arXiv (All)
open access
Refusal Is Not Robustness: Measuring Harmful Reachability in Autoregressive Language Models
LLM safety evaluations via jailbreaking typically index on attack success rate (ASR): whether a generated response violates safeguards. However, ASR only evaluates sampled outputs and provides little information on the underlying generation process. Autoregressive language models define distribution
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
- RAG-Safety-Bench: Reliable Evaluation of Retrieval-Augmented LLM Safety#999446
- Representational alignment yields generalizable safety in language models#926872
- When Failures Propagate: Causal Failure Attribution in Agentic Retrieval-Augmented Generation#659189
- When Failures Propagate: Causal Failure Attribution in Agentic Retrieval-Augmented Generation#657053
- LLM Alignment--Utility Asymmetry under Semantic-Preserving Transformations#1117048
Record · ID 1386725
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