@inproceedings{sultan-etal-2024-structured,
title = "Structured Chain-of-Thought Prompting for Few-Shot Generation of Content-Grounded {QA} Conversations",
author = "Sultan, Md Arafat and
Ganhotra, Jatin and
Astudillo, Ram{\'o}n",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.948",
pages = "16172--16187",
abstract = "We introduce a structured chain-of-thought (SCoT) prompting approach to generating content-grounded multi-turn question-answer conversations with a pre-trained large language model (LLM). At the core of our proposal is a structured breakdown of the complex task into a number of states in a state machine, so that actions corresponding to various subtasks, e.g., content reading and utterance generation, can be executed in their own dedicated states. Each state leverages a unique set of resources, including prompts and (optionally) additional tools, to augment the generation process. Automatic evaluation shows that SCoT prompting with designated states for hallucination mitigation can increase agent faithfulness to grounding documents by up to 16.8{\%}. When used as training data, our open-domain conversations synthesized from only 6 Wikipedia-based seed demonstrations train strong conversational QA agents. In out-of-domain evaluation, for example, we observe improvements of up to 13.9{\%} in F1-score against ground truth over target domain gold data when the latter is augmented with our generated examples.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sultan-etal-2024-structured">
<titleInfo>
<title>Structured Chain-of-Thought Prompting for Few-Shot Generation of Content-Grounded QA Conversations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Arafat</namePart>
<namePart type="family">Sultan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jatin</namePart>
<namePart type="family">Ganhotra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramón</namePart>
<namePart type="family">Astudillo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce a structured chain-of-thought (SCoT) prompting approach to generating content-grounded multi-turn question-answer conversations with a pre-trained large language model (LLM). At the core of our proposal is a structured breakdown of the complex task into a number of states in a state machine, so that actions corresponding to various subtasks, e.g., content reading and utterance generation, can be executed in their own dedicated states. Each state leverages a unique set of resources, including prompts and (optionally) additional tools, to augment the generation process. Automatic evaluation shows that SCoT prompting with designated states for hallucination mitigation can increase agent faithfulness to grounding documents by up to 16.8%. When used as training data, our open-domain conversations synthesized from only 6 Wikipedia-based seed demonstrations train strong conversational QA agents. In out-of-domain evaluation, for example, we observe improvements of up to 13.9% in F1-score against ground truth over target domain gold data when the latter is augmented with our generated examples.</abstract>
<identifier type="citekey">sultan-etal-2024-structured</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.948</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>16172</start>
<end>16187</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Structured Chain-of-Thought Prompting for Few-Shot Generation of Content-Grounded QA Conversations
%A Sultan, Md Arafat
%A Ganhotra, Jatin
%A Astudillo, Ramón
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F sultan-etal-2024-structured
%X We introduce a structured chain-of-thought (SCoT) prompting approach to generating content-grounded multi-turn question-answer conversations with a pre-trained large language model (LLM). At the core of our proposal is a structured breakdown of the complex task into a number of states in a state machine, so that actions corresponding to various subtasks, e.g., content reading and utterance generation, can be executed in their own dedicated states. Each state leverages a unique set of resources, including prompts and (optionally) additional tools, to augment the generation process. Automatic evaluation shows that SCoT prompting with designated states for hallucination mitigation can increase agent faithfulness to grounding documents by up to 16.8%. When used as training data, our open-domain conversations synthesized from only 6 Wikipedia-based seed demonstrations train strong conversational QA agents. In out-of-domain evaluation, for example, we observe improvements of up to 13.9% in F1-score against ground truth over target domain gold data when the latter is augmented with our generated examples.
%U https://aclanthology.org/2024.findings-emnlp.948
%P 16172-16187
Markdown (Informal)
[Structured Chain-of-Thought Prompting for Few-Shot Generation of Content-Grounded QA Conversations](https://aclanthology.org/2024.findings-emnlp.948) (Sultan et al., Findings 2024)
ACL