← Search

Swarnashree Mysore Sathyendra

2 accepted papers

2026

Chasing the Tail: Effective Rubric-based Reward Modeling for Large Language Model Post-Training

ICLR 2026poster

Reinforcement fine-tuning (RFT) often suffers from reward over-optimization, where a policy model hacks the reward signals to achieve high scores while producing low-quality outputs. Our theoretical analysis shows that the key lies in reward misspecification at the high-reward tail: the inability to…

Cited by 0SourcecodeScholar
2023

Multi-Dimensional Evaluation of Text Summarization with In-Context Learning

ACL 2023findings

Evaluation of natural language generation (NLG) is complex and multi-dimensional. Generated text can be evaluated for fluency, coherence, factuality, or any other dimensions of interest. Most frameworks that perform such multi-dimensional evaluation require training on large manually or syntheticall…