Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Expanding the Capabilities of Reinforcement Learning via Text Feedback
Yuda Song, Lili Chen, Fahim Tajwar +5
The success of RL for LLM post-training stems from an unreasonably uninformative source: a single bit of information per rollout as binary reward or preference label. At the other…
cs.LG2025
Generative Classifiers Avoid Shortcut Solutions
Alexander C. Li, Ananya Kumar, Deepak Pathak
Discriminative approaches to classification often learn shortcuts that hold in-distribution but fail even under minor distribution shift. This failure mode stems from an overrelian…