# Reason first, then respond: Modular Generation for Knowledge-infused Dialogue

arXiv: https://arxiv.org/abs/2111.05204 · HTML: https://mlsanity.com/paper/2111.05204/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 53 references that are in the map.
- First posted on arXiv 9 Nov 2021.

## Builds on (most cited first, 30 of 44)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs](https://mlsanity.com/paper/1903.00161/) (2019)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond](https://mlsanity.com/paper/1602.06023/) (2016)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [CoQA: A Conversational Question Answering Challenge](https://mlsanity.com/paper/1808.07042/) (2018)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization](https://mlsanity.com/paper/1911.12237/) (2019)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [Towards a Human-like Open-Domain Chatbot](https://mlsanity.com/paper/2001.09977/) (2020)
- [QuAC : Question Answering in Context](https://mlsanity.com/paper/1808.07036/) (2018)
- [Persistent Anti-Muslim Bias in Large Language Models](https://mlsanity.com/paper/2101.05783/) (2021)
- [Internet-Augmented Dialogue Generation](https://mlsanity.com/paper/2107.07566/) (2021)
- [Gender Bias in Neural Natural Language Processing](https://mlsanity.com/paper/1807.11714/) (2018)
- [DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehension](https://mlsanity.com/paper/1902.00164/) (2019)
- [ParlAI: A Dialog Research Software Platform](https://mlsanity.com/paper/1705.06476/) (2017)
- [Learning to Speak and Act in a Fantasy Text Adventure Game](https://mlsanity.com/paper/1903.03094/) (2019)
- [A Dataset for Document Grounded Conversations](https://mlsanity.com/paper/1809.07358/) (2018)
- [Skill Induction and Planning with Latent Language](https://mlsanity.com/paper/2110.01517/) (2021)
- [ACUTE-EVAL: Improved Dialogue Evaluation with Optimized Questions and Multi-turn Comparisons](https://mlsanity.com/paper/1909.03087/) (2019)

## Built on by (most cited first, 30 of 32)

- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [Improving alignment of dialogue agents via targeted human judgements](https://mlsanity.com/paper/2209.14375/) (2022)
- [Chain-of-Verification Reduces Hallucination in Large Language Models](https://mlsanity.com/paper/2309.11495/) (2023)
- [BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage](https://mlsanity.com/paper/2208.03188/) (2022)
- [A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems](https://mlsanity.com/paper/2402.18013/) (2024)
- [Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion](https://mlsanity.com/paper/2203.13224/) (2022)
- [Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents](https://mlsanity.com/paper/2201.04723/) (2022)
- [Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors](https://mlsanity.com/paper/2407.09136/) (2024)
- [Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedback](https://mlsanity.com/paper/2208.03270/) (2022)
- [Reflect, Not Reflex: Inference-Based Common Ground Improves Dialogue Response Quality](https://mlsanity.com/paper/2211.09267/) (2022)
- [Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback](https://mlsanity.com/paper/2501.10799/) (2025)
- [The "Colonial Impulse" of Natural Language Processing: An Audit of Bengali Sentiment Analysis Tools and Their Identity-based Biases](https://mlsanity.com/paper/2401.10535/) (2024)
- [Generative Knowledge Selection for Knowledge-Grounded Dialogues](https://mlsanity.com/paper/2304.04836/) (2023)
- [Q-TOD: A Query-driven Task-oriented Dialogue System](https://mlsanity.com/paper/2210.07564/) (2022)
- [Structured Chain-of-Thought Prompting for Few-Shot Generation of Content-Grounded QA Conversations](https://mlsanity.com/paper/2402.11770/) (2024)
- [More Victories, Less Cooperation: Assessing Cicero's Diplomacy Play](https://mlsanity.com/paper/2406.04643/) (2024)
- [MockLLM: A Multi-Agent Behavior Collaboration Framework for Online Job Seeking and Recruiting](https://mlsanity.com/paper/2405.18113/) (2024)
- [Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models](https://mlsanity.com/paper/2410.15116/) (2024)
- [Link the World: Improving Open-domain Conversation with Dynamic Spatiotemporal-aware Knowledge](https://mlsanity.com/paper/2206.14000/) (2022)
- [Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Tracking](https://mlsanity.com/paper/2302.05932/) (2023)
- [PK-ICR: Persona-Knowledge Interactive Context Retrieval for Grounded Dialogue](https://mlsanity.com/paper/2302.06674/) (2023)
- [Don't Take This Out of Context! On the Need for Contextual Models and Evaluations for Stylistic Rewriting](https://mlsanity.com/paper/2305.14755/) (2023)
- [Decoding a Neural Retriever's Latent Space for Query Suggestion](https://mlsanity.com/paper/2210.12084/) (2022)
- [KGQuiz: Evaluating the Generalization of Encoded Knowledge in Large Language Models](https://mlsanity.com/paper/2310.09725/) (2023)
- [Achieving Conversational Goals with Unsupervised Post-hoc Knowledge Injection](https://mlsanity.com/paper/2203.11399/) (2022)
- [There Is No Standard Answer: Knowledge-Grounded Dialogue Generation with Adversarial Activated Multi-Reference Learning](https://mlsanity.com/paper/2210.12459/) (2022)
- [Mind the Knowledge Gap: A Survey of Knowledge-enhanced Dialogue Systems](https://mlsanity.com/paper/2212.09252/) (2022)
- [Social Commonsense-Guided Search Query Generation for Open-Domain Knowledge-Powered Conversations](https://mlsanity.com/paper/2310.14340/) (2023)
- [Investigating Content Planning for Navigating Trade-offs in Knowledge-Grounded Dialogue](https://mlsanity.com/paper/2402.02077/) (2024)
- [Towards Language-driven Scientific AI](https://mlsanity.com/paper/2210.15327/) (2022)

## Abstract (arXiv)

Large language models can produce fluent dialogue but often hallucinate factual inaccuracies. While retrieval-augmented models help alleviate this issue, they still face a difficult challenge of both reasoning to provide correct knowledge and generating conversation simultaneously. In this work, we propose a modular model, Knowledge to Response (K2R), for incorporating knowledge into conversational agents, which breaks down this problem into two easier steps. K2R first generates a knowledge sequence, given a dialogue context, as an intermediate step. After this "reasoning step", the model then attends to its own generated knowledge sequence, as well as the dialogue context, to produce a final response. In detailed experiments, we find that such a model hallucinates less in knowledge-grounded dialogue tasks, and has advantages in terms of interpretability and modularity. In particular, it can be used to fuse QA and dialogue systems together to enable dialogue agents to give knowledgeable answers, or QA models to give conversational responses in a zero-shot setting.