Semantic Search for Information Retrieval

2025/08/25 by Farivar, Kayla
#FOS: Computer and information sciences #Information Retrieval (cs.IR)

paper · doi:10.48550/arxiv.2508.17694

Abstract

Information retrieval systems have progressed notably from lexical techniques such as BM25 and TF-IDF to modern semantic retrievers. This survey provides a brief overview of the BM25 baseline, then discusses the architecture of modern state-of-the-art semantic retrievers. Advancing from BERT, we introduce dense bi-encoders (DPR), late-interaction models (ColBERT), and neural sparse retrieval (SPLADE). Finally, we examine MonoT5, a cross-encoder model. We conclude with common evaluation tactics, pressing challenges, and propositions for future directions.

Citations

• Large Dual Encoders Are Generalizable Retrievers
• ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction
• SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking
• MS MARCO: Benchmarking Ranking Models in the Large-Data Regime
• BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models
• Pretrained Transformers for Text Ranking: BERT and Beyond
• Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
• Dense Passage Retrieval for Open-Domain Question Answering
• Document Ranking with a Pretrained Sequence-to-Sequence Model
• DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
• Latent Retrieval for Weakly Supervised Open Domain Question Answering
• MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
• Efficient Estimation of Word Representations in Vector Space
• Term-weighting approaches in automatic text retrieval
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Related

• BMX: Entropy-weighted Similarity and Semantic-enhanced Lexical Search
• A Survey of Model Architectures in Information Retrieval
• Utilizing BERT for Information Retrieval: Survey, Applications, Resources, and Challenges
• Exploring new Approaches for Information Retrieval through Natural Language Processing
• BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models