2 papers
cs.LG2024
Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
Kenneth Li, Oam Patel, Fernanda Viégas +2
We introduce Inference-Time Intervention (ITI), a technique designed to enhance the "truthfulness" of large language models (LLMs). ITI operates by shifting model activations durin…
cs.LG2024
Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
Kenneth Li, Aspen K. Hopkins, David Bau +3
Language models show a surprising range of capabilities, but the source of their apparent competence is unclear. Do these networks just memorize a collection of surface statistics,…