🧠 To reason over text and track entities, we find that language models use three types of 'pointers'! They were thought to rely only on a positional one—but when many entities appear, that system breaks down. Our new paper shows what these pointers are and how they interact 👇

🚨 New Paper 🚨 How effectively do reasoning models reevaluate their thought? We find that: - Models excel at identifying unhelpful thoughts but struggle to recover from them - Smaller models can be more robust - Self-reevaluation ability is far from true meta-cognitive awareness 1/N 🧵

New Paper Alert! Can we precisely erase conceptual knowledge from LLM parameters? Most methods are shallow, coarse, or overreach, adversely affecting related or general knowledge. We introduce🪝𝐏𝐈𝐒𝐂𝐄𝐒 — a general framework for Precise In-parameter Concept EraSure. 🧵 1/

Checkout Benno's notes about our impact of interpretability paper 👇. Also, we are organizing a workshop at #ICML2025 which is inspired by some of the questions discussed in the paper: actionable-interpretability.github.io

Have work on the actionable impact of interpretability findings? Consider submitting to our Actionable Interpretability workshop at ICML! See below for more info. Website: actionable-interpretability.github.io Deadline: May 9

🎉 Our Actionable Interpretability workshop has been accepted to #ICML2025! 🎉 > Follow @actinterp.bsky.social > Website actionable-interpretability.github.io @talhaklay.bsky.social @anja.re @mariusmosbach.bsky.social @sarah-nlp.bsky.social @iftenney.bsky.social Paper submission deadline: May 9th!

📣 📣 Looking for ethics reviewers for COLM 2025! Please sign up and share the form below 👇 forms.gle/3a52jbDNB9bd...

Communication between LLM agents can be super noisy! One rogue agent can easily drag the whole system into failure 😱 We find that (1) it's possible to detect rogue agents early on (2) interventions can boost system performance by up to 20%! Thread with details and paper link below!

How can we interpret LLM features at scale? 🤔 Current pipelines use activating inputs, which is costly and ignores how features causally affect model outputs! We propose efficient output-centric methods that better predict the steering effect of a feature. New preprint led by @yoav.ml 🧵1/

🚨 New Paper Alert: Open Problem in Machine Unlearning for AI Safety 🚨 Can AI truly "forget"? While unlearning promises data removal, controlling emergent capabilities is a inherent challenge. Here's why it matters: 👇 Paper: arxiv.org/pdf/2501.04952 1/8

What's in an attention head? 🤯 We present an efficient framework – MAPS – for inferring the functionality of attention heads in LLMs ✨directly from their parameters✨ A new preprint with Amit Elhelo 🧵 (1/10)

We invite nominations to join the ACL2025 PC as reviewer or area chair(AC). Review process through ARR Feb cycle. Tentative timeline: Review 1-20 Mar 2025, Rebuttal is 26-31 Mar 2025. ACs must be available throughout the Feb cycle. Nominations by 20 Dec 2024: shorturl.at/TaUh9 #NLProc #ACL2025NLP

📣📣 Wanna be an Area Chair or a Reviewer for @aclmeeting.bsky.social or know someone who would? Nominations and self-nominations go here 👇 docs.google.com/forms/d/e/1F...

I am seriously behind uploading Learning Machines videos, but I did want to get @jonathanberant.bsky.social's out sooner than later. It's not only a great talk, it also gives a remarkably broad overview and contextualization, so it's an excellent way to ramp up on post-training youtu.be/2AthqCX3h8U

Sparks of multi-hop reasoning ✨

Post a photo of yourself from a different era

🚨 New Paper 🚨 Can LLMs perform latent multi-hop reasoning without exploiting shortcuts? We find the answer is yes – they can recall and compose facts not seen together in training or guessing the answer, but success greatly depends on the type of the bridge entity (80% for country, 6% for year)! 1/N

It is promising to use natural language latent reasoning to interpret LLMs. But we need confidence that the latent reasoning is interpretable and faithful, such that human oversight of the reasoning trace counts as meaningful supervision. Here are 2 reasons this may be hard. 🧵

mech interp: bsky.app/starter-pack... women in nlp: bsky.app/starter-pack... nlp #1: bsky.app/starter-pack... nlp #2: bsky.app/starter-pack... ml/data/tech: bsky.app/starter-pack... robotics & ai: bsky.app/starter-pack...

First post here, let's see how it goes 🦋 Looking for an emergency reviewer 🚨🚨 For an ARR submission about tool-usage in LLMs, should be submitted within the next 30 hours. If you have reviewed before for ARR/*CL conferences before and interested, please DM me 🙏 #NLProc #NLP