97 min listen
Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies
Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies
ratings:
Length:
64 minutes
Released:
Aug 19, 2023
Format:
Podcast episode
Description
Large language models (LLMs) have demonstrated remarkable performance across a wide array of NLP tasks. However, their efficacy is undermined by undesired and inconsistent behaviors, including hallucination, unfaithful reasoning, and toxic content. A promising approach to rectify these flaws is self-correction, where the LLM itself is prompted or guided to fix problems in its own output. Techniques leveraging automated feedback -- either produced by the LLM itself or some external system -- are of particular interest as they are a promising way to make LLM-based solutions more practical and deployable with minimal human feedback. This paper presents a comprehensive review of this emerging class of techniques. We analyze and taxonomize a wide array of recent work utilizing these strategies, including training-time, generation-time, and post-hoc correction. We also summarize the major applications of this strategy and conclude by discussing future directions and challenges.
2023: Liangming Pan, Michael Saxon, Wenda Xu, Deepak Nathani, Xinyi Wang, William Yang Wang
https://arxiv.org/pdf/2308.03188v1.pdf
2023: Liangming Pan, Michael Saxon, Wenda Xu, Deepak Nathani, Xinyi Wang, William Yang Wang
https://arxiv.org/pdf/2308.03188v1.pdf
Released:
Aug 19, 2023
Format:
Podcast episode
Titles in the series (100)
Llama 2: Open Foundation and Fine-Tuned Chat Models: In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama 2-Chat, are optimized for dialogue use ca... by Papers Read on AI