Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

This academic paper presents Inference-Time Intervention (ITI), a novel method for improving the truthfulness of large language models (LLMs) like LLaMA. ITI works by adjusting internal model activations during the process of generating a response, aiming to align the model's output with known facts and avoid common misconceptions. The research demonstrates that this technique significantly boosts performance on benchmarks like TruthfulQA, even with limited training data, while remaining computationally efficient. The study also explores the trade-off between truthfulness and helpfulness and suggests that LLMs might possess an internal representation of truth.