🤖🧠NEW PAPER🧠🤖 What is the relationship between neural networks & symbolic systems? Based on evidence from mechanistic interpretability, we argue for a quasi-symbolic view of cognition: Neural nets implement symbols but only approximately Link: www.sciencedirect.com/science/art…
Who's Who of AI
Tom McCoy
Why they matter
Researcher with public evidence across AI research, NLP & language.
- AI signals
- 2 past 30d
- Sources
- 2 distinct domains
- Discussões
- 1 past 30d
- Latest signal
- 3d ago
Assistant professor at Yale Linguistics. Studying computational linguistics, cognitive science, and AI. He/him.
What they're sharing
sciencedirect.com
[2605.20529] Collocational bootstrapping: A hypothesis about the learning of subject-verb agreement in humans and neural networks arxiv.org
How do AI chatbots ‘reason’ like humans? A Yale-led study offers clues news.yale.edu
[2605.10061] Not-So-Strange Love: Language Models and Generative Linguistic Theories are More Compatible than They Appear arxiv.org
The Emergent Symbolic Structure of Artificial Neural Networks arxiv.org
Formal Properties of Language as Constraints on Neural Dynamics arxiv.org
direct.mit.edu
View on Bluesky →
Collocational bootstrapping: A hypothesis about the learning of subject-verb agreement in humans and neural networks aclanthology.org
Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference aclanthology.org
Articles & links
🤖🧠NEW PAPER🧠🤖 Children & neural networks can learn syntax from linear strings of words. How do they do it? Our hypothesis: Word co-occurrence statistics provide cues to syntax! (I.e., a new type of bootstrapping to consider!) Paper: arxiv.org/abs/2605.20529 1/n
A very nice writeup from Mike Cummings at Yale News on our work finding symbolic structure inside LLM representations! Read it if you want to learn how the vectors inside LLMs are like pointillist paintings! news.yale.edu/2026/10/08/h...
AI Weekly's analysis
→
Read full analysis →
🤖🧠 New commentary 🧠🤖 What role should large language models (LLMs) play in linguistics? I reflect on this question in a commentary now on arXiv: arxiv.org/abs/2605.10061 To appear in BBS as a commentary on @futrell.bsky.social and @kmahowald.bsky.social's excellent piece on LL…
Work done with @paulsoulos.bsky.social, @tallinzen.bsky.social, and Paul Smolensky For much more, see our paper! arxiv.org/abs/2608.29530 12/12
AI Weekly's analysis
→
- A new preprint reports that neural networks' vector representations can be closely approximated by closed-form symbolic equations with behavior 'largely unchanged.'
- The substitution was tested on small networks trained to manipulate lists and on LLMs across arithmetic, logic, computer code, and language.
- The authors say the symbolic approximation also lets them steer an LLM's behavior via targeted interventions on its internal representations.
Read full analysis →
Tom McCoy reposted
New work out today! The result of a 15 year project to offer genuine linking hypotheses between linguistics and neuroscience: a revised research program, and its first result - a novel neural binding operation ('Meld') capturing core properties of natural language syntax 🧵 arx…
AI Weekly's analysis
→
Read full analysis →
View on Bluesky →
Tom McCoy reposted
New paper out in @openmindjournal.bsky.social! "Large Language Models as Distributional Baselines for Language Tasks". With @jamichaelov.bsky.social , @camrobjones.bsky.social , Tyler Chang, and Ben Bergen. direct.mit.edu/opmi/article...
Link for "Collocational bootstrapping: A hypothesis about the learning of subject-verb agreement in humans and neural networks": aclanthology.org/2026.conll-m...
I’m excited about this paper because statistical regularities sometimes pose a problem for learning abstract syntax (e.g., aclanthology.org/P19-1334/), but these results give an example of how statistics can *support* the right abstractions! For more, see our paper: arxiv.org/…
Their own posts
Recent commentary
🤖🧠NEW PAPER🧠🤖 (The result of an 8-year project!) LLMs seem very different from symbolic systems. Yet LLMs excel in symbolic domains (e.g., language/code/math). How do they do it? Our finding: LLM representations have implicit symbolic structure! Link in thread ⬇️ 1/n
Had a great time speaking at NYU today - there's an incredible collection of people there working on computational CogSci & AI!
Today at #acl2026nlp: Check out the panel on "Linguistics and NLP in the LLM Era", featuring Allyson Ettinger, @futrell.bsky.social, Zoey Liu, and me! 2:00 - 3:30 in Gaslamp C&D
In San Diego for #acl2026nlp! Excited to talk to people about connections between CogSci, Linguistics, and AI
Their network
In Tom McCoy's orbit
Center = Tom McCoy. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.
Are you Tom McCoy? Show it.
Add the Who’s Who of AI badge to your site or bio. It links back to this profile.
Markdown: [](https://aiweekly.co/whos-who/person/rtommccoy-bsky-social)