Memory-assisted prompt editing to improve GPT-3 after deployment (Machine Learning Paper Explained)

#nlp #gpt3 #prompt

Large language models such as GPT-3 have enabled many breakthroughs and new applications recently, but they come with an important downside: Training them is very expensive, and even fine-tuning is often difficult. This paper presents an adaptive method to improve performance of such models after deployment, without ever changing the model itself. This is done by maintaining a memory of interactions and then dynamically adapting new prompts by augmenting them with memory content. This has many applications, from non-intrusive fine-tuning to personalization.

Sponsor: Introduction to Graph Neural Networks Course https://www.graphneuralnets.com/p/introduction-to-gnns?coupon_code=SUNGLASSES&affcode=999036_lzknae-d

OUTLINE: 0:00 - Intro 0:40 - Sponsor: Introduction to GNNs Course (link in description) 1:30 - Paper Overview: Improve GPT-3 after deployment via user feedback 5:30 - Proposed memory-based architecture 13:00 - A detailed look at the components 15:00 - Example tasks 24:30 - My concerns with the example setup 26:20 - Baselines used for comparison 29:50 - Experimental Results 34:20 - Conclusion & Comments

Paper: https://arxiv.org/abs/2201.06009 Code & Data: https://github.com/madaan/memprompt

Abstract: Large LMs such as GPT-3 are powerful, but can commit mistakes that are obvious to humans. For example, GPT-3 would mistakenly interpret "What word is similar to good?" to mean a homonym, while the user intended a synonym. Our goal is to effectively correct such errors via user interactions with the system but without retraining, which will be prohibitively costly. We pair GPT-3 with a growing memory of recorded cases where the model misunderstood the user's intents, along with user feedback for clarification. Such a memory allows our system to produce enhanced prompts for any new query based on the user feedback for error correction on similar cases in the past. On four tasks (two lexical tasks, two advanced ethical reasoning tasks), we show how a (simulated) user can interactively teach a deployed GPT-3, substantially increasing its accuracy over the queries with different kinds of misunderstandings by the GPT-3. Our approach is a step towards the low-cost utility enhancement for very large pre-trained LMs. All the code and data is available at this https URL.

Authors: Aman Madaan, Niket Tandon, Peter Clark, Yiming Yang

Links: Merch: http://store.ykilcher.com TabNine Code Completion (Referral): http://bit.ly/tabnine-yannick YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://discord.gg/4H8xxDF BitChute: https://www.bitchute.com/channel/yannic-kilcher LinkedIn: https://www.linkedin.com/in/ykilcher BiliBili: https://space.bilibili.com/2017636191

If you want to support me, ... https://www.youtube.com/watch?v=gYxJEd3EUKs