Article

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 …
Junghyun Lee, Sanghwa Kim, Yassir Jedra, Alexandre Proutière, Se-Young Yun
PDF Cite
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 …
Junghyun Lee, Yujun Kim, Chulhee Yun, Se-Young Yun
Cite
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 …
Junghyun Lee, Minju Hong, Kwang-Sung Jun, Chulhee Yun, Se-Young Yun
PDF Cite
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 …
Sanghwa Kim, Junghyun Lee, Se-Young Yun
PDF Cite
A Jointly Efficient and Optimal Algorithm for Heteroskedastic Generalized Linear Bandits with Adversarial Corruptions
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 …
Junghyun Lee, Branislav Kveton, Anup Rao, Subhojyoti Mukherjee, Ryan A. Rossi, Sunav Choudhary, Alexa Siu
PDF Cite
Learning to Reason in LLMs by Expectation Maximization