{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/the-whole-truth-and-nothing-but-the-truth","title":"The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding","arxiv_id":"2209.07800","date":"2022-09-16","proceeding":null,"authors":["Hao Fang","Anusha Balakrishnan","Harsh Jhamtani","John Bufe","Jean Crawford","Jayant Krishnamurthy","Adam Pauls","Jason Eisner","Jacob Andreas","Dan Klein"],"abstract":"In a real-world dialogue system, generated text must be truthful and informative while remaining fluent and adhering to a prescribed style. Satisfying these constraints simultaneously is difficult for the two predominant paradigms in language generation: neural language modeling and rule-based generation. We describe a hybrid architecture for dialogue response generation that combines the strengths of both paradigms. The first component of this architecture is a rule-based content selection model defined using a new formal framework called dataflow transduction, which uses declarative rules to transduce a dialogue agent's actions and their results (represented as dataflow graphs) into context-free grammars representing the space of contextually acceptable responses. The second component is a constrained decoding procedure that uses these grammars to constrain the output of a neural language model, which selects fluent utterances. Our experiments show that this system outperforms both rule-based and learned approaches in human evaluations of fluency, relevance, and truthfulness.","url_abs":"https://arxiv.org/abs/2209.07800v2","url_pdf":"https://arxiv.org/pdf/2209.07800v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"the-whole-truth-and-nothing-but-the-truth","repo_url":"https://github.com/microsoft/dataflow2text","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"response-generation","task_name":"Response Generation"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2209.07800","atlas_url":"https://app.syntology.ai/?focus=2209.07800","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}