From Complex to Atomic: Enhancing Augmented Generation via Knowledge-Aware Dual Rewriting and Reasoning

Jinyu Wang, Jingjing Fu, Rui Wang, Lei Song, Jiang Bian
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:62890-62915, 2025.

Abstract

Recent advancements in Retrieval-Augmented Generation (RAG) systems have significantly enhanced the capabilities of large language models (LLMs) by incorporating external knowledge retrieval. However, the sole reliance on retrieval is often inadequate for mining deep, domain-specific knowledge and for performing logical reasoning from specialized datasets. To tackle these challenges, we present an approach, which is designed to extract, comprehend, and utilize domain knowledge while constructing a coherent rationale. At the heart of our approach lie four pivotal components: a knowledge atomizer that extracts atomic questions from raw data, a query proposer that generates subsequent questions to facilitate the original inquiry, an atomic retriever that locates knowledge based on atomic knowledge alignments, and an atomic selector that determines which follow-up questions to pose guided by the retrieved information. Through this approach, we implement a knowledge-aware task decomposition strategy that adeptly extracts multifaceted knowledge from segmented data and iteratively builds the rationale in alignment with the initial query and the acquired knowledge. We conduct comprehensive experiments to demonstrate the efficacy of our approach across various benchmarks, particularly those requiring multihop reasoning steps. The results indicate a significant enhancement in performance, up to 12.6% over the second-best method, underscoring the potential of the approach in complex, knowledge-intensive applications.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-wang25ac, title = {From Complex to Atomic: Enhancing Augmented Generation via Knowledge-Aware Dual Rewriting and Reasoning}, author = {Wang, Jinyu and Fu, Jingjing and Wang, Rui and Song, Lei and Bian, Jiang}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {62890--62915}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/wang25ac/wang25ac.pdf}, url = {https://proceedings.mlr.press/v267/wang25ac.html}, abstract = {Recent advancements in Retrieval-Augmented Generation (RAG) systems have significantly enhanced the capabilities of large language models (LLMs) by incorporating external knowledge retrieval. However, the sole reliance on retrieval is often inadequate for mining deep, domain-specific knowledge and for performing logical reasoning from specialized datasets. To tackle these challenges, we present an approach, which is designed to extract, comprehend, and utilize domain knowledge while constructing a coherent rationale. At the heart of our approach lie four pivotal components: a knowledge atomizer that extracts atomic questions from raw data, a query proposer that generates subsequent questions to facilitate the original inquiry, an atomic retriever that locates knowledge based on atomic knowledge alignments, and an atomic selector that determines which follow-up questions to pose guided by the retrieved information. Through this approach, we implement a knowledge-aware task decomposition strategy that adeptly extracts multifaceted knowledge from segmented data and iteratively builds the rationale in alignment with the initial query and the acquired knowledge. We conduct comprehensive experiments to demonstrate the efficacy of our approach across various benchmarks, particularly those requiring multihop reasoning steps. The results indicate a significant enhancement in performance, up to 12.6% over the second-best method, underscoring the potential of the approach in complex, knowledge-intensive applications.} }
Endnote
%0 Conference Paper %T From Complex to Atomic: Enhancing Augmented Generation via Knowledge-Aware Dual Rewriting and Reasoning %A Jinyu Wang %A Jingjing Fu %A Rui Wang %A Lei Song %A Jiang Bian %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-wang25ac %I PMLR %P 62890--62915 %U https://proceedings.mlr.press/v267/wang25ac.html %V 267 %X Recent advancements in Retrieval-Augmented Generation (RAG) systems have significantly enhanced the capabilities of large language models (LLMs) by incorporating external knowledge retrieval. However, the sole reliance on retrieval is often inadequate for mining deep, domain-specific knowledge and for performing logical reasoning from specialized datasets. To tackle these challenges, we present an approach, which is designed to extract, comprehend, and utilize domain knowledge while constructing a coherent rationale. At the heart of our approach lie four pivotal components: a knowledge atomizer that extracts atomic questions from raw data, a query proposer that generates subsequent questions to facilitate the original inquiry, an atomic retriever that locates knowledge based on atomic knowledge alignments, and an atomic selector that determines which follow-up questions to pose guided by the retrieved information. Through this approach, we implement a knowledge-aware task decomposition strategy that adeptly extracts multifaceted knowledge from segmented data and iteratively builds the rationale in alignment with the initial query and the acquired knowledge. We conduct comprehensive experiments to demonstrate the efficacy of our approach across various benchmarks, particularly those requiring multihop reasoning steps. The results indicate a significant enhancement in performance, up to 12.6% over the second-best method, underscoring the potential of the approach in complex, knowledge-intensive applications.
APA
Wang, J., Fu, J., Wang, R., Song, L. & Bian, J.. (2025). From Complex to Atomic: Enhancing Augmented Generation via Knowledge-Aware Dual Rewriting and Reasoning. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:62890-62915 Available from https://proceedings.mlr.press/v267/wang25ac.html.

Related Material