Author

Swapnil Parekh

View on Semantic Scholar

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence May 2026

Drop the Act: Probe-Filtered RL for Faithful Chain-of-Thought Reasoning

ProFIL (**Pro**be-**Filtered Reinforcement Learning) is introduced to reduce theater, increase chain-of-thought faithfulness, and shrink chain length in a single, drop-in extension to Group Relative Policy Optimization (GRPO).

Swapnil Parekh, Naman Goyal · arXiv.org · 2 citations