10 papers
Bayesian Preference Learning for Test-Time Steerable Reward Models
Jiwoo Hong, Shao Tang, Zhipeng Wang
Reward models are central to aligning language models with human preferences via reinforcement learning (RL). As RL is increasingly applied to settings such as verifiable rewards a…
Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning
Sanghwan Bae, Jiwoo Hong, Min Young Lee +3
Recent advances in reinforcement learning with verifiable rewards (RLVR) show that large language models enhance their reasoning abilities when trained with verifiable signals. How…
Margin-aware Preference Optimization for Aligning Diffusion Models without Reference
Jiwoo Hong, Sayak Paul, Noah Lee +3
Modern preference alignment methods, such as DPO, rely on divergence regularization to a reference model for training stability-but this creates a fundamental problem we call "refe…
Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning
Guijin Son, Jiwoo Hong, Hyunwoo Ko +1
Scaling pre-training compute has proven effective for achieving mulitlinguality, but does the same hold for test-time scaling? In this work, we introduce MCLM, a multilingual math…
AlphaPO: Reward Shape Matters for LLM Alignment
Aman Gupta, Shao Tang, Qingquan Song +10
Reinforcement Learning with Human Feedback (RLHF) and its variants have made huge strides toward the effective alignment of large language models (LLMs) to follow instructions and…
When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Research
Guijin Son, Jiwoo Hong, Honglu Fan +8
Recent advances in large language models (LLMs) have fueled the vision of automated scientific discovery, often called AI Co-Scientists. To date, prior work casts these systems as…