mlsanityData to 7 Oct 2026

Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding

arXiv 2104.08455 ↗First posted 17 Apr 2021cs.CLcited by 106

Not on the map. Why?

Abstract (arXiv)

Dialogue systems powered by large pre-trained language models (LM) exhibit an innate ability to deliver fluent and natural-looking responses. Despite their impressive generation performance, these models can often generate factually incorrect statements impeding their widespread adoption. In this paper, we focus on the task of improving the faithfulness -- and thus reduce hallucination -- of Neural Dialogue Systems to known facts supplied by a Knowledge Graph (KG). We propose Neural Path Hunter which follows a generate-then-refine strategy whereby a generated response is amended using the k-hop subgraph of a KG. Neural Path Hunter leverages a separate token-level fact critic to identify plausible sources of hallucination followed by a refinement stage consisting of a chain of two neural LM's that retrieves correct entities by crafting a query signal that is propagated over the k-hop subgraph. Our proposed model can easily be applied to any dialogue generated responses without retraining the model. We empirically validate our proposed approach on the OpenDialKG dataset against a suite of metrics and report a relative improvement of faithfulness over dialogue responses by 20.35% based on FeQA (Durmus et al., 2020).

Key facts. Cited by 106 papers in the map (data through 7 Oct 2026). Builds on 39 of its 76 references that are in the map. First posted on arXiv 17 Apr 2021.

Builds on

39 of 76 references.

References · 39

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  5. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  6. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  7. 2019Language Models as Knowledge Bases?cited by 1,922
  8. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  9. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  10. 2019SpanBERT: Improving Pre-training by Representing and Predicting Spanscited by 832
  11. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  12. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 713
27 more
  1. 2018Object Hallucination in Image Captioningcited by 661
  2. 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 578
  3. 2019Composition-based Multi-Relational Graph Convolutional Networkscited by 395
  4. 2020Asking and Answering Questions to Evaluate the Factual Consistency of Summariescited by 376
  5. 2017Six Challenges for Neural Machine Translationcited by 334
  6. 2020FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarizationcited by 292
  7. 2020ToTTo: A Controlled Table-To-Text Generation Datasetcited by 267
  8. 2017Challenges in Data-to-Document Generationcited by 226
  9. 2015Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Modelscited by 207
  10. 2015A Neural Conversational Modelcited by 195
  11. 2019Challenges in Building Intelligent Open-domain Dialog Systemscited by 147
  12. 2018Pathologies of Neural Models Make Interpretations Difficultcited by 140
  13. 2020On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translationcited by 127
  14. 2019Handling Divergent Reference Texts when Evaluating Table-to-Text Generationcited by 119
  15. 2015A Neural Network Approach to Context-Sensitive Generation of Conversational Responsescited by 98
  16. 2019Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challengecited by 86
  17. 2019Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generationcited by 62
  18. 2020The Adapter-Bot: All-In-One Controllable Conversational Modelcited by 38
  19. 2019Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialoguecited by 35
  20. 2020Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systemscited by 35
  21. 2019DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphscited by 33
  22. 2018Findings of the E2E NLG Challengecited by 28
  23. 2018Augmenting Neural Response Generation with Context-Aware Topical Attentioncited by 27
  24. 2020Structure Aware Negative Sampling in Knowledge Graphscited by 26
  25. 2020User Memory Reasoning for Conversational Recommendationcited by 19
  26. 2017Flexible End-to-End Dialogue System for Knowledge Grounded Conversationcited by 18
  27. 2017Augmenting End-to-End Dialog Systems with Commonsense Knowledgecited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 17; 2023: 30; 2024: 39; 2025: 12; 2026: 4.

106 papers.

Sort:

By area:

  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  2. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  3. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 394
  4. 2024A Survey on Hallucination in Large Vision-Language Modelscited by 352
  5. 2023HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Modelscited by 329
  6. 2024Hallucination is Inevitable: An Innate Limitation of Large Language Modelscited by 329
  7. 2024Knowledge Conflicts for LLMs: A Surveycited by 274
  8. 2023Challenges and Applications of Large Language Modelscited by 251
  9. 2024Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMscited by 246
  10. 2023A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generationcited by 202
  11. 2022Factuality Enhanced Language Models for Open-Ended Text Generationcited by 200
  12. 2023"Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letterscited by 196
38 more
  1. 2024Agent AI: Surveying the Horizons of Multimodal Interactioncited by 167
  2. 2023Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answeringcited by 150
  3. 2022On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?cited by 137
  4. 2023Factuality Challenges in the Era of Large Language Modelscited by 125
  5. 2024AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathwayscited by 122
  6. 2022FaithDial: A Faithful Benchmark for Information-Seeking Dialoguecited by 108
  7. 2024VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Modelscited by 88
  8. 2024The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Modelscited by 87
  9. 2023Retrieving Multimodal Information for Augmented Generation: A Surveycited by 84
  10. 2023Cognitive Mirage: A Review of Hallucinations in Large Language Modelscited by 83
  11. 2023FLIRT: Feedback Loop In-context Red Teamingcited by 81
  12. 2021Evaluating Attribution in Dialogue Systems: The BEGIN Benchmarkcited by 75
  13. 2023Exposing Attention Glitches with Flip-Flop Language Modelingcited by 74
  14. 2022Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-trainingcited by 71
  15. 2023Automatic Evaluation of Attribution by Large Language Modelscited by 70
  16. 2021Few-Shot Bot: Prompt-Based Learning for Dialogue Systemscited by 64
  17. 2024Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systemscited by 63
  18. 2024Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agentscited by 63
  19. 2021DialFact: A Benchmark for Fact-Checking in Dialoguecited by 62
  20. 2023Mitigating Fine-Grained Hallucination by Fine-Tuning Large Vision-Language Models with Caption Rewritescited by 61
  21. 2024We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMscited by 61
  22. 2024Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generationcited by 49
  23. 2022RHO (ρ): Reducing Hallucination in Open-domain Dialogues with Knowledge Groundingcited by 47
  24. 2025Large Language Models Hallucination: A Comprehensive Surveycited by 45
  25. 2023Effective Large Language Model Adaptation for Improved Grounding and Citation Generationcited by 44
  26. 2022Contrastive Learning Reduces Hallucination in Conversationscited by 39
  27. 2024A Survey on Large Language Model Hallucination via a Creativity Perspectivecited by 38
  28. 2023SoK: Memorization in General-Purpose Large Language Modelscited by 36
  29. 2024AI Hallucinations: A Misnomer Worth Clarifyingcited by 34
  30. 2023Diving Deep into Modes of Fact Hallucinations in Dialogue Systemscited by 32
  31. 2025Generative to Agentic AI: Survey, Conceptualization, and Challengescited by 32
  32. 2024Improving Uncertainty Quantification in Large Language Models via Semantic Embeddingscited by 30
  33. 2021Rome was built in 1776: A Case Study on Factual Correctness in Knowledge-Grounded Response Generationcited by 29
  34. 2023Elastic Weight Removal for Faithful and Abstractive Dialogue Generationcited by 29
  35. 2022Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methodscited by 27
  36. 2022Evaluating Mixed-initiative Conversational Search Systems via User Simulationcited by 24
  37. 2023Domain-Agnostic Molecular Generation with Chemical Feedbackcited by 21
  38. 2024Hallucination Detection and Hallucination Mitigation: An Investigationcited by 20

50 most cited of 106 All 106 (JSON)