paper-with-me

홈 › Papers

Retrieval Capabilities of Large Language Models Scale with Pretraining FLOPs

2025-08-24 · Jacob Portes, Connor Jennings, Erica Ji Yuen, Sasha Doubov, Michael Carbin arxiv

How does retrieval performance scale with pretraining FLOPs? We benchmark retrieval performance across LLM model sizes from 125 million parameters to 7 billion parameters pretrained on datasets ranging from 1 billion tokens to more than 2 trillion tokens. We find that retrieval performance on zero-shot BEIR tasks predictably scales with LLM size, training duration, and estimated FLOPs. We also show that In-Context Learning scores are strongly correlated with retrieval scores across retrieval tasks. Finally, we highlight the implications this has for the development of LLM-based retrievers.

📄 PDF Abstract BibTeX arXiv:2508.17400

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

SCOT: Self-Supervised Contrastive Pretraining For Zero-Shot Compositional Retrieval

2025-01-12 · WACV 2025 3 · Bhavin Jawade, Joao V. B. Soares, Kapil Thadani, Deen Dayal Mohan 외

Compositional image retrieval (CIR) is a multimodal learning task where a model combines a query image with a user-provided text modification to retrieve a target image. CIR finds applications in a variety of domains inc…

Image RetrievalRetrievalTripletZero-Shot Composed Image Retrieval (ZS-CIR)

To Memorize or to Retrieve: Scaling Laws for RAG-Considerate Pretraining

2026-04-01 · Karan Singh, Michael Yu, Varun Gangal, Zhuofu Tao 외 arxiv

Retrieval-augmented generation (RAG) improves language model (LM) performance by providing relevant context at test time for knowledge-intensive situations. However, the relationship between parametric knowledge acquired…

Pretraining De-Biased Language Model with Large-scale Click Logs for Document Ranking

2023-02-27 · Xiangsheng Li, Xiaoshu Chen, Kunliang Wei, Bin Hu 외

Pre-trained language models have achieved great success in various large-scale information retrieval tasks. However, most of pretraining tasks are based on counterfeit retrieval data where the query produced by the tailo…

Document RankingInformation RetrievalLanguage ModelingLanguage Modelling+1

Large Language Models as Foundations for Next-Gen Dense Retrieval: A Comprehensive Empirical Assessment

2024-08-22 · Kun Luo, Minghao Qin, Zheng Liu, Shitao Xiao 외

Pretrained language models like BERT and T5 serve as crucial backbone encoders for dense retrieval. However, these models often exhibit limited generalization capabilities and face challenges in improving in domain accur…

Multi-Task LearningRetrievalZero-shot Generalization

GLAP: General contrastive audio-text pretraining across domains and languages

2025-06-12 · Heinrich Dinkel, Zhiyong Yan, Tianzi Wang, Yongqing Wang 외

Contrastive Language Audio Pretraining (CLAP) is a widely-used method to bridge the gap between audio and text domains. Current CLAP methods enable sound and music retrieval in English, ignoring multilingual spoken conte…

AudioCapsKeyword SpottingRetrievalText Retrieval