# A Thorough Comparison of Cross-Encoders and LLMs for Reranking SPLADE

arXiv: https://arxiv.org/abs/2403.10407 · HTML: https://mlsanity.com/paper/2403.10407/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Mar 2024.

## Built on by (most cited first, 18 of 18)

- [JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking](https://mlsanity.com/paper/2411.00142/) (2024)
- [jina-reranker-v3: Last but Not Late Interaction for Listwise Document Reranking](https://mlsanity.com/paper/2509.25085/) (2025)
- [FinSage: A Multi-aspect RAG System for Financial Filings Question Answering](https://mlsanity.com/paper/2504.14493/) (2025)
- [Classifying and Addressing the Diversity of Errors in Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2510.13975/) (2025)
- [DiSCo: LLM Knowledge Distillation for Efficient Sparse Retrieval in Conversational Search](https://mlsanity.com/paper/2410.14609/) (2024)
- [AIC CTU system at AVeriTeC: Re-framing automated fact-checking as a simple RAG task](https://mlsanity.com/paper/2410.11446/) (2024)
- [RAG-based Question Answering over Heterogeneous Data and Text](https://mlsanity.com/paper/2412.07420/) (2024)
- [Learning Retrieval Models with Sparse Autoencoders](https://mlsanity.com/paper/2603.13277/) (2026)
- [RAGSmith: A Framework for Finding the Optimal Composition of Retrieval-Augmented Generation Methods Across Datasets](https://mlsanity.com/paper/2511.01386/) (2025)
- [Is Agentic RAG worth it? An experimental comparison of RAG approaches](https://mlsanity.com/paper/2601.07711/) (2026)
- [CHORUS: Zero-shot Hierarchical Retrieval and Orchestration for Generating Linear Programming Code](https://mlsanity.com/paper/2505.01485/) (2025)
- [Recursive Question Understanding for Complex Question Answering over Heterogeneous Personal Data](https://mlsanity.com/paper/2505.11900/) (2025)
- [Multilingual vs Crosslingual Retrieval of Fact-Checked Claims: A Tale of Two Approaches](https://mlsanity.com/paper/2505.22118/) (2025)
- [Less can be More: Relieving RAG Bottlenecks via Evidence Frontloading and Pressure-Adaptive Budgeting](https://mlsanity.com/paper/2608.25115/) (2026)
- [Blending Learning to Rank and Dense Representations for Efficient and Effective Cascades](https://mlsanity.com/paper/2510.16393/) (2025)
- [Learning to Retrieve with Weakened Labels: Robust Training under Label Noise](https://mlsanity.com/paper/2512.13237/) (2025)
- [Comparative Analysis of Neural Retriever-Reranker Pipelines for Retrieval-Augmented Generation over Knowledge Graphs in E-commerce Applications](https://mlsanity.com/paper/2602.22219/) (2025)
- [AutoRelAnnotator: Calibrated Model Cascades for Cost-Efficient Relevance Evaluation in Sponsored Search](https://mlsanity.com/paper/2606.25871/) (2026)

## Abstract (arXiv)

We present a comparative study between cross-encoder and LLMs rerankers in the context of re-ranking effective SPLADE retrievers. We conduct a large evaluation on TREC Deep Learning datasets and out-of-domain datasets such as BEIR and LoTTE. In the first set of experiments, we show how cross-encoder rerankers are hard to distinguish when it comes to re-rerank SPLADE on MS MARCO. Observations shift in the out-of-domain scenario, where both the type of model and the number of documents to re-rank have an impact on effectiveness. Then, we focus on listwise rerankers based on Large Language Models -- especially GPT-4. While GPT-4 demonstrates impressive (zero-shot) performance, we show that traditional cross-encoders remain very competitive. Overall, our findings aim to to provide a more nuanced perspective on the recent excitement surrounding LLM-based re-rankers -- by positioning them as another factor to consider in balancing effectiveness and efficiency in search systems.