Vikash Singh

What I work on

Making reasoning reliable.

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:

Selected work

Research in focus

@inproceedings{singh2026verge,
  booktitle={Findings of the Association for Computational Linguistics: EMNLP 2026},
  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}
}

@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}
}

@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}
}

@inproceedings{wang2026midthink,
  booktitle={Findings of the Association for Computational Linguistics: ACL 2026},
  doi={10.18653/v1/2026.findings-acl.299},
  pages={6024--6038},
  title={Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers},
  author={Van Yang and Shouren Wang and Debargha Ganguly and Xinpeng Li and Chaoda Song and Vikash Singh and Vipin Chaudhary and Xiaotian Han},
  year={2026},
  eprint={2601.07036},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2601.07036}
}

Along the way

News & Updates

• October 2026 Privacy Policy Enforcement Guardrails for Data-Sensitive Retrieval-Augmented Generation accepted to IEEE TPS 2026.
• October 2026 Auditing Cross-Lingual Fairness in Language Model Watermarking accepted as a poster at the NeurIPS 2026 Evaluations and Datasets Track.
• October 2026 StochBench accepted to the NeurIPS 2026 MATH-AI workshop; Toward Guarantees for Clinical Reasoning in Vision Language Models via Formal Verification accepted to the NeurIPS 2026 Med-Reasoner workshop.
• September 2026 VERGE accepted to EMNLP Findings 2026.
• August 2026 Completed my Amazon Applied Scientist internship, working on generative reward models for autoformalization. Beyond Solver Verdicts is under review at ACL Rolling Review.