Active Retrieval Augmented Generation

By Zhengbao Jiang, Frank F. Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, Graham Neubig. Conference on Empirical Methods in Natural Language Processing, 2023

758 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/88884b8806262a4095036041e3567d450dba39f7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Fine-Tuning LLaMA for Multi-Stage Text Retrieval (2023, background): “This approach not only mitigates hallucinations but also enables LLMs to access knowledge that is not captured within their parameters (Yang et al., 2023; Jiang et al., 2023).”
A Comprehensive Evaluation of Tool-Assisted Generation Strategies (2023, methodology): “…this strategy as a more lightweight variant of refinement based on tools in comparison to RARR, and it is comparable to contemporaneously proposed (Jiang et al., 2023): After each CoT step, the step is checked for accuracy using a tool, and if found inaccurate, a new fixed step is generated to…”
Retrieval-Augmented Generation for Large Language Models: A Survey (2023, methodology): “Ad-ditionally, approaches like cohereAI rerank [ Cohere, 2023 ] , bge-rerank 7 , and LongLLMLingua [ Jiang et al. , 2023a ] re-calculate the semantic similarity between relevant text and the query, addressing the challenge of interpreting vector-based simulated searches for semantic similarity.”
Making Retrieval-Augmented Language Models Robust to Irrelevant Context (2023, methodology): “Other methods try to reduce the number of retrieval calls, by focusing on cases where confidence is low (Jiang et al., 2023) or retrieving information for rare entities (Mallen et al., 2023).”
Large Language Models: A Survey (2024, neutral): “Forward-looking Active Retrieval Augmented Generation (FLARE) [168] enhances the capabilities of Large Language Models (LLMs) by iteratively combining prediction and information retrieval.”
Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning (2025, neutral): “However, this could face challenges of retrieving irrelevant information (Jin et al., 2024) and failing to provide sufficiently useful context (Jiang et al., 2023).”
Retrieval-Augmented Generation for AI-Generated Content: A Survey (2024, neutral): “Rule-based: FLARE [210] actively decides whether and when to search through the probability in the generation process.”
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection (2023, methodology): “While prior work often retrieves only once at the beginning, Jiang et al. (2023) propose to adaptively retrieve passages for generation on top of a proprietary LLM or Schick et al. (2023) train an LM to generate API calls for named entities.”
WebArena: A Realistic Web Environment for Building Autonomous Agents (2023, background): “Existing works that measure answer recall in long-form QA share a similar spirit [13].”
Enabling Large Language Models to Generate Text with Citations (2023, methodology): “In I NLI - NE S EARCH , we allow LLMs to call “search” during the generation process (Yao et al., 2023; Press et al., 2022; Jiang et al., 2023).”
A Comprehensive Overview of Large Language Models (2023, positive): “Many of the multimodal tool augmentation systems employ multimodal LLMs [271], [272], [270], [261], while others utilize single modality LLMs and generate a plan on using different modality tools to solve multimodal queries [273].”
Large Language Models for Information Retrieval: A Survey (2023, neutral): “For example, when providing a passage about “Barack Obama”, language models may need additional knowledge about his university, which may not be included in the results of simply searching the initial query.”
A-MEM: Agentic Memory for LLM Agents (2025, neutral): “However, while agentic RAG approaches demonstrate agency in the retrieval phase by autonomously deciding when and what to retrieve [4, 14, 38], our agentic memory system exhibits agency at a more fundamental level through the autonomous evolution of its memory structure.”
Min-Cost Flow Routing for Evidence Assembly in Long Multimodal Documents (2026, unknown): “Iterative retrieval alternates evidence acquisition with reasoning (Press et al., 2023; Yao et al., 2023; Trivedi et al., 2023; Jiang et al., 2023; Shao et al., 2023; Asai et al., 2023).”