Recherche partagée · Trouver qui travaille sur votre propre sujet
RAG contre les hallucinations
Comment lire cette carte et vérifier ses sources ? Guide illustré
D'après 117 articles sur ce sujet publiés depuis 2021, retenus parmi les 380 résultats les plus pertinents de nos recherches sur OpenAlex. 2 prépublications comptées une fois avec leurs versions publiées. La pertinence n'a été vérifiée que pour les 120 articles les plus proches.
C'est un échantillon du domaine, pas un recensement : un sujet large compte bien plus d'articles qu'une carte n'en lit. Resserrez le sujet ou modifiez les recherches pour bien en cartographier une partie.
Les 4 recherches lancées sur OpenAlex · Une vue d'ensemble du domaine
- retrieval-augmented generation hallucinations
- grounded language generation factuality
- knowledge retrieval large language models
- RAG hallucination mitigation evaluation
Le paysage
Le premier ensemble privilégie les synthèses et les améliorations explicitement orientées vers la réduction des hallucinations, tandis que le deuxième aborde plus largement l’intégration des connaissances, leur spécialisation et leur robustesse face aux sources imparfaites. Le troisième se concentre davantage sur la manière de construire et d’exploiter le contexte récupéré, alors que le quatrième rassemble des méthodes ciblant la confiance, les frontières du contexte et la mémoire dynamique. Ces ensembles se recoupent autour de l’ancrage dans des preuves externes, tout en distinguant la qualité des sources, la préparation du contexte et la fidélité de la génération, car la récupération seule ne garantit pas l’exactitude.
Personnes
Classées selon les articles de la carte qu'elles signent, en comptant davantage ceux qu'elles signent en premier, en dernier ou comme auteur correspondant. L'ordre des auteurs dit qui a fait quoi dans beaucoup de domaines, pas qui dirige une équipe ; il n'est pas utilisé dans les listes d'auteurs alphabétiques, ni après les quinze premiers auteurs d'une grande collaboration.
-
Association for Computational Linguistics 2026
Synthèses et optimisation anti-hallucinations · 3
Ses articles sur le sujet
- HalluGuard: Evidence-Grounded Small Reasoning Models to Mitigate Hallucinations in Retrieval-Augmented Generation
- Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation
- Evidence-Aligned Entity Verification for Hallucination Detection in Retrieval-Augmented Generation
-
Abdulla Mohammed Alshehhi
Synthèses et optimisation anti-hallucinations · 1
-
Akshay Mittal
Synthèses et optimisation anti-hallucinations · 1
-
Akshitha Katkeri
Synthèses et optimisation anti-hallucinations · 1
Ses articles sur le sujet
-
Ali Z. K. Matloob
Construction du contexte et fidélité · 1
-
Amjad Hawash
Synthèses et optimisation anti-hallucinations · 1
-
Anson Li
Synthèses et optimisation anti-hallucinations · 1
-
Anwar Saif
Synthèses et optimisation anti-hallucinations · 1
Ses articles sur le sujet
-
Arif Mohamed Khan Rabi Ahamad
Confiance et adaptation du contexte · 1
Ses articles sur le sujet
-
Arunkumar Balakrishnan
Synthèses et optimisation anti-hallucinations · 1
-
Aske Plaat
Synthèses et optimisation anti-hallucinations · 1
Ses articles sur le sujet
-
Association for Artificial Intelligence 2026
Synthèses et optimisation anti-hallucinations · 1
-
AUNG KO KO OO
Synthèses et optimisation anti-hallucinations · 1
Ses articles sur le sujet
-
Balakrishna Sreeram
Intégration et robustesse des connaissances · 1
-
Bankar Akshada Santosh
Synthèses et optimisation anti-hallucinations · 1
-
Ben Malin
Synthèses et optimisation anti-hallucinations · 1
Ses articles sur le sujet
-
Berlilana Berlilana
Intégration et robustesse des connaissances · 1
-
Bijoy Bhadra
Construction du contexte et fidélité · 1
-
Brian Otieno Odhiambo
Construction du contexte et fidélité · 1
-
Caleb Barns
Synthèses et optimisation anti-hallucinations · 1
-
Ceccarelli C.
Synthèses et optimisation anti-hallucinations · 1
Ses articles sur le sujet
-
Ch. V. S. Satyamurty
Confiance et adaptation du contexte · 1
-
Chandana Sree Mala
Synthèses et optimisation anti-hallucinations · 1
Ses articles sur le sujet
-
Charles Barnabas Rodgers
Synthèses et optimisation anti-hallucinations · 1
-
Cheng Niu
Synthèses et optimisation anti-hallucinations · 1
Ses articles sur le sujet
-
Debashis De
Construction du contexte et fidélité · 1
-
Deeksha Prahlad
Intégration et robustesse des connaissances · 1
Ses articles sur le sujet
-
Diksha Khandelwal
Synthèses et optimisation anti-hallucinations · 1
-
Dipannita Mondal
Synthèses et optimisation anti-hallucinations · 1
Ses articles sur le sujet
-
Donald J. Berndt
Intégration et robustesse des connaissances · 1
Ses articles sur le sujet
Institutions
Ce sont des affiliations de publication, pas des équipes de recherche identifiées. Un organisme national comme le CNRS peut regrouper plusieurs laboratoires indépendants.
Classées selon les articles qu'un de leurs auteurs signe en premier, en dernier ou comme auteur correspondant, puis selon leur part des articles : un article signé par quatre institutions compte un quart pour chacune, si bien qu'une grande collaboration ne fait pas paraître central chacun de ses membres.
-
Manipal Academy of Higher Education · IN
Synthèses et optimisation anti-hallucinations · 1Intégration et robustesse des connaissances · 1
Signent ici en premier, en dernier ou comme auteur correspondant : Arunkumar Balakrishnan (1), Priyodip Sanyal (1), R. Vijaya Arjunan (1)
-
Tsinghua University · CN
Synthèses et optimisation anti-hallucinations · 1Intégration et robustesse des connaissances · 1
Signent ici en premier, en dernier ou comme auteur correspondant : Yifan Feng (1), Yile Wang (1), Yue Gao (1)
Articles correspondants avec cette affiliation
-
University of Technology Sydney · AU
Synthèses et optimisation anti-hallucinations · 2
Signent ici en premier, en dernier ou comme auteur correspondant : Runsong Jia (1), Yi Zhang (1)
-
Zhejiang University of Technology · CN
Synthèses et optimisation anti-hallucinations · 1Intégration et robustesse des connaissances · 1
Signent ici en premier, en dernier ou comme auteur correspondant : Jianling Lu (1), Mingqi Lv (1)
Articles correspondants avec cette affiliation
-
Chinese Academy of Sciences · CN
Synthèses et optimisation anti-hallucinations · 3Construction du contexte et fidélité · 1
Signent ici en premier, en dernier ou comme auteur correspondant : Fangfang Yuan (1), Junqian Zhao (1), Yanbing Liu (1)
Articles correspondants avec cette affiliation
- TSS-RAG: Leveraging Teacher-Student Classroom Scenarios to Mitigate Hallucinations in Retrieval-Augmented Generation
- Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation
- Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation
- Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMs
-
Google (United States) · US
Intégration et robustesse des connaissances · 1Synthèses et optimisation anti-hallucinations · 1
Signent ici en premier, en dernier ou comme auteur correspondant : Lucas Dixon (1), Tyler A. Chang (1)
-
Tongji University · CN
Intégration et robustesse des connaissances · 1Synthèses et optimisation anti-hallucinations · 1
Signent ici en premier, en dernier ou comme auteur correspondant : Yunfan Gao (1)
Articles correspondants avec cette affiliation
-
Abu Dhabi University · AE
Synthèses et optimisation anti-hallucinations · 1
Signent ici en premier, en dernier ou comme auteur correspondant : Abdulla Mohammed Alshehhi (1), Khiati Abdel Ilah Zakaria (1)
Articles correspondants avec cette affiliation
-
Amity University · IN
Synthèses et optimisation anti-hallucinations · 1
Signent ici en premier, en dernier ou comme auteur correspondant : Diksha Khandelwal (1), Subhash Chand Gupta (1)
Articles correspondants avec cette affiliation
-
Amrita Vishwa Vidyapeetham · IN
Synthèses et optimisation anti-hallucinations · 1
Signent ici en premier, en dernier ou comme auteur correspondant : Jasmin T J (1), Savitha Gopal (1)
Articles correspondants avec cette affiliation
-
An-Najah National University · PS
Synthèses et optimisation anti-hallucinations · 1
Signent ici en premier, en dernier ou comme auteur correspondant : Amjad Hawash (1), Razi Alsayyed (1)
Articles correspondants avec cette affiliation
-
Arizona State University · US
Intégration et robustesse des connaissances · 1
Signent ici en premier, en dernier ou comme auteur correspondant : Deeksha Prahlad (1), Hokeun Kim (1)
Articles correspondants avec cette affiliation
-
Bangladesh University of Engineering and Technology · BD
Construction du contexte et fidélité · 1
Signent ici en premier, en dernier ou comme auteur correspondant : Salman Rakin (1)
Articles correspondants avec cette affiliation
-
Boston University · US
Synthèses et optimisation anti-hallucinations · 1
Signent ici en premier, en dernier ou comme auteur correspondant : Ramya Krishna Kurra (1)
Articles correspondants avec cette affiliation
-
Brunel University of London · GB
Synthèses et optimisation anti-hallucinations · 1
Signent ici en premier, en dernier ou comme auteur correspondant : Ben Malin (1), Nikolaos V. Boulgouris (1)
Articles correspondants avec cette affiliation
Approches
Les articles sont regroupés selon la similarité de leurs titres et résumés ; une IA nomme chaque groupe à partir de ses articles. Un article n'est que dans un groupe.
-
Synthèses et optimisation anti-hallucinations
Ces travaux passent en revue les mécanismes, les limites et l’évaluation du RAG contre les hallucinations, et étudient des améliorations fondées sur la recherche hybride, les graphes de connaissances et des cadres de détection ou d’atténuation ancrés dans des preuves externes.
Personnes : Association for Computational Linguistics 2026, Abdulla Mohammed Alshehhi, Akshay Mittal, Akshitha Katkeri, Amjad Hawash, Anson Li
Institutions : Chinese Academy of Sciences, University of Technology Sydney, Manipal Academy of Higher Education, Tsinghua University, Zhejiang University of Technology
Ses articles
- Improving the Reliability of Large Language Models: A Hypothesis-Driven Statistical Evaluation of Hallucination Detection and Mitigation Techniques
- Mitigating Hallucinations in Large Language Models Using Retrieval-Augmented Generation and Knowledge Graphs: A Review
- Retrieval-Augmented Generation as an Epistemic Architecture: A Theoretical Account of Grounding, Provenance and Hallucination Reduction
- Reducing Hallucinations in Large Language Models Using Retrieval-Augmented Generation (RAG)
- Research on Factual Hallucination Detection and Mitigation in Large Language Models Based on Retrieval-Augmented Generation
- A Systematic Review of Hallucination Mitigation in Large Language Models Using Retrieval-Augmented Generation
- A Systematic Review of Hallucination Mitigation in Large Language Models Using Retrieval-Augmented Generation
- Hybrid retrieval-augmented generation for hallucination mitigation in domain-specific educational question-answering systems
- Why Retrieval Doesn't Cure Everything: A Review of Hallucination in Retrieval-Augmented Generation
- A Systematic Review of Retrieval-Augmented Generation Techniques for Mitigating Hallucinations in Chatbot Systems
- Detecting and Repairing Hallucinations in Retrieval-Augmented Generation
- Adaptive Hierarchical Confidence Estimation for Claim-Level Hallucination Detection in Retrieval-Augmented Generation Systems
- Retrieval-Augmented Generation for Reducing Hallucinations in Drug-Related Question Answering Systems
- Quantum-Enhanced Retrieval-Augmented Generation for Hallucination Reduction in Large Language Models
- A Review of Hallucination Suppression Technologies for Large Language Models Under RAG Architecture
- Numerical Hallucinations in Retrieval-Augmented Generation: Detection and Analysis
- A Hybrid Framework for Hallucination Detection & Mitigation in Large Language Models
- Hallucination Reduction in Retrieval-Augmented Generation (RAG)
- CnHallu-RAG: Detecting and Mitigating Hallucinations in Chinese Retrieval-Augmented Generation for High-Risk Domains
- Evidence Graph Consistency in Retrieval-Augmented Generation: A Model-Dependent Analysis of Hallucination Detection
- Building a Reliable Retrieval-Augmented Generation (RAG) System with Hallucination Awareness
- Mitigating Hallucinations in Large Language Models for Burmese Domain-Specific Question Answering
- SentHalu: A Lightweight Sentence-Level Detector for Hallucination Screening in Retrieval-Augmented Generation
- HalluGuard: Evidence-Grounded Small Reasoning Models to Mitigate Hallucinations in Retrieval-Augmented Generation
- Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation
- Evidence-Aligned Entity Verification for Hallucination Detection in Retrieval-Augmented Generation
- Hallucination in Large Language Models and Retrieval-Augmented Generation: Mechanisms, Mitigation, and Evaluation
- Reducing Hallucinations in Oncology Question Answering Using Confidence-Gated Retrieval-Augmented Generation
- AMulti-Stage Hallucination Mitigation Framework for Reliable Retrieval-Augmented Generation Systems
- Composition Hallucination in Retrieval-Augmented Generation: A Failure Mode and Benchmark Protocol
- A Retrieval-Augmented Generation (RAG) Approach to Eliminate Hallucinations in Workflow Generation
- Retrieval-Augmented Large Language Models for Clinical Decision Support: A Systematic Review of Hallucination Mitigation and Evidence Grounding
- Reducing Hallucinations in Multi-Hop Question Answering Using Wikidata-Based Retrieval-Augmented Generation
- Benchmarking Hallucination Mitigation Techniques in Large Language Models: A Comparative Study
- Real-time Prevention of Factual Hallucinations in Retrieval-Augmented Generation
- Hyper-RAG: combating LLM hallucinations using hypergraph-driven retrieval-augmented generation
- An Intelligent Biomedical Retrieval Pipeline for Reducing Hallucination Risk in Retrieval Augmented Generation
- AI Hallucinations in Retrieval-Augmented and Generative Systems: A Rigorous Review of Definitions, Failure Mechanisms, Evaluation, and Mitigation Strategies
- Hallucination in Large Language Models: A Comprehensive Survey, Taxonomy, and Mitigation Strategies
- Enhancing Factual Reliability in Large Language Models Through Retrieval Augmented Generation
- A SYSTEMATIC REVIEW OF OPTIMIZED RETRIEVAL-AUGMENTED GENERATION FRAMEWORKS FOR REDUCING HALLUCINATIONS IN LARGE LANGUAGE MODELS
- Empirical Analysis of Confidence and Semantic Fidelity in Retrieval-Augmented Generation: Understanding Hallucination Patterns Across Domains
- Retrieval-Augmented Generation (RAG) vs. Fine-Tuning: A Systematic Review of Hallucination Mitigation in Medical LLMs
- Hallucination-aware Retrieval Augmented Generation with Evidence-based Semantic Clustering
- CREAM-RAG: Enhanced Retrieval Augmented Generation to Limit Hallucination through Consistency-based Self-RAG
- Mitigating Hallucinations In Large Language Models Using Retrieval-Augmented Generation And Knowledge Graphs: A Review
- HalluGuard: Evidence-Grounded Small Reasoning Models to Mitigate Hallucinations in Retrieval-Augmented Generation
- Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation
- Reducing Hallucinations in Legal AI: A Retrieval Augmented Generation-Based Model for Accurate Legal Guidance
- Detecting Hallucinations in Retrieval-Augmented Generation via Semantic-level Internal Reasoning Graph
- Reward-driven hallucination control in retrieval-augmented generation via bandit learning
- Evidence-Aligned Entity Verification for Hallucination Detection in Retrieval-Augmented Generation
- Scalable Retrieval-Augmented Generation for Technical Documents with Hallucination Risk Control
- Mitigating Artificial Intelligence Hallucinations in Education: A Comparative Study of Retrieval-Augmented Generation (RAG) and Large Language Models
- Detecting Hallucinations in Graph Retrieval-Augmented Generation via Attention Patterns and Semantic Alignment
- Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMs
- A Unified Framework for Mitigating Hallucinations in Large Language Models: Integrating Internal and External Validation Strategies
- MEGA-RAG: a retrieval-augmented generation framework with multi-evidence guided answer refinement for mitigating hallucinations of LLMs in public health
- Hallucination Detection in Retrieval-Augmented Generation Systems via Self-Consistency Scoring—A Reference-Free, Retrieval-Aware Detection Framework
- Reducing Hallucinations in Large Language Models Through Integrated Self-Verification and Retrieval-Augmented Generation
- MALM: A Multi-Information Adapter for Large Language Models to Mitigate Hallucination
- A Review of Faithfulness Metrics for Hallucination Assessment in Large Language Models
- A comparative review of hallucination mitigation and performance improvement techniques in Small Language Models
- Hallucinations and Bias in Clinical AI: Retrieval-Augmented Generation as a Mitigation Strategy (Preprint)
- Retrieval-Augmented Generation and Hallucination in Large Language Models: A Scholarly Overview
- MultiRAG: A Knowledge-Guided Framework for Mitigating Hallucination in Multi-Source Retrieval Augmented Generation
- Finetune-RAG: Fine-Tuning Language Models to Resist Hallucination in Retrieval-Augmented Generation
- Hybrid Retrieval for Hallucination Mitigation in Large Language Models: A Comparative Analysis
- Bi'an: A Bilingual Benchmark and Model for Hallucination Detection in Retrieval-Augmented Generation
- FilterRAG: Zero-Shot Informed Retrieval-Augmented Generation to Mitigate Hallucinations in VQA
- Mitigating Hallucinations in Large Language Models via Retrieval-Augmented Generation (RAG)
- Knowledge-Grounded Detection of Factual Hallucinations in Large Language Models
- Enhancing Large Language Model Reliability: Minimizing Hallucinations with Dual Retrieval-Augmented Generation Based on the Latest Diabetes Guidelines
- ReRag: A New Architecture for Reducing the Hallucination by Retrieval- Augmented Generation
- ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability
- Mitigating Hallucinations in Large Language Models: A Comparative Study of RAG-enhanced vs. Human-Generated Medical Templates
- A Self-Reflective Retrieval Augmented Generation System to Eliminate Hallucination in LLM Generation
- Hallucination Reduction in Large Language Models with Retrieval-Augmented Generation Using Wikipedia Knowledge
- Mitigating Hallucinations in Large Language Models via Self-Refinement-Enhanced Knowledge Retrieval
- Detecting Hallucination and Coverage Errors in Retrieval Augmented Generation for Controversial Topics
- A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models
- Two-tiered Encoder-based Hallucination Detection for Retrieval-Augmented Generation in the Wild
- RAG-HAT: A Hallucination-Aware Tuning Pipeline for LLM in Retrieval-Augmented Generation
- Minimizing Factual Inconsistency and Hallucination in Large Language Models
-
Intégration et robustesse des connaissances
Ces articles examinent les architectures et le déploiement du RAG pour intégrer des connaissances actualisées, spécialisées ou personnalisées, ainsi que les difficultés liées aux conflits de connaissances, à la récupération imparfaite et à la corruption des sources.
Personnes : Balakrishna Sreeram, Berlilana Berlilana, Deeksha Prahlad, Donald J. Berndt
Institutions : Manipal Academy of Higher Education, Tsinghua University, Zhejiang University of Technology, Google (United States), Tongji University
Ses articles
- Multimodal retrieval-augmented generation for domain knowledge enhancement in large language models
- Retrieval-Augmented Generation: Architecting Trustworthy Knowledge Systems on Top of Large Language Models
- RAGMail: a cloud-based retrieval-augmented framework for reducing hallucinations in LLM text generation
- Retrieval-Augmented Generation for Large Language Models: Dense Retrieval, Knowledge Integration, and RAG Architectures
- Retrieval-Augmented Generation and Knowledge-Grounded Large Language Models
- A retrieval augmented generation based optimization approach for medical knowledge understanding and reasoning in large language models
- CCSK: Cognitive Convection of Self-Knowledge Based Retrieval Augmentation for Large Language Models
- A Systematic Review of Retrieval-Augmented Generation for Enhancing Domain-Specific Knowledge in Large Language Models
- Personalizing Large Language Models using Retrieval Augmented Generation and Knowledge Graph
- OG-RAG: Ontology-grounded retrieval-augmented generation for large language models
- Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models
- Deploying Large Language Models With Retrieval Augmented Generation
- Enhancing Spectral Knowledge Interrogation: A Reliable Retrieval-Augmented Generative Framework on Large Language Models
- PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models
- Retrieval-Augmented Generation: Enhancing Reliability in Large Language Models
- Retrieval-Augmented Generation for Large Language Models: A Survey
- Self-Knowledge Guided Retrieval Augmentation for Large Language Models
-
Construction du contexte et fidélité
Ces travaux explorent la construction du contexte documentaire, l’utilisation des preuves par l’attention, la détection des hallucinations et les stratégies de réponse ou d’évaluation, notamment pour des questions spécialisées et des sorties structurées.
Personnes : Ali Z. K. Matloob, Bijoy Bhadra, Brian Otieno Odhiambo, Debashis De
Institutions : Chinese Academy of Sciences, Bangladesh University of Engineering and Technology
Ses articles
- Hallucination Risk in Retrieval-Augmented Generation: A Probabilistic Model of Retrieval Recall, Context Length and Answer Faithfulness
- Supplementary material for: Comparing Retrieval-Augmented Generation Configurations under Noisy Retrieval: A Taxonomic Review of Hallucination Behaviour
- TSS-RAG: Leveraging Teacher-Student Classroom Scenarios to Mitigate Hallucinations in Retrieval-Augmented Generation
- Hallucination in Retrieval-Augmented Generation is a Context Construction Problem: A Constraint-Driven Cross-Modal Framework
- When Attention Escapes: Diagnosing and Mitigating Hallucination in Retrieval-Augmented Generation
- Evaluating hallucination Mitigation in Retrieval-Augmented Generation Systems through Guarded Response Strategies, Embedding Comparison, and Retrieval Depth Analysis
- An Answerability-Aware Retrieval-Augmented Generation Framework for Hallucination Reduction in Technical Documentation
- Attention Mapping for Hallucination Reduction in Arabic Financial Using Retrieval-Augmented Generation Systems
- Leveraging the Domain Adaptation of Retrieval Augmented Generation Models for Question Answering and for Hallucination Reduction
- Taming AI Hallucinations: Innovations in Retrieval-Augmented Generation and Evaluation
- Lrp4rag: Detecting Hallucinations in Retrieval-Augmented Generation Via Layer-Wise Relevance Propagation
- Reducing LLM Hallucinations in Product Q&A Systems: A Retrieval-Augmented Generation Approach
- Reducing hallucination in structured outputs via Retrieval-Augmented Generation
-
Confiance et adaptation du contexte
D’après leurs titres, ces articles proposent une estimation hybride légère de la confiance, un lissage des frontières du contexte sémantique guidé par densité à noyau et une mémoire dynamique avec prédiction des hallucinations fondée sur l’entropie.
Personnes : Arif Mohamed Khan Rabi Ahamad, Ch. V. S. Satyamurty
Ses articles
- Kernel Density Guided Semantic Context Boundary Smoothing for Hallucination-Aware Retrieval-Augmented Generation
- Lightweight Hybrid Confidence Estimation for Hallucination Detection in Retrieval-Augmented Generation Systems
- DynamiRAG: Dynamic Memory Retrieval-Augmented Generation with Entropy-Aware Hallucination Prediction
Articles
- Multimodal retrieval-augmented generation for domain knowledge enhancement in large language models
- Improving the Reliability of Large Language Models: A Hypothesis-Driven Statistical Evaluation of Hallucination Detection and Mitigation Techniques
- Mitigating Hallucinations in Large Language Models Using Retrieval-Augmented Generation and Knowledge Graphs: A Review
- Hallucination Risk in Retrieval-Augmented Generation: A Probabilistic Model of Retrieval Recall, Context Length and Answer Faithfulness
- Retrieval-Augmented Generation as an Epistemic Architecture: A Theoretical Account of Grounding, Provenance and Hallucination Reduction
- Reducing Hallucinations in Large Language Models Using Retrieval-Augmented Generation (RAG)
- Research on Factual Hallucination Detection and Mitigation in Large Language Models Based on Retrieval-Augmented Generation
- A Systematic Review of Hallucination Mitigation in Large Language Models Using Retrieval-Augmented Generation
- A Systematic Review of Hallucination Mitigation in Large Language Models Using Retrieval-Augmented Generation
- Kernel Density Guided Semantic Context Boundary Smoothing for Hallucination-Aware Retrieval-Augmented Generation
- Hybrid retrieval-augmented generation for hallucination mitigation in domain-specific educational question-answering systems
- Why Retrieval Doesn't Cure Everything: A Review of Hallucination in Retrieval-Augmented Generation
- Supplementary material for: Comparing Retrieval-Augmented Generation Configurations under Noisy Retrieval: A Taxonomic Review of Hallucination Behaviour
- A Systematic Review of Retrieval-Augmented Generation Techniques for Mitigating Hallucinations in Chatbot Systems
- Detecting and Repairing Hallucinations in Retrieval-Augmented Generation
- Adaptive Hierarchical Confidence Estimation for Claim-Level Hallucination Detection in Retrieval-Augmented Generation Systems
- Retrieval-Augmented Generation: Architecting Trustworthy Knowledge Systems on Top of Large Language Models
- Retrieval-Augmented Generation for Reducing Hallucinations in Drug-Related Question Answering Systems
- Quantum-Enhanced Retrieval-Augmented Generation for Hallucination Reduction in Large Language Models
- A Review of Hallucination Suppression Technologies for Large Language Models Under RAG Architecture
- Numerical Hallucinations in Retrieval-Augmented Generation: Detection and Analysis
- TSS-RAG: Leveraging Teacher-Student Classroom Scenarios to Mitigate Hallucinations in Retrieval-Augmented Generation
- A Hybrid Framework for Hallucination Detection & Mitigation in Large Language Models
- Hallucination Reduction in Retrieval-Augmented Generation (RAG)
- CnHallu-RAG: Detecting and Mitigating Hallucinations in Chinese Retrieval-Augmented Generation for High-Risk Domains
- Evidence Graph Consistency in Retrieval-Augmented Generation: A Model-Dependent Analysis of Hallucination Detection
- Building a Reliable Retrieval-Augmented Generation (RAG) System with Hallucination Awareness
- Mitigating Hallucinations in Large Language Models for Burmese Domain-Specific Question Answering
- Hallucination in Retrieval-Augmented Generation is a Context Construction Problem: A Constraint-Driven Cross-Modal Framework
- SentHalu: A Lightweight Sentence-Level Detector for Hallucination Screening in Retrieval-Augmented Generation
- Lightweight Hybrid Confidence Estimation for Hallucination Detection in Retrieval-Augmented Generation Systems
- HalluGuard: Evidence-Grounded Small Reasoning Models to Mitigate Hallucinations in Retrieval-Augmented Generation
- Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation
- Evidence-Aligned Entity Verification for Hallucination Detection in Retrieval-Augmented Generation
- Hallucination in Large Language Models and Retrieval-Augmented Generation: Mechanisms, Mitigation, and Evaluation
- Reducing Hallucinations in Oncology Question Answering Using Confidence-Gated Retrieval-Augmented Generation
- AMulti-Stage Hallucination Mitigation Framework for Reliable Retrieval-Augmented Generation Systems
- Composition Hallucination in Retrieval-Augmented Generation: A Failure Mode and Benchmark Protocol
- A Retrieval-Augmented Generation (RAG) Approach to Eliminate Hallucinations in Workflow Generation
- Retrieval-Augmented Large Language Models for Clinical Decision Support: A Systematic Review of Hallucination Mitigation and Evidence Grounding
- Reducing Hallucinations in Multi-Hop Question Answering Using Wikidata-Based Retrieval-Augmented Generation
- Benchmarking Hallucination Mitigation Techniques in Large Language Models: A Comparative Study
- Real-time Prevention of Factual Hallucinations in Retrieval-Augmented Generation
- Hyper-RAG: combating LLM hallucinations using hypergraph-driven retrieval-augmented generation
- An Intelligent Biomedical Retrieval Pipeline for Reducing Hallucination Risk in Retrieval Augmented Generation
- AI Hallucinations in Retrieval-Augmented and Generative Systems: A Rigorous Review of Definitions, Failure Mechanisms, Evaluation, and Mitigation Strategies
- Hallucination in Large Language Models: A Comprehensive Survey, Taxonomy, and Mitigation Strategies
- Enhancing Factual Reliability in Large Language Models Through Retrieval Augmented Generation
- A SYSTEMATIC REVIEW OF OPTIMIZED RETRIEVAL-AUGMENTED GENERATION FRAMEWORKS FOR REDUCING HALLUCINATIONS IN LARGE LANGUAGE MODELS
- RAGMail: a cloud-based retrieval-augmented framework for reducing hallucinations in LLM text generation
- Empirical Analysis of Confidence and Semantic Fidelity in Retrieval-Augmented Generation: Understanding Hallucination Patterns Across Domains
- Retrieval-Augmented Generation (RAG) vs. Fine-Tuning: A Systematic Review of Hallucination Mitigation in Medical LLMs
- Hallucination-aware Retrieval Augmented Generation with Evidence-based Semantic Clustering
- CREAM-RAG: Enhanced Retrieval Augmented Generation to Limit Hallucination through Consistency-based Self-RAG
- Retrieval-Augmented Generation for Large Language Models: Dense Retrieval, Knowledge Integration, and RAG Architectures
- Mitigating Hallucinations In Large Language Models Using Retrieval-Augmented Generation And Knowledge Graphs: A Review
- Retrieval-Augmented Generation and Knowledge-Grounded Large Language Models
- When Attention Escapes: Diagnosing and Mitigating Hallucination in Retrieval-Augmented Generation
- HalluGuard: Evidence-Grounded Small Reasoning Models to Mitigate Hallucinations in Retrieval-Augmented Generation
- Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation
- Reducing Hallucinations in Legal AI: A Retrieval Augmented Generation-Based Model for Accurate Legal Guidance
- Detecting Hallucinations in Retrieval-Augmented Generation via Semantic-level Internal Reasoning Graph
- Evaluating hallucination Mitigation in Retrieval-Augmented Generation Systems through Guarded Response Strategies, Embedding Comparison, and Retrieval Depth Analysis
- An Answerability-Aware Retrieval-Augmented Generation Framework for Hallucination Reduction in Technical Documentation
- Reward-driven hallucination control in retrieval-augmented generation via bandit learning
- Evidence-Aligned Entity Verification for Hallucination Detection in Retrieval-Augmented Generation
- DynamiRAG: Dynamic Memory Retrieval-Augmented Generation with Entropy-Aware Hallucination Prediction
- Scalable Retrieval-Augmented Generation for Technical Documents with Hallucination Risk Control
- Mitigating Artificial Intelligence Hallucinations in Education: A Comparative Study of Retrieval-Augmented Generation (RAG) and Large Language Models
- Detecting Hallucinations in Graph Retrieval-Augmented Generation via Attention Patterns and Semantic Alignment
- Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMs
- Attention Mapping for Hallucination Reduction in Arabic Financial Using Retrieval-Augmented Generation Systems
- A Unified Framework for Mitigating Hallucinations in Large Language Models: Integrating Internal and External Validation Strategies
- MEGA-RAG: a retrieval-augmented generation framework with multi-evidence guided answer refinement for mitigating hallucinations of LLMs in public health
- Hallucination Detection in Retrieval-Augmented Generation Systems via Self-Consistency Scoring—A Reference-Free, Retrieval-Aware Detection Framework
- A retrieval augmented generation based optimization approach for medical knowledge understanding and reasoning in large language models
- Reducing Hallucinations in Large Language Models Through Integrated Self-Verification and Retrieval-Augmented Generation
- CCSK: Cognitive Convection of Self-Knowledge Based Retrieval Augmentation for Large Language Models
- A Systematic Review of Retrieval-Augmented Generation for Enhancing Domain-Specific Knowledge in Large Language Models
- MALM: A Multi-Information Adapter for Large Language Models to Mitigate Hallucination
- A Review of Faithfulness Metrics for Hallucination Assessment in Large Language Models
- A comparative review of hallucination mitigation and performance improvement techniques in Small Language Models
- Hallucinations and Bias in Clinical AI: Retrieval-Augmented Generation as a Mitigation Strategy (Preprint)
- Retrieval-Augmented Generation and Hallucination in Large Language Models: A Scholarly Overview
- MultiRAG: A Knowledge-Guided Framework for Mitigating Hallucination in Multi-Source Retrieval Augmented Generation
- Finetune-RAG: Fine-Tuning Language Models to Resist Hallucination in Retrieval-Augmented Generation
- Personalizing Large Language Models using Retrieval Augmented Generation and Knowledge Graph
- Leveraging the Domain Adaptation of Retrieval Augmented Generation Models for Question Answering and for Hallucination Reduction
- Hybrid Retrieval for Hallucination Mitigation in Large Language Models: A Comparative Analysis
- Bi'an: A Bilingual Benchmark and Model for Hallucination Detection in Retrieval-Augmented Generation
- FilterRAG: Zero-Shot Informed Retrieval-Augmented Generation to Mitigate Hallucinations in VQA
- Mitigating Hallucinations in Large Language Models via Retrieval-Augmented Generation (RAG)
- Taming AI Hallucinations: Innovations in Retrieval-Augmented Generation and Evaluation
- Lrp4rag: Detecting Hallucinations in Retrieval-Augmented Generation Via Layer-Wise Relevance Propagation
- OG-RAG: Ontology-grounded retrieval-augmented generation for large language models
- Reducing LLM Hallucinations in Product Q&A Systems: A Retrieval-Augmented Generation Approach
- Knowledge-Grounded Detection of Factual Hallucinations in Large Language Models
- Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models
- Enhancing Large Language Model Reliability: Minimizing Hallucinations with Dual Retrieval-Augmented Generation Based on the Latest Diabetes Guidelines
- Deploying Large Language Models With Retrieval Augmented Generation
- ReRag: A New Architecture for Reducing the Hallucination by Retrieval- Augmented Generation
- ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability
- Mitigating Hallucinations in Large Language Models: A Comparative Study of RAG-enhanced vs. Human-Generated Medical Templates
- Enhancing Spectral Knowledge Interrogation: A Reliable Retrieval-Augmented Generative Framework on Large Language Models
- A Self-Reflective Retrieval Augmented Generation System to Eliminate Hallucination in LLM Generation
- Hallucination Reduction in Large Language Models with Retrieval-Augmented Generation Using Wikipedia Knowledge
- Mitigating Hallucinations in Large Language Models via Self-Refinement-Enhanced Knowledge Retrieval
- Detecting Hallucination and Coverage Errors in Retrieval Augmented Generation for Controversial Topics
- PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models
- A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models
- Reducing hallucination in structured outputs via Retrieval-Augmented Generation
- Retrieval-Augmented Generation: Enhancing Reliability in Large Language Models
- Two-tiered Encoder-based Hallucination Detection for Retrieval-Augmented Generation in the Wild
- RAG-HAT: A Hallucination-Aware Tuning Pipeline for LLM in Retrieval-Augmented Generation
- Retrieval-Augmented Generation for Large Language Models: A Survey
- Minimizing Factual Inconsistency and Hallucination in Large Language Models
- Self-Knowledge Guided Retrieval Augmentation for Large Language Models
Utiliser cette carte
Exporter : personnes (CSV) · institutions (CSV) · articles (CSV) · BibTeX · RIS (Zotero, Mendeley, EndNote)
D'après les métadonnées des articles dans OpenAlex, qui peuvent être incomplètes (affiliations, homonymes). Vérifiez avant de contacter qui que ce soit.