Thread: A Logic-Based Data Organization Paradigm for How-To Question Answering with Retrieval Augmented Generation

Kaikai An, Fangkai Yang, Liqun Li, Junting Lu, Sitao Cheng, Shuzheng Si, Lu Wang, Pu Zhao, Lele Cao, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Baobao Chang


Abstract
Recent advances in retrieval-augmented generation (RAG) have substantially improved question-answering systems, particularly for factoid ‘5Ws’ questions. However, significant challenges remain when addressing ‘1H’ questions, specifically how-to questions, which are integral for decision-making and require dynamic, step-by-step responses. The key limitation lies in the prevalent data organization paradigm, chunk, which commonly divides documents into fixed-size segments, and disrupts the logical coherence and connections within the context. To address this, we propose THREAD, a novel data organization paradigm enabling systems to handle how-to questions more effectively. Specifically, we introduce a new knowledge granularity, ‘logic unit’ (LU), where large language models transform documents into more structured and loosely interconnected LUs. Extensive experiments across both open-domain and industrial settings show that THREAD outperforms existing paradigms significantly, improving the success rate of handling how-to questions by 21% to 33%. Additionally, THREAD demonstrates high adaptability across diverse document formats, reducing retrieval information by up to 75% compared to chunk, and also shows better generalizability to ‘5Ws’ questions, such as multi-hop questions, outperforming other paradigms.
Anthology ID:
2025.emnlp-main.923
Volume:
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
18300–18319
Language:
URL:
https://aclanthology.org/2025.emnlp-main.923/
DOI:
Bibkey:
Cite (ACL):
Kaikai An, Fangkai Yang, Liqun Li, Junting Lu, Sitao Cheng, Shuzheng Si, Lu Wang, Pu Zhao, Lele Cao, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, and Baobao Chang. 2025. Thread: A Logic-Based Data Organization Paradigm for How-To Question Answering with Retrieval Augmented Generation. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 18300–18319, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Thread: A Logic-Based Data Organization Paradigm for How-To Question Answering with Retrieval Augmented Generation (An et al., EMNLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.emnlp-main.923.pdf
Checklist:
 2025.emnlp-main.923.checklist.pdf