Information Retrieval (cs.IR)

Apr 22, 2026Formal Sciences260423.0011

Coverage, Not Averages: Semantic Stratification for Trustworthy Retrieval Evaluation

Andrew Klearman, Radu Revutchi, Rohin Garg, Rishav Chakravarti +2 more

This paper proposes semantic stratification, a structured evaluation framework for retrieval systems that organizes documents into entity-based clusters and systematically generates queries to ensure comprehensive coverage. It addresses hidden biases in current heuristic evaluation approaches and provides formal guarantees for more trustworthy retrieval assessment.

Apr 22, 2026Formal Sciences260423.0030

Self-Aware Vector Embeddings for Retrieval-Augmented Generation: A Neuroscience-Inspired Framework for Temporal, Confidence-Weighted, and Relational Knowledge

Naizhong Xu

SmartVector augments vector embeddings with temporal awareness, confidence decay, and relational properties to improve retrieval-augmented generation accuracy on versioned knowledge. The framework doubles accuracy on versioned queries and reduces stale answers by 62% compared to standard cosine similarity retrieval.

Apr 20, 2026Formal Sciences260421.0078

Balanced Co-Clustering of Users and Items for Embedding Table Compression in Recommender Systems

Runhao Jiang, Renchi Yang, Donghao Wu

BACO is a framework that compresses embedding tables in recommender systems by clustering similar users and items to share embeddings, achieving over 75% parameter reduction with minimal accuracy loss. It outperforms existing methods by being up to 346X faster while maintaining recommendation quality.

Information Retrieval

Latest in cs.IR

Coverage, Not Averages: Semantic Stratification for Trustworthy Retrieval Evaluation

Self-Aware Vector Embeddings for Retrieval-Augmented Generation: A Neuroscience-Inspired Framework for Temporal, Confidence-Weighted, and Relational Knowledge

Balanced Co-Clustering of Users and Items for Embedding Table Compression in Recommender Systems

Follow