Taslim Mahbub — accepted AI-conference papers

2026

Mitigating Self-Preference by Authorship Obfuscation

AAAI 2026technical

Language models (LMs) judges are widely used to evaluate the quality of LM outputs. Despite many advantages, LM judges display concerning biases that can impair their integrity in evaluations. One such bias is self-preference: LM judges preferring their own answers over those produced by other LMs o

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

Sycophancy Towards Researchers Drives Performative Misalignment

David Baek, Xinnuo Li, Anay Gupta, Taslim Mahbub, Kejian Shi, Max Tegmark +1

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 0 Source ↗Scholar ↗