In New Jersey, public defenders have access to the OPD Resource Library, an AI-powered search tool that surfaces relevant information from the office's internal documents. Hereβs the tool from a defender's perspective. (1/8)
How can AI support public defense? We have worked on this question for the last two years, and have (1) built an AI retrieval tool for the NJ Office of the Public Defender and (2) conducted qualitative interviews with defenders. Our main insights π(1/12)
In New Jersey, public defenders have access to the OPD Resource Library, an AI-powered search tool that surfaces relevant information from the office's internal documents. Hereβs the tool from a defender's perspective. (1/8)
How can AI support public defense? We have worked on this question for the last two years, and have (1) built an AI retrieval tool for the NJ Office of the Public Defender and (2) conducted qualitative interviews with defenders. Our main insights π(1/12)
Legal Retrieval for Public Defenders, Stammbach et al., 2026, forthcoming in TMLR arxiv.org/abs/2601.14348
Here, we describe the research challenges we encountered while building the Resource Library. We also release a realistic benchmark for public defense retrieval (5/8)
In New Jersey, public defenders have access to the OPD Resource Library, an AI-powered search tool that surfaces relevant information from the office's internal documents. Hereβs the tool from a defender's perspective. (1/8)
How can AI support public defense? We have worked on this question for the last two years, and have (1) built an AI retrieval tool for the NJ Office of the Public Defender and (2) conducted qualitative interviews with defenders. Our main insights π(1/12)
The Resource Library is part of our broader research agenda on AI for public defense. Our accompanying papers have now been published at FAccT 2026 and are forthcoming in TMLR. The launch of the OPD Resource Library has been covered by the ABA Journal, Law360, and NJBIZ (3/8)
How Can AI Augment Access to Justice?, Cheong et al., FAccT 2026 dl.acm.org/doi/10.1145/...
The paper summarizes insights from qualitative interviews and provides a research agenda for AI for public defense (4/8)
In New Jersey, public defenders have access to the OPD Resource Library, an AI-powered search tool that surfaces relevant information from the office's internal documents. Hereβs the tool from a defender's perspective. (1/8)
How can AI support public defense? We have worked on this question for the last two years, and have (1) built an AI retrieval tool for the NJ Office of the Public Defender and (2) conducted qualitative interviews with defenders. Our main insights π(1/12)
Defenders have consistently returned to the Library and are submitting a few hundred searches each week. An overview of the tool can be found on our CITP blogpost tinyurl.com/yppwmud3 and the NJOPD press release tinyurl.com/54t93735
πLast week we announced the launch of a new AI tool in partnership with the New Jersey Office of the Public Defender!
AI can empower civil servants and improve public services, and this project provides a blueprint for doing so responsibly.
πLots of takeaways, below!
πLast week we announced the launch of a new AI tool in partnership with the New Jersey Office of the Public Defender!
AI can empower civil servants and improve public services, and this project provides a blueprint for doing so responsibly.
πLots of takeaways, below!
How can AI support public defense? We have worked on this question for the last two years, and have (1) built an AI retrieval tool for the NJ Office of the Public Defender and (2) conducted qualitative interviews with defenders. Our main insights π(1/12)
AI-fabricated case citations continue to show up in courts, but can AI also automatically flag hallucinated legal citations to reduce the verification burden? In our new paper (accepted at COLM 2026), we built a benchmark and evaluated several agentic models to find out (1/7)
How can AI support public defense? We have worked on this question for the last two years, and have (1) built an AI retrieval tool for the NJ Office of the Public Defender and (2) conducted qualitative interviews with defenders. Our main insights π(1/12)
Cheong et al., 2026 outline a research agenda around suitable AI tasks for public defense, Stammbach et al., 2026, releases a manually curated public defense retrieval benchmark (11/12)
How can AI support public defense? We have worked on this question for the last two years, and have (1) built an AI retrieval tool for the NJ Office of the Public Defender and (2) conducted qualitative interviews with defenders. Our main insights π(1/12)
Deploying AI for state agencies requires collaboration across different agencies. With engineers from AWS, NJ Innovation Authority and NJ OIT, we deployed the Resource Library as a closed universe tool with the highest possible privacy and security guarantees (9/12)
How can AI support public defense? We have worked on this question for the last two years, and have (1) built an AI retrieval tool for the NJ Office of the Public Defender and (2) conducted qualitative interviews with defenders. Our main insights π(1/12)
Insights from qualitative interviews and our collaboration with the NJOPD are very consistent. And we believe in AI mainly to assist and support defenders, not automate public defense (7/12)
This is in line with Jennifer Sellitti arguing βTechnology will not define the future of public defense. Our lawyers willβ. And one of our interview participants pointed out that βclients have a right to counsel, not to machinesβ (8/12)
How can AI support public defense? We have worked on this question for the last two years, and have (1) built an AI retrieval tool for the NJ Office of the Public Defender and (2) conducted qualitative interviews with defenders. Our main insights π(1/12)
Apart from assistance in legal writing, defenders pointed out that AI for reviewing evidence and making sense of large volumes of data would be the most helpful use cases. Lots of exciting and underexplored avenues for future AI research (5/12)
We point out multiple barriers to adoption, most importantly privacy and error tolerance. Current LLMs meet neither. We evaluated a closed-source RAG tool resulting in 66% failure cases. Thus, we built a customized AI-powered retrieval tool for the NJOPD instead (6/12)
How can AI support public defense? We have worked on this question for the last two years, and have (1) built an AI retrieval tool for the NJ Office of the Public Defender and (2) conducted qualitative interviews with defenders. Our main insights π(1/12)
In our projects, defenders point out AI to surface relevant information, and making sense of large volumes of data. This was counterintuitive to our initial beliefs where we thought AI assisting in brief writing would be the most impactful (3/12)
Together with the NJOPD, we have built and deployed the OPD Resource Library, an AI retrieval tool which surfaces relevant briefs. This scales current office practices, where defenders try to obtain such briefs and reuse legal arguments or precedents (4/12)
How can AI support public defense? We have worked on this question for the last two years, and have (1) built an AI retrieval tool for the NJ Office of the Public Defender and (2) conducted qualitative interviews with defenders. Our main insights π(1/12)
In public defense, the constitutional right to counsel meets the complexities of law, overwhelming caseloads, constrained resources, low to zero tolerance for errors and high stakes. This is a challenging context for AI systems (2/12)
The future of oral argument or trial prep will obviously involve AI. But how can we measure quality of simulations? We build out an eval suite and run some studies!
Sycophancy & issue coverage are clear areas of improvement, but models are surprisingly useful!
ππ
@nealkatyal.bsky.social says he practiced for Supreme Court oral arguments using #HarveyAI. But does AI as an oral argument simulator live up to the hype? In a new paper, we present the first comprehensive framework for evaluating AI as a practice partner for oral argument preparation.
@skyien-z.bsky.social and @nimranadeem.bsky.social evaluated LLMs for oral argument preparation -- before the hype around Katyal's TED Talk and Harvey's AI system. Findings are more nuanced: while some generations are great, there's sycophancy, limited diversity, and barely any hypotheticals
@nealkatyal.bsky.social says he practiced for Supreme Court oral arguments using #HarveyAI. But does AI as an oral argument simulator live up to the hype? In a new paper, we present the first comprehensive framework for evaluating AI as a practice partner for oral argument preparation.
π’ I'm organizing two venues for papers at the intersection of NLP/AI and climate with deadlines approaching
- A special issue in Climatic Change: βNLP and AI as Climate Solutions" (deadline June 30th), t.co/JYY3dUogVn
- The 3rd ClimateNLP Workshop at EMNLP 2026 (deadline July 15th), details π
This is the Final Call for Papers for the 3rd ClimateNLP Workshop at EMNLP 2026 π’π’
ποΈ Submission Deadline: July 15 (AOE)
- Workshop date: October 28th or 29th
We invite short and long papers at the intersection of climate change and NLP π
Details in the link π
Excited to announce the fourth Climate Change AI Summer School (virtual, July 19βAugust 22, 2026)! π
Are you an #AI or #DataScience expert who wants to tackle #ClimateChange? Are you a #climate expert trying to use #ML in your work?
Register here π www.climatechange.ai/events/summe...
Really exciting work led by Patty Liu on LLM-generated hallucinated legal citations!
We also put out a more technical draft describing a dataset and methods for benchmarking legal citation verification
princeton-polaris-lab.github.io/legal-halluc...
βCan AI reduce burdens on courts by automatically verifying citations?
Now on the CITP Blog, researchers Patty Liu, @dominsta.bsky.social, and Prof @peterhenderson.bsky.social investigate LLM-hallucinated legal citations in court documents π»
blog.citp.princeton.edu/2026/05/27/c...
Update: semantic search is now live across all of CourtListener, not just the API π
You can search case law in natural language directly on CourtListener!
free.law/2026/05/04/s...
Weβve been pushing hard on AI for public good. One example: partnering with Courtlistener to launch accessible legal semantic search! Many more cool AI projects coming soon from my group aimed at improving access to justice, often spearheaded by @dominsta.bsky.social !
π’π’ Second Call for Papers for the 3rd ClimateNLP Workshop at EMNLP 2026 π’π’
ποΈ Updated Submission Deadline: July 15 (AOE)
π We invite short and long papers at the intersection of climate change and NLP π
π Details in the original call
π’π’ Call for Papers is out for the Third ClimateNLP Workshop at EMNLP 2026 π’π’
π We invite short and long papers at the intersection of climate change and NLP π
ποΈ Submission Deadline (preliminary): May 10th, 2026
more info: nlp4climate.github.io/callforpapers/
π¨ Call for Papers: AI for Law Workshop @icmlconf.bsky.social (July 10, Seoul π°π·), welcomes submissions across three themes:
βοΈ AI for Legal Reasoning
π AI Evaluation for Law
π AI for Access to Justice
π Full papers (β€8 pages)
β° Deadline: May 22 (AoE)
πSubmission via: openreview.net/group?id=ICM...
Iβm organizing two tracks for papers at the intersection of NLP/AI and climate:
(1) A special issue in Climatic Change: βNLP and AI as Climate Solutions: Opportunities and Challengesβ
(2) The 3rd ClimateNLP Workshop at EMNLP 2026
Consider submitting if you have relevant work!
π’π’ Call for Papers is out for the Third ClimateNLP Workshop at EMNLP 2026 π’π’
π We invite short and long papers at the intersection of climate change and NLP π
ποΈ Submission Deadline (preliminary): May 10th, 2026
more info: nlp4climate.github.io/callforpapers/
π£ Call for Contributions: LEXam-v2 β A Benchmark for Legal Reasoning in AI
How well do todayβs AI systems really reason about law?
Weβre building a global benchmark based on real law school & bar exams.
π§΅ Full details, scope, and how to contribute in the thread π
π€ Why contribute?
π Substantive contribution will lead to co-authorship (targeting a top-tier AI venue)
π Report on how AI models perform on your exam questions
π Help build the first multi-jurisdictional legal reasoning benchmark
π Exams are anonymized; data can be public or evaluation-only
π¬ Interested or know someone who might be?
Please fill out the form docs.google.com/forms/d/e/1F...
If you have any questions, email us at lexam.benchmark@gmail.com
π Please share with colleagues in legal academia!
π£ Call for Contributions: LEXam-v2 β A Benchmark for Legal Reasoning in AI
How well do todayβs AI systems really reason about law?
Weβre building a global benchmark based on real law school & bar exams.
π§΅ Full details, scope, and how to contribute in the thread π
π Weβre looking for:
- Law school exams you authored
- Open-ended, short-answer, MCQ, or true/false questions
- Model answers, rubrics, or anonymized high-scoring student answers
π¨π We are organizing a Special Issue with the Climatic Change journal!
Scope: NLP and AI as Climate Solutions: Opportunities and Challenges
More details: link.springer.com/collections/...
Weβve been pushing hard on AI for public good. One example: partnering with Courtlistener to launch accessible legal semantic search! Many more cool AI projects coming soon from my group aimed at improving access to justice, often spearheaded by @dominsta.bsky.social !
π£ New Preprint!
Have you ever wondered what the political content in LLM's training data is? What are the political opinions expressed? What is the proportion of left- vs right-leaning documents in the pre- and post-training data? Do they correlate with the political biases reflected in models?
βIn the U.S., unfortunately, most people cannot afford a lawyer. What I'm currently working on is legal natural language processing + #NLP tech, which would increase access to justice.β
A new Meet the Researcher w/ @dominsta.bsky.social is up β‘οΈ #CITP Blog: blog.citp.princeton.edu/2025/04/16/m...
From @peterhenderson.bsky.social's POLARIS Lab: π¨Public Defenders - We need your insights! Weβre conducting a research study to explore how #AI can better serve you & your clients. Your experiences can shape the future of AI legal tools designed specifically for public defenders. Sign-up ππ»
π Do you have a paper about climate change, submitted to ARR and got reviews, but don't know where to submit?
Submit to the ClimateNLP workshop!
π More infos in thread
π’π’ Third and last Call for Papers for the 2nd ClimateNLP Workshop at ACL 2025 π’π’
ποΈ Submission Deadline: March 1st AOE
π We invite short and long papers at the intersection of climate change and NLP π
More info: nlp4climate.github.io
#TechTakes - Brand new CITP Blog post just dropped π "It Wasn't Me: #DeepSeek denies they stole anything, but is their model still a cost revolution?"
π’ This is part of a new series called #TechTakes, where CITP researchers comment on tech news & tech policy.
freedom-to-tinker.com/2025/02/07/i...
π’π’ Second Call for Papers for the 2nd ClimateNLP Workshop at ACL 2025 π’π’
ποΈ Submission Deadline: March 1st AOE
π We invite short and long papers at the intersection of climate change and NLP π
More info: nlp4climate.github.io
π’π’ Call for Papers is out for the Second ClimateNLP Workshop at ACL 2025 π’π’
π We invite short and long papers at the intersection of climate change and NLP π
ποΈ Submission Deadline: March 1st AOE
more info: nlp4climate.github.io/callforpapers/
π’ Excited to announce that we're going into the second iteration of ClimateNLP at #ACL2025 in Vienna!
π We invite short and long papers at the intersection of climate change and NLP π
Official call for papers later in December, submission deadline approx March. More info: nlp4climate.github.io