Truth Neurons
This addresses the reliability and safety of language models by revealing mechanistic insights into truthfulness, though it appears incremental as it builds on prior findings about truthfulness geometry.
The paper tackles the problem of understanding how truthfulness is encoded in language models by identifying 'truth neurons' that represent truthfulness in a subject-agnostic way, with experiments showing that suppressing these neurons degrades performance on TruthfulQA and other benchmarks.
Despite their remarkable success and deployment across diverse workflows, language models sometimes produce untruthful responses. Our limited understanding of how truthfulness is mechanistically encoded within these models jeopardizes their reliability and safety. In this paper, we propose a method for identifying representations of truthfulness at the neuron level. We show that language models contain truth neurons, which encode truthfulness in a subject-agnostic manner. Experiments conducted across models of varying scales validate the existence of truth neurons, confirming that the encoding of truthfulness at the neuron level is a property shared by many language models. The distribution patterns of truth neurons over layers align with prior findings on the geometry of truthfulness. Selectively suppressing the activations of truth neurons found through the TruthfulQA dataset degrades performance both on TruthfulQA and on other benchmarks, showing that the truthfulness mechanisms are not tied to a specific dataset. Our results offer novel insights into the mechanisms underlying truthfulness in language models and highlight potential directions toward improving their trustworthiness and reliability.