aiqbench analysis
This research introduces EAR, a methodological improvement for Retrieval-Augmented Generation that optimizes corpus partitioning by using entity-aware anchors rather than fixed-size chunks. While the approach significantly reduces retrieved text volume, experimental results show mixed accuracy gains across different models with no statistically significant difference in overall performance. The study highlights critical trade-offs between retrieval efficiency and answer correctness, offering a more inspectable unit for knowledge-intensive question answering tasks.
EAR: Entity-Aware Partitioning Approach for Retrieval-Augmented Generation Development
arXiv:2609.12268v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) can improve knowledge-intensive question answering, but the first design choice is easy to overlook: how should the source corpus be partitioned into retrievable units? Fixed-size chunks often return long passages whose relation to the question is only implicit. We introduce EAR, an Entity-Aware Partitioning approach for multiple-choice question answering (MCQA). EAR extracts normalized surface anchors from the question, answer options, and corpus; retrieves local windows around matching corpus anchors; and can attach a larger parent passage through an extractive summary. We evaluate EAR on a cleaned Massive Multitask Language Understanding (MMLU)-style subset of 153 questions selected by an automatic corpus-support heuristic and using decontaminated public textbook text. Across same-protocol top-k = 3 and top-k = 8 sweeps with Mistral, Gemma, and DeepSeek, EAR entity-window reduces retrieved words by 37.5-40.2% relative to chunks. Observed accuracy changes are +5.2, +1.3, and -3.9 points at top-k = 3, and +5.9, -3.3, and -4.6 points at top-k = 8; none of the entity-window differences is statistically significant. The scoped contribution is methodological: EAR provides a compact and inspectable retrieval unit, while its rule-based anchor extractor remains domain-specific and requires separate validation before transfer.
Abstract:Retrieval-augmented generation (RAG) can improve knowledge-intensive question answering, but the first design choice is easy to overlook: how should the source corpus be partitioned into retrievable units? Fixed-size chunks often return long passages whose relation to the question is only implicit. We introduce EAR, an Entity-Aware Partitioning approach for multiple-choice question answering (MCQA). EAR extracts normalized surface anchors from the question, answer options, and corpus; retrieves local windows around matching corpus anchors; and can attach a larger parent passage through an extractive summary. We evaluate EAR on a cleaned Massive Multitask Language Understanding (MMLU)-style subset of 153 questions selected by an automatic corpus-support heuristic and using decontaminated public textbook text. Across same-protocol top-k = 3 and top-k = 8 sweeps with Mistral, Gemma, and DeepSeek, EAR entity-window reduces retrieved words by 37.5-40.2% relative to chunks. Observed accuracy changes are +5.2, +1.3, and -3.9 points at top-k = 3, and +5.9, -3.3, and -4.6 points at top-k = 8; none of the entity-window differences is statistically significant. The scoped contribution is methodological: EAR provides a compact and inspectable retrieval unit, while its rule-based anchor extractor remains domain-specific and requires separate validation before transfer.
6 pages. Accepted and presented at the 2026 Innovations in Intelligent Systems and Applications Conference (ASYU 2026). To appear in the conference proceedings and IEEE Xplore
Computation and Language (cs.CL); Information Retrieval (cs.IR)
arXiv:2609.12268 [cs.CL]
(or arXiv:2609.12268v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2609.12268 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 240 words
Related coverage
A Unified Framework for Context-Aware and Relation-Aware Graph Retrieval-Augmented Generation
arXiv · Jun 17, 2026
Improving Health Literacy through Lay Summarization of Radiological Reports: An Evaluation of BioNER and Retrieval-Augmented Generation
arXiv · Sep 3, 2026
J++ Lens: Jacobian Filtering Enables More Faithful Workspace Lenses
LessWrong · Oct 8, 2026
Corpus-Guided Dual-Path Propagation for Graph Retrieval-Augmented Generation
arXiv · Oct 1, 2026