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

Zhuoyu Wu; Wenhui Ou; Pei-Sze Tan; Wenqi Fang; Sailaja Rajanala; Raphaël C. -W. Phan

eess.SPApr 13, 2026

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

Authors: Zhuoyu Wu, Wenhui Ou, Pei-Sze Tan, Wenqi Fang, Sailaja Rajanala, Raphaël C. -W. Phan

Organizations: CyPhi (ΨΦ) AI Research Lab, School of IT, Monash University, Malaysia Campus · Department of Electronic & Computer Engineering, The Hong Kong University of Science and Technology · Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences

Abstract

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.

Figures & tables

Figure 1: Overview of RECIPER Framework. In this framework, the user query is first transformed into feature vectors, which are then used to retrieve the most relevant Paragraph and Recipe embedding vectors from the Chunk Vector Database . Recipe vectors pass through a Threshold Screener to filter out highly similar entries and increase content diversity. The filtered Recipes are then combined with the Paragraphs in a Rule-based Re-rank module and merged with the original query before being fed into the LLM, producing a precise, well-grounded answer.

Group	System	R@1	R@5	R@10	nDCG@10	MRR
External Paragraph Baselines	BM25 [ 10 ]	0.6172	0.8066	0.8477	0.7335	0.6967
	all-MiniLM-L6-v2 [ 17 ]	0.7432	0.9102	0.9307	0.8438	0.8150
	Contriever [ 5 ]	0.7793	0.9131	0.9375	0.8615	0.8367
	BGE-large-en-v1.5 [ 18 ]	0.8408	0.9512	0.9619	0.9061	0.8875
	E5-large-v2 [ 16 ]	0.8477	0.9561	0.9717	0.9136	0.8945
	BM25 + BGE-large-en-v1.5	0.7549	0.9443	0.9629	0.8665	0.8345

Table 1: Retrieval performance comparison and ablation study. The upper block reports paragraph-based baselines, while the lower block analyzes recipe-based and dual-view variants under the BGE backbone. Recipe-only retrieval is weak, but combining it with paragraph retrieval improves performance, showing that procedural and contextual signals are complementary. RECIPER achieves the best overall results, especially on early-rank metrics, indicating more effective integration of procedural and contextual evidence.

Backbone	vs Paragraph		vs Hybrid
Backbone	$\Delta$ R@1	$\Delta$ nDCG@10	$\Delta$ R@1	$\Delta$ nDCG@10
MiniLM	+0.0468	+0.0344	+0.0273	+0.0151
Contriever	+0.0361	+0.0332	+0.0263	+0.0186
BGE	+0.0274	+0.0223	+0.0196	+0.0102
E5	+0.0390	+0.0242	+0.0293	+0.0138
Average	+0.0373	+0.0285	+0.0256	+0.0144

Table 2: Cross-backbone improvement of RECIPER over paragraph-only dense retrieval and naive hybrid fusion. RECIPER consistently improves early-rank accuracy across all embedding backbones.

Model	M	BERT-F1	R-L	Cos	BLT
GPT-5 [ 8 ]	$\blacklozenge$	0.8612	0.2387	0.7745	0.3787
	$\bullet$	0.8552	0.2137	0.7592	0.3747
	$\star$	0.8465	0.2035	0.7350	0.3794
Deepseek-32B [ 4 ]	$\blacklozenge$	0.8662	0.2517	0.7379	0.3604
	$\bullet$	0.8646	0.2428	0.7430	0.3555
	$\star$	0.8520	0.1945	0.7030	0.3366

Table 3: Overall QA performance across models and retrieval modes. Symbols indicate retrieval mode:

\blacklozenge

RECIPER,

\bullet

Paragraph-Dense RAG,

\star

NoRAG. Metrics are BERT-F1 (F1 score of BERTScore), R-L (ROUGE-L), Cos (Cosine similarity), and BLT (BLEURT). The best value per metric is highlighted with a yellow block and in bold font.

Evidence Retrieval

Evidence retrieval finds and organizes source-grounded information to answer questions, verify claims, and support decisions.

See all 156 papers

ProvMind: Provenance-grounded reasoning for materials synthesis
May 27, 2026Yiming Zhang, Ryo Tamura, Koji TsudaReasoning Evaluation Materials Science
Graduate School of Frontier Sciences, The University of Tokyo, Chiba, Japan. · Center for Basic Research on Materials, National Institute for Materials Science, Tsukuba, Ibaraki, Japan. · RIKEN Center for Advanced Intelligence Project, Tokyo, Japan.
Benchmark for Structured Retrieval-Augmented Generation in Perovskite Photovoltaics
Oct 18, 2026Qiwei Han, Chi Zhou, Gaoxiang YuanStructured RAG RAG Evaluation
Department of Chemistry, Duke University, Durham, NC 27708, USA · Department of Computer Science, Georgia Institute of Technology, Atlanta, GA 30332, USA · Department of Electrical and Computer Engineering, Tandon School of Engineering, New York University, Brooklyn, NY 11201, USA
Lit3R: Retrieve-Relate-Read for Evidence-Grounded Question Answering over Scientific Literature
Sep 15, 2026Akira Ise, Kotaro Kumagai, Yuta Yamaguchi +3Scientific QA Evidence-Grounded Generation
♠Tokyo University of Science · ♣Dentsu Soken Inc. · ♡Studio Ousia

May 27, 2026J/K move · Enter open · S save

ProvMind: Provenance-grounded reasoning for materials synthesis

Yiming Zhang, Ryo Tamura, Koji Tsuda

Graduate School of Frontier Sciences, The University of Tokyo, Chiba, Japan. · Center for Basic Research on Materials, National Institute for Materials Science, Tsukuba, Ibaraki, Japan. · RIKEN Center for Advanced Intelligence Project, Tokyo, Japan.

Reasoning Evaluation Materials Science Structured Reasoning LLM Reasoning

Open paper AskPDF arXiv

Materials process optimization requires reasoning over routes, conditions, tools and causal dependencies, yet most computational formulations flatten synthesis procedures into text or ordered steps. We introduce MatProcBench, a provenance-grounded benchmark constructed from literature-mined MatPROV graphs, to evaluate seven process-reasoning tasks spanning route continuity, step-level variable inference and global causal consistency under both same-split and shift-aware evaluation, including a strict dual-OOD split that combines temporal and material-class shift. We further introduce ProvMind, a process-memory reasoning framework that retrieves analogous training processes, converts them into provenance-aware option-level compatibility scores, and uses a language model for constrained final decision making. ProvMind achieves 52.84% accuracy on the dual-OOD split, outperforming prompting, retrieval-augmented and supervised fine-tuning baselines.

Abstract

Evidence Retrieval

Explore similar work

ProvMind: Provenance-grounded reasoning for materials synthesis

Benchmark for Structured Retrieval-Augmented Generation in Perovskite Photovoltaics

Lit3R: Retrieve-Relate-Read for Evidence-Grounded Question Answering over Scientific Literature