5 papers · 1 filter
LLMs Encode Harmfulness and Refusal Separately
Jiachen Zhao, Jing Huang, Zhengxuan Wu +2
LLMs are trained to refuse harmful instructions, but do they truly understand harmfulness beyond just refusing? Prior work has shown that LLMs' refusal behaviors can be mediated by…
In-Context Algebra
Eric Todd, Jannik Brinkmann, Rohit Gandikota +1
We investigate the mechanisms that arise when transformers are trained to solve arithmetic on sequences where tokens are variables whose meaning is determined only through their in…
Vector Arithmetic in Concept and Token Subspaces
Sheridan Feucht, Byron Wallace, David Bau
In order to predict the next token, LLMs must represent semantic and surface-level information about the current word. Previous work identified two types of attention heads that di…
Discovering Forbidden Topics in Language Models
Can Rager, Chris Wendler, Rohit Gandikota +1
Refusal discovery is the task of identifying the full set of topics that a language model refuses to discuss. We introduce this new problem setting and develop a refusal discovery…
Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs
Sheridan Feucht, David Atkinson, Byron Wallace +1
LLMs process text as sequences of tokens that roughly correspond to words, where less common words are represented by multiple tokens. However, individual tokens are often semantic…