Saved in:
Bibliographic Details
Main Authors: An, Kaikai, Yang, Fangkai, Li, Liqun, Lu, Junting, Cheng, Sitao, Si, Shuzheng, Wang, Lu, Zhao, Pu, Cao, Lele, Lin, Qingwei, Rajmohan, Saravan, Zhang, Dongmei, Chang, Baobao
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.13372
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909811038224384
author An, Kaikai
Yang, Fangkai
Li, Liqun
Lu, Junting
Cheng, Sitao
Si, Shuzheng
Wang, Lu
Zhao, Pu
Cao, Lele
Lin, Qingwei
Rajmohan, Saravan
Zhang, Dongmei
Chang, Baobao
author_facet An, Kaikai
Yang, Fangkai
Li, Liqun
Lu, Junting
Cheng, Sitao
Si, Shuzheng
Wang, Lu
Zhao, Pu
Cao, Lele
Lin, Qingwei
Rajmohan, Saravan
Zhang, Dongmei
Chang, Baobao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_13372
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Thread: A Logic-Based Data Organization Paradigm for How-To Question Answering with Retrieval Augmented Generation
An, Kaikai
Yang, Fangkai
Li, Liqun
Lu, Junting
Cheng, Sitao
Si, Shuzheng
Wang, Lu
Zhao, Pu
Cao, Lele
Lin, Qingwei
Rajmohan, Saravan
Zhang, Dongmei
Chang, Baobao
Artificial Intelligence
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.
title Thread: A Logic-Based Data Organization Paradigm for How-To Question Answering with Retrieval Augmented Generation
topic Artificial Intelligence
url https://arxiv.org/abs/2406.13372