly resemble harmful instructions. A natural approach is to ablate the global refusal direction, steering the hidden-state vectors away or towards the harmful-refu
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
- From Refusal Tokens to Refusal Control: Discovering and Steering Category-Specific Refusal Directions#1109790
- COLLATOR: Compositional Multi-Agent Orchestration with Counterfactual Reinforcement Learning#1131535
- Worms, Stages, and Sometimes Neither: A Contextualist Semantics for Four-Dimensionalism#725293
- Validation of Large Language Models in Healthcare: a Scoping Review#1090084
- Applications, Challenges, and Future Directions of Large Language Models in Health Care Communication: Scoping Review.#320608
Record · ID 820399
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