MULTI3IR: A Benchmark for Multi-perspective Multi-domain Multi-modal Information Retrieval

Hugging Face Daily Papers Papers

Summary

The paper introduces Multi3IR, a benchmark for multi-perspective, multi-domain, multi-modal information retrieval, and proposes SPIN, a method to improve perspective coverage in retrieval systems.

Information retrieval (IR) increasingly targets open-ended queries that admit diverse perspectives. Existing IR benchmarks, however, focus primarily on closed-ended queries, while even open-ended benchmarks largely consist of queries whose supporting documents span a single subject domain and modality. We introduce Multi^3IR, a benchmark that evaluates how well retrievers cover the multifaceted perspectives of open-ended queries across diverse domains and modalities. It comprises 104.9K Stack Exchange queries, each annotated with perspective descriptions that capture the query's implicit viewpoints. We further propose SPIN, a parameter- and label-efficient method that learns noise vectors to steer embeddings toward diverse yet meaningful semantic directions. Experiments show that existing multimodal retrievers suffer from single-perspective bias, while SPIN substantially improves perspective coverage on Multi^3IR and generalizes well to unseen open-ended IR benchmarks. The dataset and experimental code are available at https://github.com/seokwon99/Multi3IR.
Original Article
View Cached Full Text

Cached at: 09/03/26, 03:51 AM

Paper page - MULTI3IR: A Benchmark for Multi-perspective Multi-domain Multi-modal Information Retrieval

Source: https://huggingface.co/papers/2608.30949

Abstract

A new benchmark and steering method improve retrieval coverage of diverse perspectives across domains and modalities for open-ended queries.

Information retrieval (IR) increasingly targetsopen-ended queriesthat admit diverse perspectives. Existing IR benchmarks, however, focus primarily on closed-ended queries, while even open-ended benchmarks largely consist of queries whose supporting documents span a single subject domain and modality. We introduce Multi^3IR, a benchmark that evaluates how well retrievers cover the multifaceted perspectives ofopen-ended queriesacross diverse domains and modalities. It comprises 104.9K Stack Exchange queries, each annotated with perspective descriptions that capture the query’s implicit viewpoints. We further propose SPIN, a parameter- and label-efficient method that learnsnoise vectorsto steer embeddings toward diverse yet meaningful semantic directions. Experiments show that existingmultimodal retrieverssuffer fromsingle-perspective bias, while SPIN substantially improvesperspective coverageon Multi^3IR and generalizes well to unseen open-ended IR benchmarks. The dataset and experimental code are available at https://github.com/seokwon99/Multi3IR.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2608\.30949

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.30949 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.30949 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.30949 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles