mlsanityData to 14 Oct 2026

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

arXiv 2403.10407 ↗First posted 15 Mar 2024cs.IRcited by 18

Not on the map. Why?

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.

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

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 10; 2026: 4.

18 papers.

Sort:

By area:

  1. 2024JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Rerankingcited by 34
  2. 2025jina-reranker-v3: Last but Not Late Interaction for Listwise Document Rerankingcited by 24
  3. 2025FinSage: A Multi-aspect RAG System for Financial Filings Question Answeringcited by 19
  4. 2025Classifying and Addressing the Diversity of Errors in Retrieval-Augmented Generation Systemscited by 10
  5. 2024DiSCo: LLM Knowledge Distillation for Efficient Sparse Retrieval in Conversational Searchcited by 9
  6. 2024AIC CTU system at AVeriTeC: Re-framing automated fact-checking as a simple RAG taskcited by 8
  7. 2024RAG-based Question Answering over Heterogeneous Data and Textcited by 7
  8. 2026Learning Retrieval Models with Sparse Autoencoderscited by 6
  9. 2025RAGSmith: A Framework for Finding the Optimal Composition of Retrieval-Augmented Generation Methods Across Datasetscited by 5
  10. 2026Is Agentic RAG worth it? An experimental comparison of RAG approachescited by 5
  11. 2025CHORUS: Zero-shot Hierarchical Retrieval and Orchestration for Generating Linear Programming Codecited by 3
  12. 2025Recursive Question Understanding for Complex Question Answering over Heterogeneous Personal Datacited by 1
6 more
  1. 2025Multilingual vs Crosslingual Retrieval of Fact-Checked Claims: A Tale of Two Approachescited by 1
  2. 2026Less can be More: Relieving RAG Bottlenecks via Evidence Frontloading and Pressure-Adaptive Budgetingcited by 1
  3. 2025Blending Learning to Rank and Dense Representations for Efficient and Effective Cascadescited by 0
  4. 2025Learning to Retrieve with Weakened Labels: Robust Training under Label Noisecited by 0
  5. 2025Comparative Analysis of Neural Retriever-Reranker Pipelines for Retrieval-Augmented Generation over Knowledge Graphs in E-commerce Applicationscited by 0
  6. 2026AutoRelAnnotator: Calibrated Model Cascades for Cost-Efficient Relevance Evaluation in Sponsored Searchcited by 0