# STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with FeedBack

Source: [STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with FeedBack](<https://www.sota2.com/research/paper/68fa75311e209131cea66479>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-11-05T05:01:09.456Z

Authors: Shashank Kirtania, Naman Gupta, Priyanshu Gupta, Krishna Kariya, Sumit Gulwani, Arun Iyer, Suresh Parthasarathy, Arjun Radhakrishna, Sriram K. Rajamani, Gustavo Soares

Published: 2024-10-14T14:56:01.000Z

## 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Large Language Models (LLMs) often generate incorrect or outdated information, especially in low-resource settings or when dealing with private data.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. STACKFEED defines a ReACT actor agent on each document to perform structured edits based on document specific targeted instructions. Experimental results showcase that STACKFEED significantly improves KB quality and performance of the RAG system. We evaluate STACKFEED on low-resource programming problems, modified python packaged and factual question-answering tasks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2410.10584>)

[PDF](<https://arxiv.org/pdf/2410.10584.pdf>)
