arXiv (All)
open access
See it, Say it, Sorted: Mechanistic Diagnosis and Parameter-Space Mitigation of Emergent Misalignment in LLMs
Safety-aligned LLMs can exhibit emergent misalignment (EM): narrow domain adaptation unexpectedly triggers catastrophic safety failures across unrelated domains. Prior static analyses leave training dynamics unmapped, while existing defenses rely on heuristics that degrade utility. We present a dyna
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
- Validating LLM-Modernized Scientific Software Through Differential Fault Injection#609684
- Validating LLM-Modernized Scientific Software Through Differential Fault Injection#458251
- AnchorBench: A Multi-Pathway Benchmark for the Anchoring Effect in LLMs#458335
- If It's Not Buggy, Don't Fix It: On the Dynamics of Iterative Bug-fixing with LLMs#673594
- SWE-Test: Benchmarking LLM Vulnerability Discovery via Input Prediction#668140
Record · ID 1129575
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