paper-with-me

Papers

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

2024-03-15 · Hervé Déjean, Stéphane Clinchant, Thibault Formal

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.

📄 PDF Abstract BibTeX arXiv:2403.10407

Code (0)

등록된 구현이 없습니다.

Tasks

RerankingRe-Ranking

Methods 이 논문이 사용한 방법론

Attention 설명 없음
SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Multi-Head Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

The Evolution of Reranking Models in Information Retrieval: From Heuristic Methods to Large Language Models

2025-12-18 · Tejul Pandit, Sakshi Mahendru, Meet Raval, Dhvani Upadhyay arxiv

Reranking is a critical stage in contemporary information retrieval (IR) systems, improving the relevance of the user-presented final results by honing initial candidate sets. This paper is a thorough guide to examine th…

Knowledge DistillationInformation Retrieval

Evaluating Large Language Models for Cross-Lingual Retrieval

2025-09-18 · Longfei Zuo, Pingjun Hong, Oliver Kraus, Barbara Plank 외 arxiv

Multi-stage information retrieval (IR) has become a widely-adopted paradigm in search. While Large Language Models (LLMs) have been extensively evaluated as second-stage reranking models for monolingual IR, a systematic …

Information RetrievalMachine Translation

Self-Calibrated Listwise Reranking with Large Language Models

2024-11-07 · Ruiyang Ren, Yuhao Wang, Kun Zhou, Wayne Xin Zhao 외

Large language models (LLMs), with advanced linguistic capabilities, have been employed in reranking tasks through a sequence-to-sequence approach. In this paradigm, multiple passages are reranked in a listwise manner an…

Reranking

Supervised Fine-Tuning or Contrastive Learning? Towards Better Multimodal LLM Reranking

2025-10-16 · Ziqi Dai, Xin Zhang, Mingxin Li, Yanzhao Zhang 외 arxiv

In information retrieval, training reranking models mainly focuses on two types of objectives: metric learning (e.g. contrastive loss to increase the predicted scores on relevant query-document pairs) and classification …

Information RetrievalContrastive LearningMetric Learning

FreeRet: MLLMs as Training-Free Retrievers

2025-09-29 · Yuhan Zhu, Xiangyu Zeng, Chenting Wang, Xinhao Li 외 arxiv

Multimodal large language models (MLLMs) are emerging as versatile foundations for mixed-modality retrieval. Yet, they often require heavy post-hoc training to convert them into contrastive encoders for retrieval. This w…