Roy Mayan

NLP and Computational Linguistics 💬

[Yoav Gur Arieh @GurYoav]

🧠 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 👇

[Yoav Gur Arieh @GurYoav]

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/

[Mor Geva @megamor2]

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 how steering a feature will affect model outputs.

New preprint led by my student @GurYoav with dream team @Roym4498, Chen Agassy, and Atticus Geiger 🧵1/

[Roy Mayan @Roym4498]

These bracelets are awesome!
Thank you Wiz 😎

@wiz_io #SecDevLove