Back to home

Tag

LLM safety

2 articles

Policy Invariance as a Better LLM Judge Test
Research/May 12

Policy Invariance as a Better LLM Judge Test

This paper argues that accuracy alone is not enough to trust LLM safety judges, and proposes policy invariance as a reliability test.

ASMR-Bench Tests Sabotage Detection in ML Code
Research/Apr 20

ASMR-Bench Tests Sabotage Detection in ML Code

ASMR-Bench probes whether auditors can spot subtle sabotage in ML research codebases, and the answer so far is: not reliably.