Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
Paper
•
2307.15217
•
Published
•
37
Mehul Damani PRO
mehuldamani
AI & ML interests
Reinforcement Learning, Large Language Models
Recent Activity
published
a model
20 minutes ago
mehuldamani/regularBrier_mixedNumCandidates_rlcr_multi_from_rlvr_chkpt360
published
a model
1 day ago
mehuldamani/strongBrier_newPrompt_rlcr_multi_from_rlvr_chkpt360
published
a model
2 days ago
mehuldamani/rlcr_single_from_rlvr_chkpt360
Organizations
None yet
authored
4
papers
6 months ago
Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty
Paper
•
2507.16806
•
Published
•
7
Learning How Hard to Think: Input-Adaptive Allocation of LM Computation
Paper
•
2410.04707
•
Published
The Surprising Effectiveness of Test-Time Training for Abstract Reasoning
Paper
•
2411.07279
•
Published
•
3