Computer Science PhD Student at Northeastern University Research Fellow @GoodfireAI
Boston, MA
Joined December 2014
- Tweets203
- Following531
- Followers540
- Likes1K
Eric Todd retweeted
Can we trace an AI model's answers back to its training data?
Surprisingly, even when we know exactly which documents taught a model a fact, attribution methods often fail to find them.
Our CATT benchmark investigates why and uncovers two simple fixes
catt.baulab.info🧵
Eric Todd retweeted
Our first keynote is underway! Sheridan Feucht @sheridan_feucht is talking about how LLMs read, from multi-token words to text in images. Join us in Room P3!
Eric Todd retweeted
Tomorrow at 9:10am, I'll be talking about two case studies of "How LLMs Read" @BlackboxNLP. What exactly do I mean by "reading"? Come to P3 tomorrow morning and find out! :)
🎉 Thrilled to announce the keynote speakers for BlackboxNLP 2026 @emnlpmeeting, with three incredible perspectives on interpretability:
🔍 Ivan Titov @iatitov
🔍 Sheridan Feucht @sheridan_feucht
🔍 Michael Hahn @mhahn29
Join us on October 29th! 🇭🇺
Eric Todd retweeted
Interested in ICL, induction heads, or phase shifts in training? Come say hi at our #EMNLP2026 poster!
In-Context Learning Beyond Copying
Hall H, Poster Session A
Sun Oct 25, 11:00–12:30
arxiv.org/abs/2511.05743
Eric Todd retweeted
Literary works are often translated into the same language multiple times, and each translation interprets the original in its own way.
How can we use these different translations to train better literary MT systems? Can synthetic references be as good as human ones?
Eric Todd retweeted
Interpretability stress-testing results can be unreliable if you set up the test wrong.
We introduce "How to train your model organism" (w/ @davidbau @byron_c_wallace), where we propose to use more realistic model organisms for interpretability auditing.
Eric Todd retweeted
VLMs use pointer-like signals for spatial variable binding. But where does the binding actually happen?
We find a dual mechanism: the vision encoder is the primary source of binding, with the LM backbone playing a secondary role.
Eric Todd retweeted
At #COLM2026 tomorrow!
If swapping a demographic attribute flips an LLM's answer, is that bias? Compared to what? A paraphrase often does too.
Come chat about baselines for counterfactual prompting:
📍 Wed 10/7, 11am–1pm, Imperial #41
w/ @mosh_levy @yoavgo @byron_c_wallace
1/ (New paper!)
If swapping the gender in an input prompt makes the AI model give a different answer it means that it has to have a gender bias, right? Wrong.
🧵on counterfactual prompting for LLM evals:
Paper: arxiv.org/abs/2605.01048
Eric Todd retweeted
The craziest experiment in my lab is a new setup by @diatkinson where he has found a way induce introspection on open LMs using @dillonplunkett's protocol, that lets him look inside introspection. It's nuts.
Here's how the experiment works... 🧵 →
Eric Todd retweeted
Presenting this at #COLM2026 tomorrow!
Poster Session 1, 11am-1pm
Imperial Ballroom, poster #66
Eric Todd retweeted
New COLM paper: Identifying Introspection From the Inside
When an LLM tells us about its decisions, does it 𝘬𝘯𝘰𝘸 what drives its choices—or is it guessing?
In our setting, we find that faithful models decide and report with the same layers. Unfaithful ones don't. 🧵
Eric Todd retweeted
At #COLM2026 this week!
No paper here, but lately I’ve been studying how training pressures shape whether Transformers memorize or generalize in multi-hop/world-modeling tasks, and how to maintain plasticity for continual learning.
Hit me up if you’re around!
Eric Todd retweeted
Come say hi at COLM! I’ll be around, and I’ll make a few spots available for 1:1s. As usual, I’m hiring PhD students. interp/safety/reasoning/understanding/++ !!
Eric Todd retweeted
Excited to share our @NeurIPSConf 2026 paper!
What goes on inside AI protein folding models? We use mechanistic interpretability to study ESMFold, OpenFold, and Boltz-1, and find biochemical representations like charge that can be used to steer predictions
folding.baulab.info/
Eric Todd retweeted
[New preprint] How do images in VLMs align with words? In this work, we found a set of attention heads responsible for OCR. But to our surprise, these heads were actually able to verbalize much more than just text. So, we used them to create a simple logit lens for image tokens!
Eric Todd retweeted
New paper! 🫡
We introduce Matryoshka Attribution, a new attribution method which uses gradient descent to find which parts of a neural network are responsible for a behaviour.
MAttr is #1 on the Mechanistic Interpretability Benchmark by a wide margin (2.9× the runner up).
Eric Todd retweeted
Introducing Parallax 🔍
We're a new UK/EU-based nonprofit research lab building scalable methods and infrastructure to audit the beliefs, goals, and plans that shape model behaviours in long-horizon agentic evaluations.
parallx.ai — Thread 🧵 1/
Eric Todd retweeted
How similar are two images? Prior metrics (e.g., LPIPS, DreamSim) give just a single score. But actually, there are multiple *senses* of similarity (color, pose, etc.)
We introduce TPIPS -- Text-Prompted Image Perceptual Similarity
"pip install tpips"
peterwang512.github.io/TPIPS 🧵
Eric Todd retweeted
What seminal papers should every grad student in deep learning know?
I'd like to update papers.baulab.info/ to add the most important new deep learning paper this year (or in the last few years).
What should be added?
