# Are LLM-Based Retrievers Worth Their Cost? An Empirical Study of Efficiency, Robustness, and Reasoning Overhead

arXiv: https://arxiv.org/abs/2604.03676 · HTML: https://mlsanity.com/paper/2604.03676/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 24 of its 54 references that are in the map.
- First posted on arXiv 4 Apr 2026.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 24 of 24)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [Promptagator: Few-shot Dense Retrieval From 8 Examples](https://mlsanity.com/paper/2209.11755/) (2022)
- [BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval](https://mlsanity.com/paper/2407.12883/) (2024)
- [SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval](https://mlsanity.com/paper/2109.10086/) (2021)
- [COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List](https://mlsanity.com/paper/2104.07186/) (2021)
- [ReasonIR: Training Retrievers for Reasoning Tasks](https://mlsanity.com/paper/2504.20595/) (2025)
- [RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation](https://mlsanity.com/paper/2403.05313/) (2024)
- [InPars: Data Augmentation for Information Retrieval using Large Language Models](https://mlsanity.com/paper/2202.05144/) (2022)
- [DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval](https://mlsanity.com/paper/2508.07995/) (2025)
- [On the Calibration and Uncertainty of Neural Learning to Rank Models](https://mlsanity.com/paper/2101.04356/) (2021)
- [Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation](https://mlsanity.com/paper/2502.02464/) (2025)
- [DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillation](https://mlsanity.com/paper/2508.16998/) (2025)
- [MM-BRIGHT: A Multi-Task Multimodal Benchmark for Reasoning-Intensive Retrieval](https://mlsanity.com/paper/2601.09562/) (2026)
- [DAT: Dynamic Alpha Tuning for Hybrid Retrieval in Retrieval-Augmented Generation](https://mlsanity.com/paper/2503.23013/) (2025)
- [RECOR: Reasoning-focused Multi-turn Conversational Retrieval Benchmark](https://mlsanity.com/paper/2601.05461/) (2026)
- [TEMPO: A Realistic Multi-Domain Benchmark for Temporal Reasoning-Intensive Retrieval](https://mlsanity.com/paper/2601.09523/) (2026)
- [Aligned Query Expansion: Efficient Query Expansion for Information Retrieval through LLM Alignment](https://mlsanity.com/paper/2507.11042/) (2025)

## Built on by (most cited first, 4 of 4)

- [Argus-Retriever: Vision-LLM Late-Interaction Retrieval with Region-Aware Query-Conditioned MoE for Visual Document Retrieval](https://mlsanity.com/paper/2606.04300/) (2026)
- [Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems](https://mlsanity.com/paper/2605.04018/) (2026)
- [Annotated Surrogate Retrieval for Polish Statutory Law](https://mlsanity.com/paper/2608.30929/) (2026)
- [Mixture-of-Experts Language Models Can Be Strong and Efficient Retrievers](https://mlsanity.com/paper/2609.13486/) (2026)

## Abstract (arXiv)

Large language model retrievers improve performance on complex queries, but their practical value depends on efficiency, robustness, and reliable confidence signals in addition to accuracy. We reproduce a reasoning-intensive retrieval benchmark (BRIGHT) across 12 tasks and 14 retrievers, and extend evaluation with cold-start indexing cost, query latency distributions and throughput, corpus scaling, robustness to controlled query perturbations, and confidence use (AUROC) for predicting query success. We also quantify reasoning overhead by comparing standard queries to five provided reasoning-augmented variants, measuring accuracy gains relative to added latency. We find that some reasoning-specialized retrievers achieve strong effectiveness while remaining competitive in throughput, whereas several large LLM-based bi-encoders incur substantial latency for modest gains. Reasoning augmentation incurs minimal latency for sub-1B encoders but exhibits diminishing returns for top retrievers and may reduce performance on formal math/code domains. Confidence calibration is consistently weak across model families, indicating that raw retrieval scores are unreliable for downstream routing without additional calibration. We release all code and artifacts for reproducibility.