AI summary · arXiv: 2310.11511v1 · cs.CL

Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection

Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, Hannaneh Hajishirzi
Original paper Submitted to arXiv on 17 Oct. 2023 30 pages, 2 figures, 12 tables License: CC BY 4.0

How to read this summary? Illustrated guide

The essentials

  • Large language models (LLMs) often generate responses with factual inaccuracies due to heavy reliance on training data.
  • Retrieval-Augmented Generation (RAG) supplements LLMs with external knowledge to improve response accuracy.
  • Traditional RAG approaches indiscriminately retrieve fixed passages, limiting versatility and leading to unhelpful responses.
  • Self-Reflective Retrieval-Augmented Generation (Self-RAG) empowers LLMs to adaptively retrieve passages and engage in self-reflection during generation.
  • Self-RAG uses reflection tokens for the LLM to control behavior during inference, tailoring responses based on task requirements.
  • Experimental evaluations show that Self-RAG outperforms existing models in fact verification, multiple-choice reasoning, open-domain question answering, biography writing, and long-form QA tasks.

Key points written by AI: they may contain errors, check them against the paper.

AI-generated keywords: Large Language Models Retrieval-Augmented Generation Self-Reflective Retrieval-Augmented Generation Factuality Performance

Read further

  • Comprehensive Summary
  • Layman's Summary
  • Blog article
  • Original abstract
In the realm of large language models (LLMs), there is a common issue where responses generated by these models often contain factual inaccuracies due to their heavy reliance on the knowledge they have been trained on. To address this problem, researchers have developed Retrieval-Augmented Generation (RAG), a method that supplements LLMs with relevant external knowledge to improve response accuracy. However, traditional RAG approaches indiscriminately retrieve and incorporate a fixed number of passages, regardless of their relevance or necessity, which can limit the versatility of the LLM or lead to unhelpful responses. To enhance the quality and factuality of LLM-generated responses, a new framework called Self-Reflective Retrieval-Augmented Generation (Self-RAG) has been introduced. This innovative framework empowers an LLM to adaptively retrieve passages on-demand and engage in self-reflection during the generation process. By utilizing special tokens known as reflection tokens, the LLM can control its behavior during inference, allowing it to tailor its responses based on specific task requirements. Experimental evaluations of Self-RAG against state-of-the-art LLMs and retrieval-augmented models across various tasks demonstrate significant improvements in performance. In closed-set tasks such as fact verification and multiple-choice reasoning datasets, Self-RAG showcases superior accuracy compared to existing models. For short-form generation tasks like open-domain question answering, Self-RAG excels at providing accurate answers to diverse queries. Additionally, in long-form generation tasks such as biography writing and long-form QA, Self-RAG outperforms other models in terms of correctness, fluency, and citation precision. Overall, proves to be a groundbreaking framework that not only enhances the factuality and quality of LLM-generated responses but also improves their overall performance across a wide range of tasks.

Was this synthesis useful?

Score: 0

Why do we need votes?

Votes are used to determine whether we need to re-run our summarizing tools. If the count reaches -10, our tools can be restarted.

Figures and plots

Ask about a figure by number or use its question button to request visual analysis. Up to two figures and four image panels per question. Values read from plots are approximate; check the original data.

AI assistant instructions?

Tools for this paper

Explain it differently 1 free rewrite left today
Save to a collection Group papers in collections to compare them, chat with them and export them. Continue with Google Create a free account Log in

Advanced tools Premium

For researchers who follow a field closely: citation alerts, journal-club slides, version comparison and Zotero export. Discover Premium

Zotero Zotero guide
Citation alerts 299 papers already cite it: be emailed each new one. Citation alerts guide
Who works on it?

Among the 31 papers around this one, the name that comes back most: Ori Ram (2 papers)

Continue with Google Create a free account: your first map is free
Weekly letter The latest letter of its field, "Artificial intelligence this week" of 16 November 2026: Artificial intelligence this week: What impressive scores leave out · Receive one by email for free

Papers around this one

See them on a map

Ranked by how close their title and abstract are to this paper’s. Select some to read them together.

Closest papers

  1. Very close Another approach to the problem
    Learning When to Retrieve, What to Rewrite, and How to Respond in Conversational QA
    Nirmal Roy, Leonardo F. R. Ribeiro, Rexhina Blloshmi et al. · 2024 · Computation and Language · cited 25 times · AI summary available

    Learning When to Retrieve, What to Rewrite, and How to Respond lets an LLM decide when to retrieve for conversational QA, while Self-RAG uses on-demand retrieval and self-reflection.

    Abstract

    Augmenting Large Language Models (LLMs) with information retrieval capabilities (i.e., Retrieval-Augmented Generation (RAG)) has proven beneficial for knowledge-intensive tasks. However, understanding users' contextual search intent when generating responses is an understudied topic for conversational question answering (QA). This conversational extension leads to additional concerns when compared to single-turn QA as it is more challenging for systems to comprehend conversational context and manage retrieved passages over multiple turns. In this work, we propose a method for enabling LLMs to decide when to retrieve in RAG settings given a conversational context. When retrieval is deemed nec…

  2. Very close Same method, another problem
    SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains
    Ran Xu, Hui Liu, Sreyashi Nag et al. · 2024 · Computation and Language · cited 57 times · AI summary available

    SimRAG uses self-training to adapt RAG for specialized-domain question answering, whereas Self-RAG trains an LLM to retrieve and critique its generations.

    Abstract

    Retrieval-augmented generation (RAG) enhances the question-answering (QA) abilities of large language models (LLMs) by integrating external knowledge. However, adapting general-purpose RAG systems to specialized fields such as science and medicine poses unique challenges due to distribution shifts and limited access to domain-specific data. To tackle this, we propose SimRAG, a self-training approach that equips the LLM with joint capabilities of question answering and question generation for domain adaptation. Our method first fine-tunes the LLM on instruction-following, question-answering, and search-related data. Then, it prompts the same LLM to generate diverse domain-relevant questions f…

  3. Very close Another approach to the problem
    Corrective Retrieval Augmented Generation
    Shi-Qi Yan, Jia-Chen Gu, Yun Zhu et al. · 2024 · Computation and Language · preprint, not peer reviewed · cited 349 times · AI summary available

    Corrective Retrieval Augmented Generation evaluates retrieved-document quality to improve robustness, while Self-RAG uses reflection tokens to assess passages and generations.

    Abstract

    Large language models (LLMs) inevitably exhibit hallucinations since the accuracy of generated texts cannot be secured solely by the parametric knowledge they encapsulate. Although retrieval-augmented generation (RAG) is a practicable complement to LLMs, it relies heavily on the relevance of retrieved documents, raising concerns about how the model behaves if retrieval goes wrong. To this end, we propose the Corrective Retrieval Augmented Generation (CRAG) to improve the robustness of generation. Specifically, a lightweight retrieval evaluator is designed to assess the overall quality of retrieved documents for a query, returning a confidence degree based on which different knowledge retriev…

  4. Very close Review
    Retrieval-Augmented Generation for Large Language Models: A Survey
    Yunfan Gao, Yun Xiong, Xinyu Gao et al. · 2023 · Computation and Language · preprint, not peer reviewed · cited 4,438 times · AI summary available

    Retrieval-Augmented Generation for Large Language Models: A Survey reviews RAG methods and applications, including their effects on hallucination and answer accuracy.

    Abstract

    Large language models (LLMs) demonstrate powerful capabilities, but they still face challenges in practical applications, such as hallucinations, slow knowledge updates, and lack of transparency in answers. Retrieval-Augmented Generation (RAG) refers to the retrieval of relevant information from external knowledge bases before answering questions with LLMs. RAG has been demonstrated to significantly enhance answer accuracy, reduce model hallucination, particularly for knowledge-intensive tasks. By citing sources, users can verify the accuracy of answers and increase trust in model outputs. It also facilitates knowledge updates and the introduction of domain-specific knowledge. RAG effectivel…

  5. Very close
    Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting
    Zilong Wang, Zifeng Wang, Long T. Le et al. · 2024 · International Conference on Learning Representations · cited 125 times · Not summarized yet
    Abstract

    Retrieval augmented generation (RAG) combines the generative abilities of large language models (LLMs) with external knowledge sources to provide more accurate and up-to-date responses. Recent RAG advancements focus on improving retrieval outcomes through iterative LLM refinement or self-critique capabilities acquired through additional instruction tuning of LLMs. In this work, we introduce Speculative RAG - a framework that leverages a larger generalist LM to efficiently verify multiple RAG drafts produced in parallel by a smaller, distilled specialist LM. Each draft is generated from a distinct subset of retrieved documents, offering diverse perspectives on the evidence while reducing inpu…

  6. Very close
    SKILL-RAG: Self-Knowledge Induced Learning and Filtering for Retrieval-Augmented Generation
    Tomoaki Isoda · 2025 · arXiv.org · preprint, not peer reviewed · Not summarized yet
    Abstract

    Retrieval-Augmented Generation (RAG) has significantly improved the performance of large language models (LLMs) on knowledge-intensive tasks in recent years. However, since retrieval systems may return irrelevant content, incorporating such information into the model often leads to hallucinations. Thus, identifying and filtering out unhelpful retrieved content is a key challenge for improving RAG performance.To better integrate the internal knowledge of the model with external knowledge from retrieval, it is essential to understand what the model"knows"and"does not know"(which is also called"self-knowledge"). Based on this insight, we propose SKILL-RAG (Self-Knowledge Induced Learning and Fi…

  7. Very close Broader context
    Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models
    Fei Wang, Xingchen Wan, Ruoxi Sun et al. · 2024 · Computation and Language · cited 90 times · AI summary available

    Astute RAG analyzes errors and conflicts caused by imperfect retrieval, a concern related to Self-RAG's effort to assess retrieved passages.

    Abstract

    Retrieval-Augmented Generation (RAG), while effective in integrating external knowledge to address the limitations of large language models (LLMs), can be undermined by imperfect retrieval, which may introduce irrelevant, misleading, or even malicious information. Despite its importance, previous studies have rarely explored the behavior of RAG through joint analysis on how errors from imperfect retrieval attribute and propagate, and how potential conflicts arise between the LLMs' internal knowledge and external sources. We find that imperfect retrieval augmentation might be inevitable and quite harmful, through controlled analysis under realistic conditions. We identify the knowledge confli…

  8. Very close
    Bidirectional RAG: Safe Self-Improving Retrieval-Augmented Generation Through Multi-Stage Validation
    Teja Chinthala · 2025 · arXiv.org · preprint, not peer reviewed · cited 1 time · Not summarized yet
    Abstract

    Retrieval-Augmented Generation RAG systems enhance large language models by grounding responses in external knowledge bases, but conventional RAG architectures operate with static corpora that cannot evolve from user interactions. We introduce Bidirectional RAG, a novel RAG architecture that enables safe corpus expansion through validated write back of high quality generated responses. Our system employs a multi stage acceptance layer combining grounding verification (NLI based entailment, attribution checking, and novelty detection to prevent hallucination pollution while enabling knowledge accumulation. Across four datasets Natural Questions, TriviaQA, HotpotQA, Stack Overflow with three r…

Prior work it builds on

  1. Very close A method it uses
    Active Retrieval Augmented Generation
    Zhengbao Jiang, Frank F. Xu, Luyu Gao et al. · 2023 · Computation and Language · cited 961 times · AI summary available
    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 wh…

  2. Close A method it uses
    In-Context Retrieval-Augmented Language Models
    Ori Ram, Yoav Levine, Itay Dalmedigos et al. · 2023 · Transactions of the Association for Computational Linguistics · cited 1,192 times · AI summary available
    Abstract

    Abstract Retrieval-Augmented Language Modeling (RALM) methods, which condition a language model (LM) on relevant documents from a grounding corpus during generation, were shown to significantly improve language modeling performance. In addition, they can mitigate the problem of factually inaccurate text generation and provide natural source attribution mechanism. Existing RALM approaches focus on modifying the LM architecture in order to facilitate the incorporation of external information, significantly complicating deployment. This paper considers a simple alternative, which we dub In-Context RALM: leaving the LM architecture unchanged and prepending grounding documents to the input, witho…

  3. Close Used in depth by this paper A method it uses
    Enabling Large Language Models to Generate Text with Citations
    Tianyu Gao, Howard Yen, Jia-Tong Yu et al. · 2023 · Conference on Empirical Methods in Natural Language Processing · cited 947 times · AI summary available
    Abstract

    Large language models (LLMs) have emerged as a widely-used tool for information seeking, but their generated outputs are prone to hallucination. In this work, our aim is to allow LLMs to generate text with citations, improving their factual correctness and verifiability. Existing work mainly relies on commercial search engines and human evaluation, making it challenging to reproduce and compare different modeling approaches. We propose ALCE, the first benchmark for Automatic LLMs' Citation Evaluation. ALCE collects a diverse set of questions and retrieval corpora and requires building end-to-end systems to retrieve supporting evidence and generate answers with citations. We develop automatic…

  4. Close
    Making Retrieval-Augmented Language Models Robust to Irrelevant Context
    Ori Yoran, Tomer Wolfson, Ori Ram et al. · 2023 · International Conference on Learning Representations · cited 533 times · AI summary available
    Abstract

    Retrieval-augmented language models (RALMs) hold promise to produce language understanding systems that are are factual, efficient, and up-to-date. An important desideratum of RALMs, is that retrieved information helps model performance when it is relevant, and does not harm performance when it is not. This is particularly important in multi-hop reasoning scenarios, where misuse of irrelevant evidence can lead to cascading errors. However, recent work has shown that retrieval augmentation can sometimes have a negative effect on performance. In this work, we present a thorough analysis on five open-domain question answering benchmarks, characterizing cases when retrieval reduces accuracy. We …

  5. Close A method it uses
    Self-Refine: Iterative Refinement with Self-Feedback
    Aman Madaan, Niket Tandon, Prakhar Gupta et al. · 2023 · Neural Information Processing Systems · cited 5,475 times · AI summary available
    Abstract

    Like humans, large language models (LLMs) do not always generate the best output on their first try. Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from LLMs through iterative feedback and refinement. The main idea is to generate an initial output using an LLMs; then, the same LLMs provides feedback for its output and uses it to refine itself, iteratively. Self-Refine does not require any supervised training data, additional training, or reinforcement learning, and instead uses a single LLM as the generator, refiner, and feedback provider. We evaluate Self-Refine across 7 diverse tasks, ranging from dialog response gener…

Papers that cite it

  1. Very close Uses this paper in depth
    Characterising and Analysing Retrieval-Augmented Generation Techniques
    E. Igbekele, O. Daramola · 2026 · Not summarized yet
    Abstract

    The advent of Large Language Models (LLMs) across many application domains has increased the need for Retrieval-Augmented Generation (RAG) to reduce hallucinations and improve LLM performance. Thus far, several RAG techniques with impressive features and capabilities have been proposed in the literature, making it a herculean task to select the most appropriate RAG techniques for specific problem scenarios. Thus, we propose a conceptual framework comprising main dimensions and sub-dimensions for characterising (defining"what it is") and analysing (defining"how well it does") existing RAG techniques. The conceptual framework was developed through a qualitative analysis of the attributes of RA…

  2. Very close
    The Power of Noise: Redefining Retrieval for RAG Systems
    Florin Cuconasu, Giovanni Trappolini, Federico Siciliano et al. · 2024 · Information Retrieval · cited 278 times · AI summary available
    Abstract

    Retrieval-Augmented Generation (RAG) systems represent a significant advancement over traditional Large Language Models (LLMs). RAG systems enhance their generation ability by incorporating external data retrieved through an Information Retrieval (IR) phase, overcoming the limitations of standard LLMs, which are restricted to their pre-trained knowledge and limited context window. Most research in this area has predominantly concentrated on the generative aspect of LLMs within RAG systems. Our study fills this gap by thoroughly and critically analyzing the influence of IR components on RAG systems. This paper analyzes which characteristics a retriever should possess for an effective RAG's pr…

  3. Very close
    Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach
    Zhuowan Li, Cheng Li, Mingyang Zhang et al. · 2024 · Computation and Language · cited 71 times · AI summary available
    Abstract

    Retrieval Augmented Generation (RAG) has been a powerful tool for Large Language Models (LLMs) to efficiently process overly lengthy contexts. However, recent LLMs like Gemini-1.5 and GPT-4 show exceptional capabilities to understand long contexts directly. We conduct a comprehensive comparison between RAG and long-context (LC) LLMs, aiming to leverage the strengths of both. We benchmark RAG and LC across various public datasets using three latest LLMs. Results reveal that when resourced sufficiently, LC consistently outperforms RAG in terms of average performance. However, RAG's significantly lower cost remains a distinct advantage. Based on this observation, we propose Self-Route, a simple…

  4. Very close
    Searching for Best Practices in Retrieval-Augmented Generation
    Xiaohua Wang, Zhenghua Wang, Xuan Gao et al. · 2024 · Computation and Language · cited 169 times · AI summary available
    Abstract

    Retrieval-augmented generation (RAG) techniques have proven to be effective in integrating up-to-date information, mitigating hallucinations, and enhancing response quality, particularly in specialized domains. While many RAG approaches have been proposed to enhance large language models through query-dependent retrievals, these approaches still suffer from their complex implementation and prolonged response times. Typically, a RAG workflow involves multiple processing steps, each of which can be executed in various ways. Here, we investigate existing RAG approaches and their potential combinations to identify optimal RAG practices. Through extensive experiments, we suggest several strategie…

  5. Very close
    A Survey on RAG with LLMs
    Muhammad Arslan, Hussam Ghanem, Saba Munawar et al. · 2024 · Procedia Computer Science · cited 271 times · Not summarized yet
    Abstract

    In the fast-paced realm of digital transformation, businesses are increasingly pressured to innovate and boost efficiency to remain competitive and foster growth. Large Language Models (LLMs) have emerged as game-changers across industries, revolutionizing various sectors by harnessing extensive text data to analyze and generate human-like text. Despite their impressive capabilities, LLMs often encounter challenges when dealing with domain-specific queries, potentially leading to inaccuracies in their outputs. In response, Retrieval-Augmented Generation (RAG) has emerged as a viable solution. By seamlessly integrating external data retrieval into text generation processes, RAG aims to enhanc…

How are these papers found?

We compare the title and abstract of this paper with those of every paper summarized on this site, and with the papers Semantic Scholar recommends, those it cites and those citing it (for a much-cited paper, its most recent citations and, from OpenAlex, the most cited ones). Among the prior work and the follow-ups, the papers that use each other in depth, a method it uses and the much-cited follow-ups come a little higher. The levels (very close, close, related) come from the similarity of the texts, not from a judgment of quality; * marks a paper without an abstract, compared by its title. The sentence under a paper is written by an AI from the two abstracts: check it in the papers. A paper marked not relevant by three readers leaves the list.

Updated on 4 November 2026.

The illustrated guide to the papers around a paper

The previous summary was created more than a year ago and can be re-run (if necessary) by clicking on the Run button below.

Disclaimer: The AI-based summarization tool and virtual assistant provided on this website may not always provide accurate and complete summaries or responses. We encourage you to carefully review and evaluate the generated content to ensure its quality and relevance to your needs.