arXiv (All)
open access
HeadEdit: Calibrating Language Model Behavior Through the Frozen Unembedding Matrix
Alignment does not eliminate behavioral errors in language models. Models may still refuse benign requests, call unnecessary tools, or yield to false user claims. Current methods mitigate such errors as a computation problem, and rarely explore if the desired behavior is already encoded in the model
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
- Representational alignment yields generalizable safety in language models#926872
- CALIBURN: Self-Calibrated LLM Unlearning Alignment#821781
- Asymptotic Universal Alignment: A New Alignment Framework via Test-Time Scaling#1141471
- Relative Density Ratio Optimization for Stable and Statistically Consistent Model Alignment#1116246
- COEC: Calibrated Orthogonal-Equivalence Compensation for Structured Pruning of Large Language Models#662308
Record · ID 1156105
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