@unpublished{gupta2024stackfeed,
author = {Gupta, Naman and Kirtania, Shashank and Gupta, Priyanshu and Kariya, Krishna and Gulwani, Sumit and Iyer, Arun and Parthasarathy, Suresh and Radhakrishna, Arjun and Rajamani, Sriram and Soares, Gustavo},
title = {STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with Feedback},
year = {2024},
month = {October},
abstract = {Large Language Models (LLMs) often generate incorrect or outdated information, especially in low-resource settings or when dealing with private data. To address this, Retrieval-Augmented Generation (RAG) uses external knowledge bases (KBs), but these can also suffer from inaccuracies. We introduce STACKFEED, a novel Structured Textual Actor-Critic Knowledge base editing with FEEDback approach that iteratively refines the KB based on expert feedback using a multi-actor, centralized critic reinforcement learning framework. Each document is assigned to an actor, modeled as a ReACT agent, which performs structured edits based on document-specific targeted instructions from a centralized critic. Experimental results show that STACKFEED significantly improves KB quality and RAG system performance, enhancing accuracy by up to 8% over baselines.},
url = {http://approjects.co.za/?big=en-us/research/publication/stackfeed/},
note = {Preprint},
}