mlsanityData to 7 Oct 2026

Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features

arXiv 2107.06963 ↗First posted 14 Jul 2021cs.CLcited by 74

Not on the map. Why?

Abstract (arXiv)

Knowledge-grounded dialogue systems are intended to convey information that is based on evidence provided in a given source text. We discuss the challenges of training a generative neural dialogue model for such systems that is controlled to stay faithful to the evidence. Existing datasets contain a mix of conversational responses that are faithful to selected evidence as well as more subjective or chit-chat style responses. We propose different evaluation measures to disentangle these different styles of responses by quantifying the informativeness and objectivity. At training time, additional inputs based on these evaluation measures are given to the dialogue model. At generation time, these additional inputs act as stylistic controls that encourage the model to generate responses that are faithful to the provided evidence. We also investigate the usage of additional controls at decoding time using resampling techniques. In addition to automatic metrics, we perform a human evaluation study where raters judge the output of these controlled generation models to be generally more objective and faithful to the evidence compared to baseline dialogue systems.

Key facts. Cited by 74 papers in the map (data through 7 Oct 2026). Builds on 23 of its 31 references that are in the map. First posted on arXiv 14 Jul 2021.

Builds on

23 of 31 references.

References · 23

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  4. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  5. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  6. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 820
  7. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  8. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  9. 2016How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generationcited by 356
  10. 2017Faithful to the Original: Fact Aware Neural Abstractive Summarizationcited by 141
  11. 2019What makes a good conversation? How controllable attributes affect human judgmentscited by 140
  12. 2017A Knowledge-Grounded Neural Conversation Modelcited by 136
11 more
  1. 2018Data-to-Text Generation with Content Selection and Planningcited by 106
  2. 2020Controlled Hallucinations: Learning to Generate Faithfully from Noisy Datacited by 83
  3. 2020Sequential Latent Knowledge Selection for Knowledge-Grounded Dialoguecited by 82
  4. 2019Learning to Select Knowledge for Response Generation in Dialog Systemscited by 80
  5. 2018Polite Dialogue Generation Without Parallel Datacited by 57
  6. 2018Towards Exploiting Background Knowledge for Building Conversation Systemscited by 57
  7. 2020A Controllable Model of Grounded Response Generationcited by 49
  8. 2019The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agentscited by 45
  9. 2019Conversing by Reading: Contentful Neural Conversation with On-demand Machine Readingcited by 32
  10. 2020Reducing Quantity Hallucinations in Abstractive Summarizationcited by 22
  11. 2020Response-Anticipated Memory for On-Demand Knowledge Integration in Response Generationcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 16; 2023: 30; 2024: 15; 2025: 6; 2026: 4.

74 papers.

Sort:

By area:

  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  2. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 394
  3. 2021Measuring Attribution in Natural Language Generation Modelscited by 253
  4. 2022Factuality Enhanced Language Models for Open-Ended Text Generationcited by 200
  5. 2023Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answeringcited by 150
  6. 2022On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?cited by 137
  7. 2022A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Modelscited by 128
  8. 2024RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systemscited by 115
  9. 2022FaithDial: A Faithful Benchmark for Information-Seeking Dialoguecited by 108
  10. 2023What You See is What You Read? Improving Text-Image Alignment Evaluationcited by 105
  11. 2023Enhancing Uncertainty-Based Hallucination Detection with Stronger Focuscited by 98
  12. 2023Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedbackcited by 71
38 more
  1. 2021DialFact: A Benchmark for Fact-Checking in Dialoguecited by 62
  2. 2024Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generationcited by 49
  3. 2022RHO (ρ): Reducing Hallucination in Open-domain Dialogues with Knowledge Groundingcited by 47
  4. 2023KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detectioncited by 43
  5. 2022mFACE: Multilingual Summarization with Factual Consistency Evaluationcited by 42
  6. 2023Opportunities and Challenges in Neural Dialog Tutoringcited by 33
  7. 2023Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuningcited by 33
  8. 2023Diving Deep into Modes of Fact Hallucinations in Dialogue Systemscited by 32
  9. 2021Rome was built in 1776: A Case Study on Factual Correctness in Knowledge-Grounded Response Generationcited by 29
  10. 2023Elastic Weight Removal for Faithful and Abstractive Dialogue Generationcited by 29
  11. 2022Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methodscited by 27
  12. 2023The Dangers of trusting Stochastic Parrots: Faithfulness and Trust in Open-domain Conversational Question Answeringcited by 26
  13. 2022Multi-Stage Prompting for Knowledgeable Dialogue Generationcited by 22
  14. 2024Hallucination Detection and Hallucination Mitigation: An Investigationcited by 20
  15. 2023Improving Factual Consistency for Knowledge-Grounded Dialogue Systems via Knowledge Enhancement and Alignmentcited by 19
  16. 2023"Why is this misleading?": Detecting News Headline Hallucinations with Explanationscited by 17
  17. 2024Gl'orIA -- A Generative and Open Large Language Model for Portuguesecited by 16
  18. 2024Zero-shot Persuasive Chatbots with LLM-Generated Strategies and Information Retrievalcited by 14
  19. 2023With a Little Push, NLI Models can Robustly and Efficiently Predict Faithfulnesscited by 13
  20. 2023Pointwise Mutual Information Based Metric and Decoding Strategy for Faithful Generation in Document Grounded Dialogscited by 11
  21. 2022Don't Forget Your ABC's: Evaluating the State-of-the-Art in Chat-Oriented Dialogue Systemscited by 9
  22. 2023textitDial BeInfo for Faithfulness: Improving Factuality of Information-Seeking Dialogue via Behavioural Fine-Tuningcited by 9
  23. 2024SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generationcited by 9
  24. 2022TRUE: Re-evaluating Factual Consistency Evaluationcited by 7
  25. 2023Improved Instruction Ordering in Recipe-Grounded Conversationcited by 7
  26. 2023Critic-Driven Decoding for Mitigating Hallucinations in Data-to-text Generationcited by 7
  27. 2023Measuring and Mitigating Constraint Violations of In-Context Learning for Utterance-to-API Semantic Parsingcited by 6
  28. 2023Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inferencecited by 6
  29. 2025Evaluating Evaluation Metrics -- The Mirage of Hallucination Detectioncited by 6
  30. 2023Sequence-Level Certainty Reduces Hallucination In Knowledge-Grounded Dialogue Generationcited by 5
  31. 2022Stylized Knowledge-Grounded Dialogue Generation via Disentangled Template Rewritingcited by 4
  32. 2023Controllable Generation of Dialogue Acts for Dialogue Systems via Few-Shot Response Generation and Rankingcited by 4
  33. 2023Generating Faithful Text From a Knowledge Graph with Noisy Reference Textcited by 4
  34. 2023Calibrating Likelihoods towards Consistency in Summarization Modelscited by 4
  35. 2024SLM Meets LLM: Balancing Latency, Interpretability and Consistency in Hallucination Detectioncited by 4
  36. 2024Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucinationcited by 4
  37. 2022Precisely the Point: Adversarial Augmentations for Faithful and Informative Text Generationcited by 3
  38. 2022Evaluating Parameter Efficient Learning for Generationcited by 3

50 most cited of 74 All 74 (JSON)