Dylan Bouchard, PhD

I'm an applied research scientist at Thomson Reuters Labs. My research focuses on AI safety, particularly uncertainty quantification, hallucination detection, and bias and fairness in large language models. Previously, I built and led the AI Research program at CVS Health, conducting research and developing open-source projects including UQLM and LangFair. I hold a PhD in Economics (Econometrics) from North Carolina State University.

Select Publications

1. D. Bouchard, M. S. Chauhan, D. Skarbrevik, H.-K. Ra, V. Bajaj, and Z. Ahmad. UQLM: A Python Package for Uncertainty Quantification in Large Language Models. Journal of Machine Learning Research, 27(13):1–10, 2026. [JMLR]
2. D. Bouchard, M. S. Chauhan, Z. Ahmad, and H.-K. Ra. Functional Entropy: Predicting Functional Correctness in LLM-Generated Code with Uncertainty Quantification. EMNLP (Main Conference), 2026. [arXiv]
3. D. Bouchard and M. S. Chauhan. Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorers. Transactions on Machine Learning Research, 2025. [TMLR]
4. D. Bouchard, M. S. Chauhan, V. Bajaj, and D. Skarbrevik. Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study. Transactions on Machine Learning Research, 2026. [TMLR]
5. M. S. Chauhan, V. Gyanchandani, and D. Bouchard. When Do Supervised UQ Ensembles Improve LLM Hallucination Detection? A Robustness Study. Findings of AACL-IJCNLP, 2026. [arXiv]
6. D. Bouchard. Bring Your Own Prompts: Use-Case-Specific Bias and Fairness Evaluation for LLMs. LT-EDI Workshop at ACL, 2026. [ACL Anthology]
7. D. Bouchard, M. S. Chauhan, D. Skarbrevik, V. Bajaj, and Z. Ahmad. LangFair: A Python Package for Assessing Bias and Fairness in Large Language Model Use Cases. Journal of Open Source Software, 10(105):7570, 2025. [DOI]
8. D. Bouchard and M. S. Chauhan. Beyond Single-Turn Confidence: Trajectory-Adapted Uncertainty Quantification for LLM Agents. Under review, 2026. [arXiv]
9. D. Bouchard. Is Escalation Worth It? A Decision-Theoretic Characterization of LLM Cascades. Under review, 2026. Accepted to the AdaptFM Workshop at ICML 2026 (non-archival). [arXiv]

Open-Source Projects

• UQLM — Uncertainty Quantification for Language Models

  A Python toolkit for LLM hallucination detection via uncertainty quantification, implementing black-box, white-box, LLM-judge, and ensemble scorers. 1.2K+ GitHub stars, 60K+ PyPI downloads; recognized by LangChain.

  Repository · Documentation

• LangFair — Bias & Fairness Assessment for LLMs

  A Python package for use-case-level LLM bias and fairness assessment using a bring-your-own-prompts approach. 250+ GitHub stars, 40K+ downloads; integrated into the LangChain ecosystem and incorporated into the Coalition for Health AI's responsible AI best practices.

  Repository · Documentation

Selected Talks

• Functional Entropy: Predicting Functional Correctness in LLM-Generated Code with Uncertainty Quantification. SURGeLLM Workshop at ACL 2026 (oral presentation).
• Bring Your Own Prompts: Use-Case-Specific Bias and Fairness Evaluation for LLMs. LT-EDI Workshop at ACL 2026 (oral presentation).
• Uncertainty Quantification for Language Models: Standardizing and Evaluating Black-Box, White-Box, LLM Judge, and Ensemble Scorers. NeurIPS 2025 LLM Evaluation Workshop.
• UQLM: Detecting LLM Hallucinations with Uncertainty Quantification in Python. PyData Global 2025 (oral presentation).
• UQLM: A Toolkit for LLM Hallucination Detection Using Uncertainty Quantification. AI Alliance Trust and Safety Working Group, July 2025 (invited talk).

Service

Reviewing: NeurIPS, ICML, ICLR, COLM, ACL, ACM TIST, and ACM CHI.

Program committee: Multiplicity and Homogenization in AI (NeurIPS 2026).

Awards: Best Reviewer, LT-EDI Workshop at ACL 2026.