Want to create an interactive transcript for this episode?
Podcast: Arxiv Papers
Episode: Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models
Description:
The paper explores how sparse autoencoders reveal mechanisms behind hallucinations in language models, focusing on entity recognition and self-knowledge, influencing the model's response behavior.
https://arxiv.org/abs//2411.14257
YouTube: https://www.youtube.com/@ArxivPapers
TikTok: https://www.tiktok.com/@arxiv_papers
Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016
Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers