10 papers
Rubric Judgments Lack Uncertainty: Conformal Weighting for LLM Evaluation
Licheng Pan, Haocheng Yang, Haoxuan Li +7
Rubric-based evaluation is widely used to assess large language model (LLM) outputs by decomposing quality into multiple criteria and assigning each a binary judgment from an LLM v…
CleanRM: Reward Modeling from Noisy Feedback with a Few Clean Feedback for RLHF
Licheng Pan, Haocheng Yang, Yuzhou Chen +7
Feedback noise is pervasive in preference data, arising from subjective human judgments, annotation mistakes, and imperfect LLM judges. Standard reward modeling trained on such fee…
Not All Criteria Matter: Importance-Aware Criteria Weighting for Rubric-Based LLM Evaluation
Haocheng Yang, Licheng Pan, Yiming Dong +7
Rubric-based evaluation assesses the responses of large language models (LLMs) by aggregating the verification results of explicit criteria, yet not all criteria matter equally. Ho…
RubricArmor: Adversarial Evolution Improves LLM-Based Rubric Generation
Haocheng Yang, Yuchao Zhang, Licheng Pan +8
Rubric-based reinforcement learning (RL) provides interpretable rewards for aligning large language models (LLMs) by evaluating responses against query-specific evaluation criteria…
Rubrics on Trial: Evolving Rubrics from a Single Query via Synthetic Pairwise Evidence
Haocheng Yang, Licheng Pan, Xiaoxi Li +8
Rubric evolution offers a promising approach to improving the quality of rubrics generated by large language models (LLMs). Central to this process is rubric comparison, which iden…
Uncertainty-Aware Reward Modeling for Stable RLHF
Licheng Pan, Haocheng Yang, Haoxuan Li +7
Reinforcement learning from human feedback (RLHF) aligns large language models by training reward models on preference data and optimizing policies to maximize predicted rewards. H…
Looped World Models
Hongyuan Adam Lu, Z. L. Victor Wei, Qun Zhang +28
Current world models face a fundamental tension: faithful long-horizon simulation demands deep computation, but deeper models are expensive to deploy and prone to compounding error…
Optimal Transport for LLM Reward Modeling from Noisy Preference
Licheng Pan, Haochen Yang, Haoxuan Li +8
Reward models are fundamental to Reinforcement Learning from Human Feedback (RLHF), yet real-world datasets are inevitably corrupted by noisy preference. Conventional training obje…
Mitigating Hidden Confounding by Progressive Confounder Imputation via Large Language Models
Hao Yang, Haoxuan Li, Luyu Chen +3
Hidden confounding remains a central challenge in estimating treatment effects from observational data, as unobserved variables can lead to biased causal estimates. While recent wo…
Estimating the Effects of Sample Training Orders for Large Language Models without Retraining
Hao Yang, Haoxuan Li, Mengyue Yang +2
The order of training samples plays a crucial role in large language models (LLMs), significantly impacting both their external performance and internal learning dynamics. Traditio…