The paper introduces SYNTRA, a method to reduce hallucination in large language models (LLMs) on abstractive summarization tasks. By optimizing the LLM's system message via prefix-tuning on a synthetic task, hallucination is reduced on real-world downstream tasks.

https://arxiv.org/abs//2310.06827

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