mlsanityData to 7 Oct 2026

RHO (ρ): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding

arXiv 2212.01588 ↗First posted 3 Dec 2022cs.CL cs.AIcited by 47

Not on the map. Why?

Abstract (arXiv)

Dialogue systems can leverage large pre-trained language models and knowledge to generate fluent and informative responses. However, these models are still prone to produce hallucinated responses not supported by the input source, which greatly hinders their application. The heterogeneity between external knowledge and dialogue context challenges representation learning and source integration, and further contributes to unfaithfulness. To handle this challenge and generate more faithful responses, this paper presents RHO (ρ) utilizing the representations of linked entities and relation predicates from a knowledge graph (KG). We propose (1) local knowledge grounding to combine textual embeddings with the corresponding KG embeddings; and (2) global knowledge grounding to equip RHO with multi-hop reasoning abilities via the attention mechanism. In addition, we devise a response re-ranking technique based on walks over KG sub-graphs for better conversational reasoning. Experimental results on OpenDialKG show that our approach significantly outperforms state-of-the-art methods on both automatic and human evaluation by a large margin, especially in hallucination reduction (17.54% in FeQA).

Key facts. Cited by 47 papers in the map (data through 7 Oct 2026). Builds on 53 of its 82 references that are in the map. First posted on arXiv 3 Dec 2022.

Builds on

53 of 82 references.

References · 53

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  6. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  7. 2019Language Models as Knowledge Bases?cited by 1,922
  8. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 951
  9. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 929
  10. 2016Complex Embeddings for Simple Link Predictioncited by 897
  11. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 893
  12. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
38 more
  1. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  2. 2020Recipes for building an open-domain chatbotcited by 593
  3. 2019ERNIE: Enhanced Language Representation with Informative Entitiescited by 525
  4. 2019KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representationcited by 356
  5. 2019K-BERT: Enabling Language Representation with Knowledge Graphcited by 303
  6. 2020FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarizationcited by 292
  7. 2021QuestEval: Summarization Asks for Fact-based Evaluationcited by 241
  8. 2020Reducing conversational agents' overconfidence through linguistic calibrationcited by 209
  9. 2018SimplE Embedding for Link Prediction in Knowledge Graphscited by 195
  10. 2020Recipes for Safety in Open-domain Chatbotscited by 168
  11. 2019Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoringcited by 164
  12. 2022On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?cited by 137
  13. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
  14. 2020Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answeringcited by 122
  15. 2020A Survey of Knowledge-Enhanced Text Generationcited by 119
  16. 2020Knowledge-Grounded Dialogue Generation with Pre-trained Language Modelscited by 107
  17. 2020KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoningcited by 106
  18. 2021Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Groundingcited by 106
  19. 2021Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and Selectioncited by 75
  20. 2021Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Featurescited by 74
  21. 2019Barack's Wife Hillary: Using Knowledge-Graphs for Fact-Aware Language Modelingcited by 71
  22. 2020End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systemscited by 65
  23. 2019Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphscited by 59
  24. 2021Improving Factual Consistency of Abstractive Summarization via Question Answeringcited by 55
  25. 2020Knowledge Bridging for Empathetic Dialogue Generationcited by 50
  26. 2020A Controllable Model of Grounded Response Generationcited by 49
  27. 2019DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphscited by 33
  28. 2021Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representationcited by 32
  29. 2020GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systemscited by 29
  30. 2020Multi-hop Question Generation with Graph Convolutional Networkcited by 20
  31. 2022DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue Generationcited by 19
  32. 2021A Survey of Knowledge Graph Embedding and Their Applicationscited by 17
  33. 2021Grounding Dialogue Systems via Knowledge Graph Aware Decoding with Pre-trained Transformerscited by 8
  34. 2020A Survey of Document Grounded Dialogue Systems (DGDS)cited by 6
  35. 2022CHAE: Fine-Grained Controllable Story Generation with Characters, Actions and Emotionscited by 6
  36. 2019Multi-Relational Question Answering from Narratives: Machine Reading and Reasoning in Simulated Worldscited by 4
  37. 2019AMUSED: A Multi-Stream Vector Representation Method for Use in Natural Dialoguecited by 4
  38. 2020Knowledge-graph based Proactive Dialogue Generation with Improved Meta-Learningcited by 3

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 12; 2024: 23; 2025: 9; 2026: 3.

47 papers.

Sort:

By area:

  1. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 888
  2. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 663
  3. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  4. 2024A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Modelscited by 266
  5. 2023SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistencycited by 89
  6. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 85
  7. 2024LLM Internal States Reveal Hallucination Risk Faced With a Querycited by 80
  8. 2023Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-based Retrofittingcited by 70
  9. 2024Retrieval-Augmented Generation for Natural Language Processing: A Surveycited by 70
  10. 2024We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMscited by 61
  11. 2023RECALL: A Benchmark for LLMs Robustness against External Counterfactual Knowledgecited by 51
  12. 2023Making Large Language Models Perform Better in Knowledge Graph Completioncited by 48
35 more
  1. 2025Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinationscited by 48
  2. 2025Large Language Models Hallucination: A Comprehensive Surveycited by 45
  3. 2023KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detectioncited by 43
  4. 2023Teaching Language Models to Hallucinate Less with Synthetic Taskscited by 31
  5. 2024Mitigating Large Language Model Hallucination with Faithful Finetuningcited by 24
  6. 2023KnowledgeNavigator: Leveraging Large Language Models for Enhanced Reasoning over Knowledge Graphcited by 22
  7. 2025Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMscited by 22
  8. 2024Hallucination Detection and Hallucination Mitigation: An Investigationcited by 20
  9. 2024Graph-Based Retriever Captures the Long Tail of Biomedical Knowledgecited by 20
  10. 2024An Audit on the Perspectives and Challenges of Hallucinations in NLPcited by 17
  11. 2024LRP4RAG: Detecting Hallucinations in Retrieval-Augmented Generation via Layer-wise Relevance Propagationcited by 17
  12. 2024Mitigating Hallucinations in Large Language Models via Self-Refinement-Enhanced Knowledge Retrievalcited by 16
  13. 2024ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Modelscited by 14
  14. 2024Certainly Uncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awarenesscited by 13
  15. 2024Fine-Tuning Large Language Models to Appropriately Abstain with Semantic Entropycited by 9
  16. 2024ANAH: Analytical Annotation of Hallucinations in Large Language Modelscited by 7
  17. 2023Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inferencecited by 6
  18. 2024Enhanced Language Model Truthfulness with Learnable Intervention and Uncertainty Expressioncited by 6
  19. 2024Generative Subgraph Retrieval for Knowledge Graph-Grounded Dialog Generationcited by 6
  20. 2023Think While You Write: Hypothesis Verification Promotes Faithful Knowledge-to-Text Generationcited by 5
  21. 2024Into the Unknown: Self-Learning Large Language Modelscited by 5
  22. 2023Extrinsically-Focused Evaluation of Omissions in Medical Summarizationcited by 4
  23. 2024Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucinationcited by 4
  24. 2025Black-Box Hallucination Detection via Consistency Under the Uncertain Expressioncited by 4
  25. 2025KERAG_R: Knowledge-Enhanced Retrieval-Augmented Generation for Recommendationcited by 3
  26. 2025PsychCounsel-Bench: Evaluating the Psychology Intelligence of Large Language Modelscited by 2
  27. 2026How Retrieved Context Shapes Internal Representations in RAGcited by 2
  28. 2024ACCORD: Closing the Commonsense Measurability Gapcited by 1
  29. 2024Evidence-Enhanced Triplet Generation Framework for Hallucination Alleviation in Generative Question Answeringcited by 1
  30. 2024Retrieval-Augmented Language Model for Extreme Multi-Label Knowledge Graph Link Predictioncited by 0
  31. 2024Detecting Response Generation Not Requiring Factual Judgmentcited by 0
  32. 2025The Impact of Negated Text on Hallucination with Large Language Modelscited by 0
  33. 2025Improving LLM's Attachment to External Knowledge In Dialogue Generation Tasks Through Entity Anonymizationcited by 0
  34. 2026Beyond Overlap Metrics: Rewarding Reasoning and Preferences for Faithful Multi-Role Dialogue Summarizationcited by 0
  35. 2026On Improving Faithfulness of Podcasts from Documentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generation
  2. 2025Aligning Knowledge Graphs and Language Models for Factual Accuracy
  3. 2021Reason first, then respond: Modular Generation for Knowledge-infused Dialogue
  4. 2023Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents
  5. 2026SKG-Eval: Stateful Evaluation of Multi-Turn Dialogue via Incremental Semantic Knowledge Graphs
  6. 2025ProgRAG: Hallucination-Resistant Progressive Retrieval and Reasoning over Knowledge Graphs
  7. 2022Towards Large-Scale Interpretable Knowledge Graph Reasoning for Dialogue Systems
  8. 2023MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models