Résumé IA · 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
Article original Soumis à arXiv le 17 Oct. 2023 30 pages, 2 figures, 12 tables Licence : CC BY 4.0 Aussi en : en

Comment lire ce résumé ? Guide illustré

Pour aller plus loin

  • Résumé Complet
  • Résumé vulgarisé
  • Article de blog
  • Abstract original
Le résumé n'est pas encore prêt

Cette synthèse vous a-t-elle été utile ?

Note : 0

Pourquoi avons-nous besoin de votes ?

Les votes sont utilisés pour déterminer si nous devons réexécuter nos outils de synthèse. Si le compte atteint -10, nos outils peuvent être redémarrés.

Figures et graphiques

Posez une question sur une figure en indiquant son numéro ou en utilisant son bouton de question pour demander une analyse visuelle. Au maximum deux figures et quatre panneaux par question. Les valeurs lues sur les graphiques sont approximatives ; vérifiez les données originales.

Instructions pour utiliser l'assistant IA ?

Outils pour cet article

Expliquer autrement 1 réécriture gratuite restante aujourd'hui
Enregistrer dans une collection Regroupez des articles en collections pour les comparer, les interroger et les exporter. Continuer avec Google Créer un compte gratuit Se connecter

Outils avancés Premium

Pour suivre un domaine de près : alertes de citations, diapositives de journal club, comparaison des versions et envoi vers Zotero. Découvrir Premium

Zotero Guide Zotero
Alertes de citation 299 articles le citent déjà : recevez chaque nouveau par email. Guide des alertes de citations
Qui travaille dessus ?

Parmi les 31 articles autour de celui-ci, le nom qui revient le plus : Ori Ram (2 articles)

Continuer avec Google Créez un compte gratuit : votre première carte est offerte
Lettre hebdomadaire La dernière lettre de son domaine, « Intelligence artificielle cette semaine » du 16 novembre 2026 : Intelligence artificielle cette semaine : ce que les bons scores ne disent pas · En recevoir une par email gratuitement

Les articles autour de celui-ci

Les voir sur une carte

Classés selon la proximité de leur titre et de leur résumé avec ceux de cet article. Sélectionnez-en pour les lire ensemble.

Les articles les plus proches

  1. Très proche
    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 · cité 25 fois · Résumé IA disponible
    Résumé scientifique

    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. Très proche
    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 · cité 57 fois · Résumé IA disponible
    Résumé scientifique

    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. Très proche
    Corrective Retrieval Augmented Generation
    Shi-Qi Yan, Jia-Chen Gu, Yun Zhu et al. · 2024 · Computation and Language · preprint, non relu par les pairs · cité 349 fois · Résumé IA disponible
    Résumé scientifique

    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. Très proche
    Retrieval-Augmented Generation for Large Language Models: A Survey
    Yunfan Gao, Yun Xiong, Xinyu Gao et al. · 2023 · Computation and Language · preprint, non relu par les pairs · cité 4 438 fois · Résumé IA disponible
    Résumé scientifique

    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. Très proche
    Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting
    Zilong Wang, Zifeng Wang, Long T. Le et al. · 2024 · International Conference on Learning Representations · cité 125 fois · Pas encore résumé
    Résumé scientifique

    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. Très proche
    SKILL-RAG: Self-Knowledge Induced Learning and Filtering for Retrieval-Augmented Generation
    Tomoaki Isoda · 2025 · arXiv.org · preprint, non relu par les pairs · Pas encore résumé
    Résumé scientifique

    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. Très proche
    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 · cité 90 fois · Résumé IA disponible
    Résumé scientifique

    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. Très proche
    Bidirectional RAG: Safe Self-Improving Retrieval-Augmented Generation Through Multi-Stage Validation
    Teja Chinthala · 2025 · arXiv.org · preprint, non relu par les pairs · cité 1 fois · Pas encore résumé
    Résumé scientifique

    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…

Les travaux antérieurs sur lesquels il s’appuie

  1. Très proche Une méthode qu’il utilise
    Active Retrieval Augmented Generation
    Zhengbao Jiang, Frank F. Xu, Luyu Gao et al. · 2023 · Computation and Language · cité 961 fois · Résumé IA disponible
    Résumé scientifique

    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. Proche Une méthode qu’il utilise
    In-Context Retrieval-Augmented Language Models
    Ori Ram, Yoav Levine, Itay Dalmedigos et al. · 2023 · Transactions of the Association for Computational Linguistics · cité 1 192 fois · Résumé IA disponible
    Résumé scientifique

    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. Proche Utilisé en profondeur par cet article Une méthode qu’il utilise
    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 · cité 947 fois · Résumé IA disponible
    Résumé scientifique

    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. Proche
    Making Retrieval-Augmented Language Models Robust to Irrelevant Context
    Ori Yoran, Tomer Wolfson, Ori Ram et al. · 2023 · International Conference on Learning Representations · cité 533 fois · Résumé IA disponible
    Résumé scientifique

    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. Proche Une méthode qu’il utilise
    Self-Refine: Iterative Refinement with Self-Feedback
    Aman Madaan, Niket Tandon, Prakhar Gupta et al. · 2023 · Neural Information Processing Systems · cité 5 475 fois · Résumé IA disponible
    Résumé scientifique

    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…

Les articles qui le citent

  1. Très proche Utilise cet article en profondeur
    Characterising and Analysing Retrieval-Augmented Generation Techniques
    E. Igbekele, O. Daramola · 2026 · Pas encore résumé
    Résumé scientifique

    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. Très proche
    The Power of Noise: Redefining Retrieval for RAG Systems
    Florin Cuconasu, Giovanni Trappolini, Federico Siciliano et al. · 2024 · Information Retrieval · cité 278 fois · Résumé IA disponible
    Résumé scientifique

    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. Très proche
    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 · cité 71 fois · Résumé IA disponible
    Résumé scientifique

    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. Très proche
    Searching for Best Practices in Retrieval-Augmented Generation
    Xiaohua Wang, Zhenghua Wang, Xuan Gao et al. · 2024 · Computation and Language · cité 169 fois · Résumé IA disponible
    Résumé scientifique

    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. Très proche
    A Survey on RAG with LLMs
    Muhammad Arslan, Hussam Ghanem, Saba Munawar et al. · 2024 · Procedia Computer Science · cité 271 fois · Pas encore résumé
    Résumé scientifique

    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…

Comment ces articles sont-ils trouvés ?

Nous comparons le titre et le résumé de cet article avec ceux de tous les articles résumés sur ce site, et avec les articles que Semantic Scholar recommande, ceux qu’il cite et ceux qui le citent (pour un article très cité, ses citations les plus récentes et, depuis OpenAlex, les plus citées). Parmi les travaux antérieurs et les suites, les articles qui s’utilisent en profondeur, une méthode qu’il utilise et les suites très citées remontent un peu. Les niveaux (très proche, proche, apparenté) viennent de la similarité des textes, pas d’un jugement de qualité ; * signale un article sans résumé, comparé par son titre. La phrase sous un article est écrite par une IA à partir des deux résumés : vérifiez-la dans les articles. Un article jugé hors sujet par trois lecteurs quitte la liste.

Mis à jour le 4 novembre 2026.

Le guide illustré des articles autour d’un article

Le résumé précédent a été créé il y a plus d'un an et peut être réexécuté (si nécessaire) en cliquant sur le bouton Exécuter ci-dessous.

Avertissement : Notre outil de synthèse basé sur l'IA et l'assistant virtuel fournis sur ce site Web peuvent ne pas toujours fournir des résumés complets ou des réponses exactes. Nous vous encourageons à examiner attentivement et à évaluer le contenu généré pour vous assurer de sa qualité et de sa pertinence par rapport à vos besoins.