Structured Chain-of-Thought Prompting for Few-Shot Generation of Content-Grounded QA Conversations

Md Arafat Sultan, Jatin Ganhotra, Ramón Astudillo


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.
Anthology ID:
2024.findings-emnlp.948
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
16172–16187
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.948
DOI:
Bibkey:
Cite (ACL):
Md Arafat Sultan, Jatin Ganhotra, and Ramón Astudillo. 2024. Structured Chain-of-Thought Prompting for Few-Shot Generation of Content-Grounded QA Conversations. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 16172–16187, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Structured Chain-of-Thought Prompting for Few-Shot Generation of Content-Grounded QA Conversations (Sultan et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.948.pdf