Teddi Worledge
PhD Candidate, Computer Science · Stanford University
About
Hi! I am a final-year computer science PhD candidate at Stanford, advised by Carlos Guestrin and supported by the NSF GRFP Fellowship.
I care about making AI systems reliable and trustworthy. I'm interested in equipping users to interrogate LLM generations as capabilities scale with citations, data attribution, and explanations. These days, I'm always looking for new legal AI applications, complementary human-AI performance, and what verifiability means to legal professionals.
Previously, I was at UC Berkeley, where I was fortunate to work with Ben Recht and Esther Rolf.
Recent Updates
October 2026 · Attended the AAAI/ACM Conference on AI, Ethics, and Society in Malmö, Sweden to share our work on AI for case review at the Los Angeles Superior Court.
October 2026 · Named as a Crosby Intelligence Fellow.
August 2026 · Our work on Uncovering Verifiability Trade-offs in LLM Generations was accepted for publication in Transactions of the Association for Computational Linguistics!
July 2026 · Our work on AI assistance for debt collection case review is in the New York Times!
More Updates
July 2026 · Our work in collaboration with the Los Angeles Superior Court, AI Assistance for Court Review of Default Judgments, was accepted to AIES!
July 2026 · Our workshop on Attributing Model Behavior at Scale: Data Attribution and Provenance (ATTRIB) will be at NeurIPS 2026 in Sydney, Australia! If you work on data attribution, AI citations, or their applications to other domains (e.g., law or music), we would love to see your submission.
June 2026 · I am interning this summer at Crosby to work on RL for legal contract red-lining and negotiation.
Talks
- Crosby: In Conversation with Peter Henderson · September 2026 — Fireside chat with Peter Henderson, assistant professor at Princeton University leading the Polaris Lab, about legal alignment, reinforcement learning for legal tasks, and paradigms of HCI design for law.
- Orrick: Behind the Scenes: Legal AI Applications and Citations · July 2026 — Conversation with Vedika Mehera, Director of Orrick Labs, about the state of legal AI applications, explainability, and citations for Orrick's 2026 summer associate class.
- Civil Bench Seminar at the Los Angeles Superior Court · May 2026 — Shared our recent work on AI assistance for debt collection case review with the civil judges of LA Court––the largest trial court in the nation. Debt collection cases account for nearly a quarter of all civil cases. Courthouses are already racing to process crowded dockets and caseload is increasing even further! We need to work on safely equipping courts with reliable assistive AI, while preserving judicial discretion.
More Talks
- CodeX & Stanford Law School AI Initiative: CS x Law Evening · May 2026 — Given the reputational carnage from hallucinated legal AI citations, I discussed LLM citations, why they fail, and some predictions for the trajectory of legal AI.
- ACM CS & Law · March 2026 — Presented a law student user study of our AI case review assistant.
- JURIX AI for Access to Justice · December 2025 — Presented on the development of our AI assistant for real-world case review.
- Code for Humanities Guest Lecture · June 2025 — Presented on LLMs to a group of Stanford humanities professors learning how to code! We covered different steps of the model training pipeline and why hallucinations are possible.
- Wonderfest · April 2024 — An open-to-all public session, where I got to talk about LLM citations and why they aren't reliable.
- NeurIPS ATTRIB · December 2023 — Workshop spotlight! Presented our unifying framework for training data attribution and LLM citations.
Papers
- AI Assistance for Court Review of Default Judgments AAAI/ACM Conference on AI, Ethics, and Society, 2026
- The Extractive-Abstractive Spectrum: Uncovering Verifiability Trade-offs in LLM Generations Transactions of the Association for Computational Linguistics, 2026
- Unifying Corroborative and Contributive Attributions in Large Language Models IEEE Conference on Secure and Trustworthy Machine Learning, 2024
- Representation matters: Assessing the importance of subgroup allocations in training data International Conference on Machine Learning, 2021