Associate Prof @TAMULawSchool JD @Harvard_Law | PhD @MITBrainandCog | Law, language, cognition, AI
Fort Worth, TX
Joined June 2020
- Tweets187
- Following406
- Followers689
- Likes1.2K
Eric Martínez retweeted
This paper finds that frontier AI models correctly format Bluebook citations only 42.6% of the time on average. The best results come from combining AI with a deterministic rule engine rather than relying on the model alone. spkl.io/60117Pymc
#LegalTech #AI
Eric Martínez retweeted
Don't ask AI to Bluebook your citations until you read this study. Heck, maybe don't even ask?
Frontier models produced correct citations just 42.6% of the time.
AI can solve open math problems and find security flaws.
But can it reliably format a legal citation?
New paper w/ Matthew Dahl: across frontier models, the answer is no. We then build a system that
does much better.
papers.ssrn.com/sol3/papers.…
THREAD 1/
Eric Martínez retweeted
Disappointing but important.
"We develop a new benchmark of 2,058 Bluebook queries and show that, on average, frontier language models produce a fully compliant legal citation only 42.6% of the time in a zero-shot setting."
Excited to dive more into this...
Eric Martínez retweeted
This is an extremely interesting and well-written paper with a very surprising result. Makes me wonder whether we've really internalized how important jaggedness is and how long it will stick around.
Also, I will pay any bluebook-savvy law student who wants to earn some extra money $20 an hour to go through the methodology and experimental design with a fine toothed comb and come up with persnickety little criticisms, not because I think you're likely to find anything that discredits the validity of the central finding but because it will really piss Eric off and that will be hilarious. DM me if interested. Maybe start with the "models can't display small caps" thing, they seem very defensive about small caps in the footnotes. I smell weakness.
AI can solve open math problems and find security flaws.
But can it reliably format a legal citation?
New paper w/ Matthew Dahl: across frontier models, the answer is no. We then build a system that
does much better.
papers.ssrn.com/sol3/papers.…
THREAD 1/
Eric Martínez retweeted
Now out in PNAS!
Link to the paper: pnas.org/doi/10.1073/pnas.23…
News story by MIT News: news.mit.edu/2025/esperanto-…
What is a language?
Some think math, logic and music are like natural languages, but the brain doesn't treat them as such.
What about constructed languages?
Here is a preprint on what we discovered in @ev_fedorenko ’s lab: tinyurl.com/2p8f8vnp
Eric Martínez retweeted
MIT researchers found that legal language is intentionally complex, not for clarity, but to create a false sense of authority. Even lawyers prefer plain English. mitsha.re/iMCm50ValLB
Eric Martínez retweeted
New paper with @alexanderdfung, @PramodRT9 , @jessica__chomik , @Nancy_Kanwisher, @ev_fedorenko on the representations that underlie our intuitive physical reasoning about the world. Thread 🧵about our new preprint 📄✨linked here: tinyurl.com/intphyslang 1/10
Eric Martínez retweeted
David did a “scientist interview” with me his freshman year, and I immediately recruited him to help with our law in the brain project. So happy to see him advancing in his academic career! ✨
Congrats to the 4 MIT students who have been named 2025 Rhodes Scholars - esp David Oluigbo in @ev_fedorenko lab, who plans to apply AI to complex medical problems and systemic healthcare challenges. 🙌 mcgovern.mit.edu/2024/11/16/…
Eric Martínez retweeted
Congrats to the 4 MIT students who have been named 2025 Rhodes Scholars - esp David Oluigbo in @ev_fedorenko lab, who plans to apply AI to complex medical problems and systemic healthcare challenges. 🙌 mcgovern.mit.edu/2024/11/16/…
Eric Martínez retweeted
Out now in Cognitive Science: We investigate how people think judges should handle immoral laws. Should judges follow the law no matter what, or can exceptions be made for (grossly) immoral laws? We surveyed 167 laypeople and 141 participants with legal training to find out.
Eric Martínez retweeted
[Please retweet!] My paper, 'Cognitive Representations of Social Relationships and their Developmental Origins" has been accepted at Behavioral and Brain Sciences! I'm thrilled to be able to engage with people's commentary! Please consider writing one! osf.io/preprints/psyarxiv/xh…
Eric Martínez retweeted
Many AI governance stakeholders agree that certain laws or regulations should apply only to “frontier models.” But what is a “frontier model”? LawAI’s latest working paper discusses some of the most important legal considerations for efforts to define that term: law-ai.org/frontier-model-de…
Eric Martínez retweeted
@LanguageMIT and I are so pleased about this:
mitpress.mit.edu/cognitive-s…
Thanks to @HarvardLibrary @mitlibraries @mitpress for making this happen!
Eric Martínez retweeted
Our philosophy-informed LLM papers now out in TACL! See the improved paper or thread linked below for more on “bibliotechnism”, the referential ability of ngram models, what it means to say LLMs (or humans) have beliefs, beachgoing bardolaters, and more.
direct.mit.edu/tacl/article/…
Eric Martínez retweeted
Very humbled to be in such amazing company on this list... Congrats to everyone recognized!
So, so grateful for the support from my mentors and collaborators.
The Download: introducing our 35 Innovators Under 35 list for 2024 trib.al/eXYFtVL
Eric Martínez retweeted
Excited to have been named one of @techreview's 35 under 35!
I am happy that, these days, language & human cognition are topics that the world cares deeply about (thanks to recent developments in AI). Not only are these topics impactful, they are also fun to study!
The Download: introducing our 35 Innovators Under 35 list for 2024 trib.al/eXYFtVL
Eric Martínez retweeted
🚨New preprint!🚨 My first first-author project with @RouseTurner @natvelali @cocosci_lab
How do people evaluate idle collaborators who don’t help out during group tasks?
TL;DR: Sometimes it’s okay not to help with the dishes 🧵👇
Link: tinyurl.com/32wfwkxp
Eric Martínez retweeted
Now out in Cognition!
➰"Ambivalence by Design: A Computational Account of Loopholes"➰
by Qian, Bridgers, Parece, @MayaTaliaferro, and me
bit.ly/cognitionLoophole
