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

• URL: http://arxiv.org/abs/2410.10584v1
• Date: Mon, 14 Oct 2024 14:56:01 GMT
• Title: STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with FeedBack
• Authors: Naman Gupta, Shashank Kirtania, Priyanshu Gupta, Krishna Kariya, Sumit Gulwani, Arun Iyer, Suresh Parthasarathy, Arjun Radhakrishna, Sriram K. Rajamani, Gustavo Soares,
• Abstract summary: We introduce FEED, a novel Structured Textual Actor-Critic Knowledge base editing with FEEDback approach. FEED iteratively refines the KB based on expert feedback using a multi-actor, centralized critic reinforcement learning framework. Experimental results show that FEED significantly improves quality and RAG system performance, enhancing accuracy by up to 8% over baselines.
• Score: 9.82445545347097
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) often generate incorrect or outdated information, especially in low-resource settings or when dealing with private data.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.

Related papers

• Keys to Robust Edits: from Theoretical Insights to Practical Advances [20.10464264597003]
  Large language models (LLMs) have revolutionized knowledge storage and retrieval, but face challenges with conflicting and outdated information. This work investigates the cause of failures in locate-and-edit methods, offering theoretical insights into their key-value modeling. Empirical analysis reveals that keys used by current methods fail to meet robustness and specificity requirements.
  arXiv  Detail & Related papers  (2024-10-12T02:54:12Z)
• Retrieving, Rethinking and Revising: The Chain-of-Verification Can Improve Retrieval Augmented Generation [38.80878966092216]
  Recent Retrieval Augmented Generation (RAG) aims to enhance Large Language Models (LLMs) We propose the chain-of-verification (CoV-RAG) to enhance the external retrieval correctness and internal generation consistency.
  arXiv  Detail & Related papers  (2024-10-08T08:34:54Z)
• Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language Models [65.10456412127405]
  A significant portion of real-world knowledge is stored in an unstructured format. Techniques like local layer key-value storage and term-driven optimization are not effective for handling unstructured knowledge. We propose a novel Unstructured Knowledge Editing method, namely UnKE, which extends previous assumptions in the layer dimension and token dimension.
  arXiv  Detail & Related papers  (2024-05-24T08:42:40Z)
• CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models [49.16989035566899]
  Retrieval-Augmented Generation (RAG) is a technique that enhances the capabilities of large language models (LLMs) by incorporating external knowledge sources. This paper constructs a large-scale and more comprehensive benchmark, and evaluates all the components of RAG systems in various RAG application scenarios.
  arXiv  Detail & Related papers  (2024-01-30T14:25:32Z)
• CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation [87.44350003888646]
  Eval-Instruct can acquire pointwise grading critiques with pseudo references and revise these critiques via multi-path prompting. CritiqueLLM is empirically shown to outperform ChatGPT and all the open-source baselines.
  arXiv  Detail & Related papers  (2023-11-30T16:52:42Z)
• Bridging the KB-Text Gap: Leveraging Structured Knowledge-aware Pre-training for KBQA [28.642711264323786]
  We propose a Structured Knowledge-aware Pre-training method (SKP) to bridge the gap between texts and structured KBs. In the pre-training stage, we introduce two novel structured knowledge-aware tasks, guiding the model to effectively learn the implicit relationship and better representations of complex subgraphs. In the downstream KBQA task, we further design an efficient linearization strategy and an interval attention mechanism, which assist the model to better encode complex subgraphs.
  arXiv  Detail & Related papers  (2023-08-28T09:22:02Z)
• Mapping and Cleaning Open Commonsense Knowledge Bases with Generative Translation [14.678465723838599]
  In particular, open information extraction (OpenIE) is often used to induce structure from a text. OpenIEs contain an open-ended, non-canonicalized set of relations, making the extracted knowledge's downstream exploitation harder. We propose approaching the problem by generative translation, i.e., by training a language model to generate fixed- assertions from open ones.
  arXiv  Detail & Related papers  (2023-06-22T09:42:54Z)
• Enriching Relation Extraction with OpenIE [70.52564277675056]
  Relation extraction (RE) is a sub-discipline of information extraction (IE) In this work, we explore how recent approaches for open information extraction (OpenIE) may help to improve the task of RE. Our experiments over two annotated corpora, KnowledgeNet and FewRel, demonstrate the improved accuracy of our enriched models.
  arXiv  Detail & Related papers  (2022-12-19T11:26:23Z)
• CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation [91.16551253297588]
  COunterfactual Generation via Retrieval and Editing (CORE) is a retrieval-augmented generation framework for creating diverse counterfactual perturbations for training. CORE first performs a dense retrieval over a task-related unlabeled text corpus using a learned bi-encoder. CORE then incorporates these into prompts to a large language model with few-shot learning capabilities, for counterfactual editing.
  arXiv  Detail & Related papers  (2022-10-10T17:45:38Z)
• EditEval: An Instruction-Based Benchmark for Text Improvements [73.5918084416016]
  This work presents EditEval: An instruction-based, benchmark and evaluation suite for automatic evaluation of editing capabilities. We evaluate several pre-trained models, which shows that InstructGPT and PEER perform the best, but that most baselines fall below the supervised SOTA. Our analysis shows that commonly used metrics for editing tasks do not always correlate well, and that optimization for prompts with the highest performance does not necessarily entail the strongest robustness to different models.
  arXiv  Detail & Related papers  (2022-09-27T12:26:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.