Knowledge Tree
Relations (1)
related 0.10 — supporting 1 fact
The concept of consciousness is linked to TruthfulQA through research investigating deception-related features in large language models, where [1] demonstrates how manipulating these features affects the model's performance on the TruthfulQA benchmark.
Facts (1)
Sources
The Evidence for AI Consciousness, Today - AI Frontiers ai-frontiers.org 1 fact
claimThe researchers validated the deception-related features identified in Llama 70B using TruthfulQA, a standard benchmark for common factual misconceptions, demonstrating that amplifying these features increases the model's willingness to state falsehoods.