4 papers
Tracing mechanisms of sycophantic agreement in language models
Sixing Chen, Zhuofan Josh Ying, Logan Riggs Smith +2
Sycophantic agreement in language models refers to the tendency to overly affirm a user's stated beliefs or preferences, often at the expense of factual accuracy. Although it is wi…
Factual Retrieval in LLMs Is a Redundant, Distributed and Non-Contiguous Process
Hail Hochman, Natalie Shapira, Yoav Goldberg
Large language models (LLMs) store and recall factual knowledge, yet the precise mechanism of how entity representations are transformed to enable specific attribute retrieval rema…
LLMs Process Lists With General Filter Heads
Arnab Sen Sharma, Giordano Rogers, Natalie Shapira +1
We investigate the mechanisms underlying a range of list-processing tasks in LLMs, and we find that LLMs have learned to encode a compact, causal representation of a general filter…
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…