8 citations · 19 across the 10 of their papers we have counts for
5 papers · 1 filter
Identifying Introspection From the Inside
David I. Atkinson, Dillon Plunkett, David Bau
Large language models make claims about themselves that are both consequential and increasingly difficult to verify from behavior alone. How can we distinguish plausible confabulat…
In-Context Learning Beyond Copying: A Training-Time Analysis of Abstractive ICL
Kerem Sahin, Sheridan Feucht, Adam Belfki +4
The sudden emergence of induction circuits and the ability to perform in-context copying in LLMs coincides with a sharp drop in training loss over a short span of the training proc…
Language Models use Lookbacks to Track Beliefs
Nikhil Prakash, Natalie Shapira, Arnab Sen Sharma +5
How do language models (LMs) represent characters' beliefs, especially when those beliefs may differ from reality? This question lies at the heart of understanding the Theory of Mi…
Erasing Conceptual Knowledge from Language Models
Rohit Gandikota, Sheridan Feucht, Samuel Marks +1
In this work, we introduce Erasure of Language Memory (ELM), a principled approach to concept-level unlearning that operates by matching distributions defined by the model's own in…
Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking
Nikhil Prakash, Tamar Rott Shaham, Tal Haklay +2
Fine-tuning on generalized tasks such as instruction following, code generation, and mathematics has been shown to enhance language models' performance on a range of tasks. Neverth…