← Search

David Baek

2 accepted papers

2026

D-FUSEr: Diverse Failure, Unified Success via Error-Distribution Shaping in LLM Reasoning

ICML 2026poster

Test-time scaling methods such as majority vote aggregation and iterative refinement (e.g., self-reflection or multi-agent inference) improve reasoning performance by leveraging multiple solution samples. However, their efficacy depends not only on raw performance, but critically on the distribution…

Cited by 0SourceScholar
2026

Sycophancy Towards Researchers Drives Performative Misalignment

ICML 2026spotlight

The increasing situational awareness of language models raises safety concerns: models might be aware when they are evaluated, and adjust their behavior to evade monitoring and resist modification, e.g., pretending to be aligned only in evaluation. This \emph{alignment faking} behavior is often inte…

Cited by 0SourceScholar