3 citations · 5 across the 4 of their papers we have counts for
3 papers · 1 filter
Automated Researchers Can Mitigate Well-characterized Alignment Failures
Chen Yueh-Han, Jiaxin Wen, Jan Hendrik Kirchner
Automating alignment research may accelerate progress toward aligned AI, but whether it does is hard to measure. Luckily, many alignment failures, such as deception, sycophancy, an…
Code Monitor Red Teaming for Public-Test-Passing Code
Junchi Liao, Jiawen Deng, Fuji Ren
Visible tests are a common gate for LLM-generated code, but passing them does not certify specification correctness. We study a deployment-like monitoring problem: after code has p…
Auditing language models for hidden objectives
Samuel Marks, Johannes Treutlein, Trenton Bricken +32
We study the feasibility of conducting alignment audits: investigations into whether models have undesired objectives. As a testbed, we train a language model with a hidden objecti…