Manya Wadhwa

SkillFactory: Self-Distillation for Learning Cognitive Behaviors

QUDsim: Quantifying Discourse Similarities in LLM-Generated Text

To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning

EvalAgents: Discovering Implicit Evaluation Criteria from the Web

Pairwise or Pointwise? Evaluating Feedback Protocols for Bias in LLM-Based Evaluation