mlsanityData to 7 Oct 2026

Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Model

arXiv 2210.17418 ↗First posted 31 Oct 2022cs.CL cs.AI cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

In this work, we present a model for document-grounded response generation in dialog that is decomposed into two components according to Bayes theorem. One component is a traditional ungrounded response generation model and the other component models the reconstruction of the grounding document based on the dialog context and generated response. We propose different approximate decoding schemes and evaluate our approach on multiple open-domain and task-oriented document-grounded dialog datasets. Our experiments show that the model is more factual in terms of automatic factuality metrics than the baseline model. Furthermore, we outline how introducing scaling factors between the components allows for controlling the tradeoff between factuality and fluency in the model output. Finally, we compare our approach to a recently proposed method to control factuality in grounded dialog, CTRL (arXiv:2107.06963), and show that both approaches can be combined to achieve additional improvements.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 47 of its 62 references that are in the map. First posted on arXiv 31 Oct 2022.

Builds on

47 of 62 references.

References · 47

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  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. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  7. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  8. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  9. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  10. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  11. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  12. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
35 more
  1. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 820
  2. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  3. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  4. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
  5. 2020Recipes for building an open-domain chatbotcited by 593
  6. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  7. 2021Internet-Augmented Dialogue Generationcited by 217
  8. 2019The Second Conversational Intelligence Challenge (ConvAI2)cited by 178
  9. 2019Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoringcited by 164
  10. 2021Noisy Channel Language Model Prompting for Few-Shot Text Classificationcited by 163
  11. 2017Faithful to the Original: Fact Aware Neural Abstractive Summarizationcited by 141
  12. 2019Taskmaster-1: Toward a Realistic and Diverse Dialog Datasetcited by 139
  13. 2022On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?cited by 137
  14. 2021Q2: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answeringcited by 131
  15. 2022FaithDial: A Faithful Benchmark for Information-Seeking Dialoguecited by 108
  16. 2018A Dataset for Document Grounded Conversationscited by 104
  17. 2022Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completioncited by 102
  18. 2020doc2dial: A Goal-Oriented Document-Grounded Dialogue Datasetcited by 88
  19. 2021Evaluating Attribution in Dialogue Systems: The BEGIN Benchmarkcited by 75
  20. 2021Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Featurescited by 74
  21. 2020Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Accesscited by 58
  22. 2020Low-Resource Knowledge-Grounded Dialogue Generationcited by 53
  23. 2019Simple and Effective Noisy Channel Modeling for Neural Machine Translationcited by 37
  24. 2020Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directionscited by 34
  25. 2021Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialogcited by 33
  26. 2021"How Robust r u?": Evaluating Task-Oriented Dialogue Systems on Spoken Conversationscited by 30
  27. 2021Rome was built in 1776: A Case Study on Factual Correctness in Knowledge-Grounded Response Generationcited by 29
  28. 2021Focused Attention Improves Document-Grounded Generationcited by 24
  29. 2021Pretraining the Noisy Channel Model for Task-Oriented Dialoguecited by 23
  30. 2021Am I Me or You? State-of-the-Art Dialogue Models Cannot Maintain an Identitycited by 22
  31. 2016The Neural Noisy Channelcited by 19
  32. 2021Learning to Select External Knowledge with Multi-Scale Negative Samplingcited by 16
  33. 2021NVIDIA NeMo Neural Machine Translation Systems for English-German and English-Russian News and Biomedical Tasks at WMT21cited by 8
  34. 2021Adapting Document-Grounded Dialog Systems to Spoken Conversations using Data Augmentation and a Noisy Channel Modelcited by 5
  35. 2021Cascaded Span Extraction and Response Generation for Document-Grounded Dialogcited by 4

Built on by

Cited by year

Citing papers per year: 2023: 3.

3 papers.

  1. 2023Elastic Weight Removal for Faithful and Abstractive Dialogue Generationcited by 29
  2. 2023textitDial BeInfo for Faithfulness: Improving Factuality of Information-Seeking Dialogue via Behavioural Fine-Tuningcited by 9
  3. 2023Task-oriented Document-Grounded Dialog Systems by HLTPR@RWTH for DSTC9 and DSTC10cited by 4