From the 1 of 17 linked papers with an AI index.
17 papers
Rubrics on Trial: Evolving Rubrics from a Single Query via Synthetic Pairwise Evidence
Haocheng Yang, Licheng Pan, Xiaoxi Li +5
The paper proposes a query‑only method that automatically creates and validates fine‑grained rubrics for evaluating large language models by using synthetic rubric‑conditioned resp…
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…
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…
Robust Reward Modeling for Large Language Models via Causal Decomposition
Yunsheng Lu, Zijiang Yang, Licheng Pan +1
Reward models are central to aligning large language models, yet they often overfit to spurious cues such as response length and overly agreeable tone. Most prior work weakens thes…
DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment
Hao Wang, Licheng Pan, Yuan Lu +7
Training time-series forecasting models requires aligning the conditional distribution of model forecasts with that of the label sequence. The standard direct forecast (DF) approac…
ImplicitRM: Unbiased Reward Modeling from Implicit Preference Data for LLM alignment
Hao Wang, Haocheng Yang, Licheng Pan +7
Reward modeling represents a long-standing challenge in reinforcement learning from human feedback (RLHF) for aligning language models. Current reward modeling is heavily contingen…