activity
20222025
most citedEmergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task

63 citations · 108 across the 9 of their papers we have counts for

collaborators
Showing 2023Show all

1 paper · 1 filter

cs.LG2023★ 40 cited

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…