RECIPER: A Dual-View Retrieval Pipeline for Procedure-Oriented Materials Question Answering

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wu, Zhuoyu, Ou, Wenhui, Tan, Pei-Sze, Fang, Wenqi, Rajanala, Sailaja, Phan, Raphaël C. -W.
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914469007851520
author Wu, Zhuoyu
Ou, Wenhui
Tan, Pei-Sze
Fang, Wenqi
Rajanala, Sailaja
Phan, Raphaël C. -W.
author_facet Wu, Zhuoyu
Ou, Wenhui
Tan, Pei-Sze
Fang, Wenqi
Rajanala, Sailaja
Phan, Raphaël C. -W.
contents Retrieving procedure-oriented evidence from materials science papers is difficult because key synthesis details are often scattered across long, context-heavy documents and are not well captured by paragraph-only dense retrieval. We present RECIPER, a dual-view retrieval pipeline that indexes both paragraph-level context and compact large language model-extracted procedural summaries, then combines the two candidate streams with lightweight lexical reranking. Across four dense retrieval backbones, RECIPER consistently improves early-rank retrieval over paragraph-only dense retrieval, achieving average gains of +3.73 in Recall@1, +2.85 in nDCG@10, and +3.13 in MRR. With BGE-large-en-v1.5, it reaches 86.82%, 97.07%, and 97.85% on Recall@1, Recall@5, and Recall@10, respectively. We further observe improved downstream question answering under automatic metrics, suggesting that procedural summaries can serve as a useful complementary retrieval signal for procedure-oriented materials question answering. Code and data are available at https://github.com/ReaganWu/RECIPER.
format Preprint
id arxiv_https___arxiv_org_abs_2604_11229
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RECIPER: A Dual-View Retrieval Pipeline for Procedure-Oriented Materials Question Answering
Wu, Zhuoyu
Ou, Wenhui
Tan, Pei-Sze
Fang, Wenqi
Rajanala, Sailaja
Phan, Raphaël C. -W.
Signal Processing
Artificial Intelligence
Computation and Language
Retrieving procedure-oriented evidence from materials science papers is difficult because key synthesis details are often scattered across long, context-heavy documents and are not well captured by paragraph-only dense retrieval. We present RECIPER, a dual-view retrieval pipeline that indexes both paragraph-level context and compact large language model-extracted procedural summaries, then combines the two candidate streams with lightweight lexical reranking. Across four dense retrieval backbones, RECIPER consistently improves early-rank retrieval over paragraph-only dense retrieval, achieving average gains of +3.73 in Recall@1, +2.85 in nDCG@10, and +3.13 in MRR. With BGE-large-en-v1.5, it reaches 86.82%, 97.07%, and 97.85% on Recall@1, Recall@5, and Recall@10, respectively. We further observe improved downstream question answering under automatic metrics, suggesting that procedural summaries can serve as a useful complementary retrieval signal for procedure-oriented materials question answering. Code and data are available at https://github.com/ReaganWu/RECIPER.
title RECIPER: A Dual-View Retrieval Pipeline for Procedure-Oriented Materials Question Answering
topic Signal Processing
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2604.11229