24 citations · 81 across the 44 of their papers we have counts for
4 papers · 1 filter
Conceptors for Semantic Steering
Ilias Triantafyllopoulos, Young-Min Cho, Ren Tao +6
Activation-based steering provides control of LLM behavior at inference time, but the dominant paradigm reduces each concept to a single direction whose geometry is left largely un…
The FIX Benchmark: Extracting Features Interpretable to eXperts
Helen Jin, Shreya Havaldar, Chaehyeon Kim +10
Feature-based methods are commonly used to explain model predictions, but these methods often implicitly assume that interpretable features are readily available. However, this is…
Empirical influence functions to understand the logic of fine-tuning
Jordan K. Matelsky, Lyle Ungar, Konrad P. Kording
Understanding the process of learning in neural networks is crucial for improving their performance and interpreting their behavior. This can be approximately understood by asking…
Continual Learning for Sentence Representations Using Conceptors
Tianlin Liu, Lyle Ungar, João Sedoc
Distributed representations of sentences have become ubiquitous in natural language processing tasks. In this paper, we consider a continual learning scenario for sentence represen…