Instance-Optimal Estimation with Multiple LLM Judges on a Budget
Evaluating large language models increasingly relies on LLM-as-a-judge protocols, but such evaluations remain costly: different judges have different prices and reliabilities, and …
Looking Through the Mirror: Minimax-Optimal Regularized Regrets in Online Learning and Bandits
We revisit regularized regret minimization under full-information and bandit feedback, where a learner optimizes an objective of the form $\langle r, \pi \rangle - \eta^{-1} …
Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences
We consider the problem of *regularized* best-response max-regret minimization in online RLHF under general preferences and bandit feedback. While various regularizers are utilized …
A Jointly Efficient and Optimal Algorithm for Heteroskedastic Generalized Linear Bandits with Adversarial Corruptions
We consider the problem of heteroskedastic generalized linear bandits (GLBs) with adversarial corruptions, which subsumes various stochastic contextual bandit settings, including …
sanghwa-kim
Learning to Reason in LLMs by Expectation Maximization
Large language models (LLMs) solve reasoning problems by first generating a rationale and then answering. We formalize reasoning as a latent variable model and derive a …