paper-with-me

홈 › Papers

State Space Models are Strong Text Rerankers

2024-12-18 · Zhichao Xu, Jinghua Yan, Ashim Gupta, Vivek Srikumar

Transformers dominate NLP and IR; but their inference inefficiencies and challenges in extrapolating to longer contexts have sparked interest in alternative model architectures. Among these, state space models (SSMs) like Mamba offer promising advantages, particularly $O(1)$ time complexity in inference. Despite their potential, SSMs' effectiveness at text reranking -- a task requiring fine-grained query-document interaction and long-context understanding -- remains underexplored. This study benchmarks SSM-based architectures (specifically, Mamba-1 and Mamba-2) against transformer-based models across various scales, architectures, and pre-training objectives, focusing on performance and efficiency in text reranking tasks. We find that (1) Mamba architectures achieve competitive text ranking performance, comparable to transformer-based models of similar size; (2) they are less efficient in training and inference compared to transformers with flash attention; and (3) Mamba-2 outperforms Mamba-1 in both performance and efficiency. These results underscore the potential of state space models as a transformer alternative and highlight areas for improvement in future IR applications.

📄 PDF Abstract BibTeX arXiv:2412.14354

Code (0)

등록된 구현이 없습니다.

Tasks

Long-Context UnderstandingMambaRerankingState Space ModelsText Reranking

Methods 이 논문이 사용한 방법론

Mamba Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module.…

Similar Papers 제목 키워드 기반

BTZSC: A Benchmark for Zero-Shot Text Classification Across Cross-Encoders, Embedding Models, Rerankers and LLMs

2026-03-12 · Ilias Aarab arxiv

Zero-shot text classification (ZSC) offers the promise of eliminating costly task-specific annotation by matching texts directly to human-readable label descriptions. While early approaches have predominantly relied on c…

Natural Language InferenceEmotion ClassificationText Classification

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

Distillation versus Contrastive Learning: How to Train Your Rerankers

2025-07-11 · Zhichao Xu, Zhiqi Huang, Shengyao Zhuang, Vivek Srikumar arxiv

Training effective text rerankers is crucial for information retrieval. Two strategies are widely used: contrastive learning (optimizing directly on ground-truth labels) and knowledge distillation (transferring knowledge…

Knowledge DistillationInformation RetrievalContrastive Learning

Efficiency-Effectiveness Reranking FLOPs for LLM-based Rerankers

2025-07-08 · Zhiyuan Peng, Ting-Ruen Wei, Tingyu Song, Yilun Zhao 외

Large Language Models (LLMs) have recently been applied to reranking tasks in information retrieval, achieving strong performance. However, their high computational demands often hinder practical deployment. Existing stu…

Information RetrievalReranking

Rethink Training of BERT Rerankers in Multi-Stage Retrieval Pipeline

2021-01-21 · Luyu Gao, Zhuyun Dai, Jamie Callan

Pre-trained deep language models~(LM) have advanced the state-of-the-art of text retrieval. Rerankers fine-tuned from deep LM estimates candidate relevance based on rich contextualized matching signals. Meanwhile, deep L…

RetrievalText Retrieval