PhD Student · Case Western Reserve University · Cleveland, OH

Vikash Singh

I make LLM reasoning formally verifiable by pairing language models with SMT solvers and theorem provers, so their outputs can be mathematically checked before anyone has to trust them.

~ $

-r-xcv.pdf→curriculum vitae · 157K lrwxgithub→github.com/vicky157 lrwxlinkedin→linkedin.com/in/vikash-singh-john lrwxx→x.com/vikash_joh60795 lrwxscholar→scholar.google.com/zt0c4Ws lrwxsemantic→semanticscholar.org/author/vikash-singh lrwxemail→vikashjohn2505@gmail.com

total 7 · 1 file · 6 symlinks

~ $

About

Vikash Singh is a PhD student at Case Western Reserve University working on making Large Language Models safe, reliable, and formally verifiable, so they can be deployed in settings like healthcare, law, and automated reasoning where a plausible-but-wrong answer is not acceptable. His research runs along three threads:

Formal Verification

Neurosymbolic systems that pair LLMs with SMT solvers and theorem provers, so model outputs are mathematically checked for logical consistency before they reach users.

Uncertainty Quantification

Knowing when to trust LLM reasoning: grammar-based uncertainty signals and selective verification that catch errors token probabilities miss.

Efficient Inference & Systems

Training-free control of inference-time compute budgets, retrieval over structured knowledge graphs, and GPU performance modeling for distributed training.

Latest Publications

ACL 2026

VERGE: Formal Refinement and Guidance Engine for Verifiable LLM Reasoning

Vikash Singh, Darion Cassel, Nathaniel Weir, Nick Feng, Sam Bayless

Preprint BibTeX

@misc{singh2026verge,
  title={VERGE: Formal Refinement and Guidance Engine for Verifiable LLM Reasoning},
  author={Vikash Singh and Darion Cassel and Nathaniel Weir and Nick Feng and Sam Bayless},
  year={2026},
  eprint={2601.20055},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2601.20055}
}

ICLR 2026

Trust The Typical

Debargha Ganguly, Sreehari Sankar, Biyao Zhang, Vikash Singh, Kanan Gupta, Harshini Kavuru, A. Luo, Weicong Chen, Warren Morningstar, R. Machiraju, Vipin Chaudhary

Preprint BibTeX

@misc{ganguly2026t3,
  title={Trust The Typical},
  author={Debargha Ganguly and Sreehari Sankar and Biyao Zhang and Vikash Singh and Kanan Gupta and Harshini Kavuru and A. Luo and Weicong Chen and Warren Morningstar and R. Machiraju and Vipin Chaudhary},
  year={2026},
  eprint={2602.04581},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2602.04581}
}

NeurIPS 2025 May 2025

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

Debargha Ganguly, Vikash Singh, Sreehari Sankar, Biyao Zhang, Xuecen Zhang, Srinivasan Iyengar, Xiaotian Han, Amit Sharma, S. Kalyanaraman, Vipin Chaudhary

HTML arXiv Code BibTeX

@misc{ganguly2025,
  title={Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks},
  author={Debargha Ganguly and Vikash Singh and Sreehari Sankar and Biyao Zhang and Xuecen Zhang and Srinivasan Iyengar and Xiaotian Han and Amit Sharma and S. Kalyanaraman and Vipin Chaudhary},
  year={2025},
  eprint={2505.20047},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2505.20047}
}

Findings of ACL 2026

Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers

Wang Yang, Debargha Ganguly, Xinpeng Li, Chaoda Song, Shouren Wang, Vikash Singh, Vipin Chaudhary, Xiaotian Han

Preprint BibTeX

@misc{wang2026midthink,
  title={Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers},
  author={Wang Yang and Debargha Ganguly and Xinpeng Li and Chaoda Song and Shouren Wang and Vikash Singh and Vipin Chaudhary and Xiaotian Han},
  year={2026},
  eprint={2601.07036},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2601.07036}
}

View All Publications

News & Updates

May 2026 Started Applied Scientist Internship at Amazon.
May 2026 HugRAG accepted at ICML 2026.
April 2026 Two papers accepted at ACL 2026: VERGE / FORGE at the main conference and Mid-Think as Findings.
January 2026 Paper accepted to ICLR 2026 (Trust The Typical).
September 2025 Paper accepted to NeurIPS'25 (Grammars of Formal Uncertainty: When to Trust LLMs).
September 2025 Two papers accepted to HiPC'25.
July 2025 Got accepted to Amazon Applied Science Internship at New York.
May 2025 Research Assistant At CWRU CSDS Department
Jan 2025-May 2025 Teaching Assistant for Data Mining Course.
Aug 2024-December 2024 Teaching Assistant for Computer Security Course at CWRU.
Aug 2024-Present Started PhD in Computer Science at Case Western Reserve University.
May 2024 Summer Internship at MGenio Inc.
Jan 2024 - May 2024 Teaching Assistant for Computational Perception and Compiler Design Courses at CWRU.
Aug 2023 - Dec 2023 Started Masters in Computer Science at Case Western Reserve University.
May 2023 Completed B.Tech in Civil Engineering at Indian Institute of Technology, Mandi
Jan 2022-Sep 2022 Internship at DRDO
May 2021 - Aug 2021 Internship at Indian Institute of Technology, Mandi
Aug 2019- May 2023 B.Tech in Civil Engineering at Indian Institute of Technology, Mandi