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

arXiv:2604.11229v1 Announce Type: cross 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.

Related

• Scalable High-Recall Constraint-Satisfaction-Based Information Retrieval for Clinical Trials Matching
• MultiDocFusion: Hierarchical and Multimodal Chunking Pipeline for Enhanced RAG on Long Industrial Documents
• Regime-Conditional Retrieval: Theory and a Transferable Router for Two-Hop QA
• RecaLLM: Addressing the Lost-in-Thought Phenomenon with Explicit In-Context Retrieval
• Uncertainty-Aware Web-Conditioned Scientific Fact-Checking

Source: arXiv cs.AI | 2026-04-14