{"slug": "ear-entity-aware-partitioning-approach-for-retrieval-augmented-generation", "title": "EAR: Entity-Aware Partitioning Approach for Retrieval-Augmented Generation Development", "summary": "Researchers introduced EAR, an Entity-Aware Partitioning approach for retrieval-augmented generation (RAG) that extracts normalized surface anchors from questions, answer options, and corpora to build compact retrieval units. Evaluated on a cleaned 153-question MMLU-style subset with Mistral, Gemma, and DeepSeek at top-k = 3 and top-k = 8, EAR's entity-window method reduced retrieved words by 37.5-40.2% relative to fixed-size chunks, with accuracy changes of +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 statistically significant. The authors describe the contribution as methodological, noting the rule-based anchor extractor remains domain-specific and requires separate validation before transfer.", "body_md": "arXiv:2609.12268v1 Announce Type: new \nAbstract: 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.", "url": "https://wpnews.pro/news/ear-entity-aware-partitioning-approach-for-retrieval-augmented-generation", "canonical_source": "https://arxiv.org/abs/2609.12268", "published_at": "2026-09-14 04:00:00+00:00", "updated_at": "2026-09-14 04:27:54.875652+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "natural-language-processing", "ai-research"], "entities": ["EAR", "Mistral", "Gemma", "DeepSeek", "MMLU", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/ear-entity-aware-partitioning-approach-for-retrieval-augmented-generation", "markdown": "https://wpnews.pro/news/ear-entity-aware-partitioning-approach-for-retrieval-augmented-generation.md", "text": "https://wpnews.pro/news/ear-entity-aware-partitioning-approach-for-retrieval-augmented-generation.txt", "jsonld": "https://wpnews.pro/news/ear-entity-aware-partitioning-approach-for-retrieval-augmented-generation.jsonld"}}