Active Retrieval Augmented Generation

• URL: http://arxiv.org/abs/2305.06983v2
• Date: Sun, 22 Oct 2023 00:11:13 GMT
• Title: Active Retrieval Augmented Generation
• Authors: Zhengbao Jiang, Frank F. Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, Graham Neubig
• Abstract summary: Augmenting large language models (LMs) by retrieving information from external knowledge resources is one promising solution. Most existing retrieval augmented LMs employ a retrieve-and-generate setup that only retrieves information once based on the input. We propose Forward-Looking Active REtrieval augmented generation (FLARE), a generic method which iteratively uses a prediction of the upcoming sentence to anticipate future content.
• Score: 123.68874416084499
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite the remarkable ability of large language models (LMs) to comprehend and generate language, they have a tendency to hallucinate and create factually inaccurate output. Augmenting LMs by retrieving information from external knowledge resources is one promising solution. Most existing retrieval augmented LMs employ a retrieve-and-generate setup that only retrieves information once based on the input. This is limiting, however, in more general scenarios involving generation of long texts, where continually gathering information throughout generation is essential. In this work, we provide a generalized view of active retrieval augmented generation, methods that actively decide when and what to retrieve across the course of the generation. We propose Forward-Looking Active REtrieval augmented generation (FLARE), a generic method which iteratively uses a prediction of the upcoming sentence to anticipate future content, which is then utilized as a query to retrieve relevant documents to regenerate the sentence if it contains low-confidence tokens. We test FLARE along with baselines comprehensively over 4 long-form knowledge-intensive generation tasks/datasets. FLARE achieves superior or competitive performance on all tasks, demonstrating the effectiveness of our method. Code and datasets are available at https://github.com/jzbjyb/FLARE.

Related papers

• Retrieve-Plan-Generation: An Iterative Planning and Answering Framework for Knowledge-Intensive LLM Generation [47.22520829950929]
  We propose the Retrieve-Plan-Generation (RPG) framework for large language models (LLMs) RPG generates plan tokens to guide subsequent generation in the plan stage. In the answer stage, the model selects relevant fine-grained paragraphs based on the plan and uses them for further answer generation.
  arXiv  Detail & Related papers  (2024-06-21T08:45:52Z)
• DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Models [12.580730377998158]
  We introduce Dynamic Retrieval Augmented Generation based on the real-time Information Needs of Large Language Models (LLMs) Our framework is specifically designed to make decisions on when and what to retrieve based on the LLM's real-time information needs during the text generation process. Experimental results show that DRAGIN achieves superior performance on all tasks, demonstrating the effectiveness of our method.
  arXiv  Detail & Related papers  (2024-03-15T07:45:37Z)
• ARKS: Active Retrieval in Knowledge Soup for Code Generation [18.22108704150575]
  We introduce Active Retrieval in Knowledge Soup (ARKS), an advanced strategy for generalizing large language models for code. We employ an active retrieval strategy that iteratively refines the query and updates the knowledge soup. Experimental results on ChatGPT and CodeLlama demonstrate a substantial improvement in the average execution accuracy of ARKS on LLMs.
  arXiv  Detail & Related papers  (2024-02-19T17:37:28Z)
• Large Language Models for Generative Information Extraction: A Survey [89.71273968283616]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in text understanding and generation. We present an extensive overview by categorizing these works in terms of various IE subtasks and techniques. We empirically analyze the most advanced methods and discover the emerging trend of IE tasks with LLMs.
  arXiv  Detail & Related papers  (2023-12-29T14:25:22Z)
• Contextual Knowledge Pursuit for Faithful Visual Synthesis [33.191847768674826]
  In large language models (LLMs), a prevalent strategy to reduce hallucinations is to retrieve factual knowledge from an external database. This paper proposes Conparametric Knowledge Pursuit (CKPT), a framework that leverages the complementary strengths of external and parametric knowledge to help generators produce reliable visual content.
  arXiv  Detail & Related papers  (2023-11-29T18:51:46Z)
• DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text [73.68051228972024]
  Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when relying on their internal knowledge. Retrieval-augmented LLMs have emerged as a potential solution to ground LLMs in external knowledge.
  arXiv  Detail & Related papers  (2023-10-31T04:37:57Z)
• RegaVAE: A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling [79.56442336234221]
  We introduce RegaVAE, a retrieval-augmented language model built upon the variational auto-encoder (VAE) It encodes the text corpus into a latent space, capturing current and future information from both source and target text. Experimental results on various datasets demonstrate significant improvements in text generation quality and hallucination removal.
  arXiv  Detail & Related papers  (2023-10-16T16:42:01Z)
• Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy [164.83371924650294]
  We show that strong performance can be achieved by a method we call Iter-RetGen, which synergizes retrieval and generation in an iterative manner. A model output shows what might be needed to finish a task, and thus provides an informative context for retrieving more relevant knowledge. Iter-RetGen processes all retrieved knowledge as a whole and largely preserves the flexibility in generation without structural constraints.
  arXiv  Detail & Related papers  (2023-05-24T16:17:36Z)
• Generate rather than Retrieve: Large Language Models are Strong Context Generators [74.87021992611672]
  We present a novel perspective for solving knowledge-intensive tasks by replacing document retrievers with large language model generators. We call our method generate-then-read (GenRead), which first prompts a large language model to generate contextutal documents based on a given question, and then reads the generated documents to produce the final answer.
  arXiv  Detail & Related papers  (2022-09-21T01:30:59Z)

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.