Amit Sharma

Principal Researcher, Microsoft Research

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 5

Friday, December 5, 2025 · 11:00 AM → 2:00 PM

Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks

#911 · Debargha Ganguly, Vikash Singh, Sreehari Sankar, Biyao Zhang, Xuecen Zhang, Srinivasan Iyengar, Xiaotian Han, Amit Sharma, Shivkumar Kalyanaraman, Vipin Chaudhary

SCFG-based framework characterizes uncertainty in LLM formal reasoning, enabling selective verification that reduces errors while minimally abstaining.