paper-with-me

홈 › Papers

Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models

2024-09-17 · Orion Weller, Benjamin Van Durme, Dawn Lawrie, Ashwin Paranjape, Yuhao Zhang, Jack Hessel

Instruction-tuned language models (LM) are able to respond to imperative commands, providing a more natural user interface compared to their base counterparts. In this work, we present Promptriever, the first retrieval model able to be prompted like an LM. To train Promptriever, we curate and release a new instance-level instruction training set from MS MARCO, spanning nearly 500k instances. Promptriever not only achieves strong performance on standard retrieval tasks, but also follows instructions. We observe: (1) large gains (reaching SoTA) on following detailed relevance instructions (+14.3 p-MRR / +3.1 nDCG on FollowIR), (2) significantly increased robustness to lexical choices/phrasing in the query+instruction (+12.9 Robustness@10 on InstructIR), and (3) the ability to perform hyperparameter search via prompting to reliably improve retrieval performance (+1.4 average increase on BEIR). Promptriever demonstrates that retrieval models can be controlled with prompts on a per-query basis, setting the stage for future work aligning LM prompting techniques with information retrieval.

📄 PDF Abstract BibTeX arXiv:2409.11136

Code (1)

orionw/promptriever 공식 구현

Tasks

Information RetrievalRetrieval

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
BASE 설명 없음

Similar Papers 제목 키워드 기반

INSTRUCTIR: A Benchmark for Instruction Following of Information Retrieval Models

2024-02-22 · Hanseok Oh, Hyunji Lee, Seonghyeon Ye, Haebin Shin 외

Despite the critical need to align search targets with users' intention, retrievers often only prioritize query information without delving into the users' intended search context. Enhancing the capability of retrievers …

Information RetrievalInstruction FollowingLanguage ModelingLanguage Modelling+1

mFollowIR: a Multilingual Benchmark for Instruction Following in Retrieval

2025-01-31 · Orion Weller, Benjamin Chang, Eugene Yang, Mahsa Yarmohammadi 외

Retrieval systems generally focus on web-style queries that are short and underspecified. However, advances in language models have facilitated the nascent rise of retrieval models that can understand more complex querie…

Instruction FollowingRetrieval

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

STORM: Stepwise Token Optimization with Reward-Guided Beam Search

2026-06-09 · Arthur Satouf, Giulio D'Erasmo, Yuxuan Zong, Habiboulaye Amadou Boubacar 외 arxiv

Modern retrieval increasingly relies on dense and learned-sparse neural models that are effective but require encoding the entire corpus into a specialized index, rebuilt whenever the model changes. Lexical retrievers li…

SAGE: Benchmarking and Improving Retrieval for Deep Research Agents

2026-02-05 · Tiansheng Hu, Yilun Zhao, Canyu Zhang, Arman Cohan 외 arxiv

Deep research agents have emerged as powerful systems for addressing complex queries. Meanwhile, LLM-based retrievers have demonstrated strong capability in following instructions or reasoning. This raises a critical que…