Papers
arxiv:2401.06532

INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning

Published on Jan 12
Authors:
,
,
,

Abstract

Large language models (LLMs) have demonstrated impressive capabilities in various natural language processing tasks. Despite this, their application to information retrieval (IR) tasks is still challenging due to the infrequent occurrence of many IR-specific concepts in natural language. While prompt-based methods can provide task descriptions to LLMs, they often fall short in facilitating comprehensive understanding and execution of IR tasks, thereby limiting LLMs' applicability. To address this gap, in this work, we explore the potential of instruction tuning to enhance LLMs' proficiency in IR tasks. We introduce a novel instruction tuning dataset, INTERS, encompassing 21 tasks across three fundamental IR categories: query understanding, document understanding, and query-document relationship understanding. The data are derived from 43 distinct datasets with manually written templates. Our empirical results reveal that INTERS significantly boosts the performance of various publicly available LLMs, such as LLaMA, Mistral, and Phi, in search-related tasks. Furthermore, we conduct a comprehensive analysis to ascertain the effects of base model selection, instruction design, volume of instructions, and task variety on performance. We make our dataset and the models fine-tuned on it publicly accessible at https://github.com/DaoD/INTERS.

Community

I love this! Ive felt for quite a while that we use models for RAG without properly training them for common RAG tasks. Thanks for addressing this @yutaozhu94 !

@yutaozhu94 would you consider adding the dataset to the hub?

https://github.com/DaoD/INTERS

cc @davanstrien

Any updates on the dataset? @yutaozhu94 ? The Github repo is still largely empty.

@HanLee

⭐ We will release the datasets, models, templates, and codes within a month (before Feb. 15th). Thanks for your attention!

Lets hope it works out!

@librarian-bot recommend

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Paper author

@HanLee @derek-thomas Hey, thanks for your interest in our study. The dataset and fine-tuned models have been released. Feel free to contact us if there is any feedback!

Sign up or log in to comment

Models citing this paper 5

Browse 5 models citing this paper

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2401.06532 in a Space README.md to link it from this page.

Collections including this paper 3