Lune

EMNLP Findings2022

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

Nico Daheim, David Thulke, Christian Dugast, Hermann Ney

Abstract

In this work, we present a model for documentgrounded 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 opendomain 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 (Rashkin et al., 2021), and show that both approaches can be combined to achieve additional improvements.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Retrieval Augmentation Reduces Hallucination in Conversation cites BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
  • Retrieval Augmentation Reduces Hallucination in Conversation cites Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
  • Retrieval Augmentation Reduces Hallucination in Conversation cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
  • Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks cites BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on13

  1. Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
  2. BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger et al.ICLR 2020 · 8,443 citations
  3. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
  4. Retrieval Augmentation Reduces Hallucination in ConversationKurt Shuster, Spencer Poff, Moya Chen, Douwe Kiela et al.EMNLP Findings 2021 · 579 citations
  5. Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence ScoringSamuel Humeau, Kurt Shuster, Marie-Anne Lachaux, Jason WestonICLR 2020 · 316 citations

Related papers

  1. Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable FeaturesHannah Rashkin, David Reitter, Gaurav Singh Tomar, Dipanjan DasACL 2021
  2. Pointwise Mutual Information Based Metric and Decoding Strategy for Faithful Generation in Document Grounded DialogsYatin Nandwani, Vineet Kumar, Dinesh Raghu, Sachindra Joshi et al.EMNLP 2023 · 4 citations
  3. Enhancing Factuality through Consensus and Consistency in Summarization Using Minimum Bayes Risk DecodingRiza Setiawan Soetedjo, Yusuke Sakai, Hidetaka Kamigaito, Jingun Kwon et al.ACL Findings 2026
  4. A Controllable Model of Grounded Response GenerationZeqiu Wu, Michel Galley, Chris Brockett, Yizhe Zhang et al.AAAI 2021 · 89 citations
  5. RetGen: A Joint Framework for Retrieval and Grounded Text Generation ModelingYizhe Zhang, Siqi Sun, Xiang Gao, Yuwei Fang et al.AAAI 2022 · 45 citations
Dusk over the sea between two cliffs drawn in fine vertical lines