Arman Cohan

armanc

·

armancohan

AI & ML interests

None yet

Recent Activity

upvoted a paper about 7 hours ago

Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs

authored a paper 4 months ago

RbtAct: Rebuttal as Supervision for Actionable Review Feedback Generation

authored a paper 4 months ago

References Improve LLM Alignment in Non-Verifiable Domains

View all activity

Organizations

armanc 's papers 16

arxiv:2603.09723

arxiv:2602.16802

arxiv:2601.09876

arxiv:2504.00810

arxiv:2503.20757

arxiv:2503.21821

arxiv:2503.16416

arxiv:2502.13917

arxiv:2501.12380

arxiv:2501.06590

arxiv:2403.15246

arxiv:2402.00838

arxiv:2311.09835

arxiv:2309.08963

arxiv:2010.05987

arxiv:1904.07094