IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information Retrieval

North American Chapter of the Association for Computational Linguistics (NAACL), 2025

6 March 2025

ArXiv (abs)PDF HTML HuggingFace (21 upvotes)Github (6★)

Papers citing "IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information Retrieval"

9 / 9 papers shown

LimRank: Less is More for Reasoning-Intensive Information Reranking

427

27 Oct 2025

ReasonIF: Large Reasoning Models Fail to Follow Instructions During Reasoning

208

17 Oct 2025

On the Theoretical Limitations of Embedding-Based Retrieval

271

28 Aug 2025

Towards Better Instruction Following Retrieval Models

543

27 May 2025

Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective

268

21 May 2025

Rank1: Test-Time Compute for Reranking in Information Retrieval

429

25 Feb 2025

mFollowIR: a Multilingual Benchmark for Instruction Following in RetrievalEuropean Conference on Information Retrieval (ECIR), 2025

317

31 Jan 2025

LLMs are Also Effective Embedding Models: An In-depth Overview

550

17 Dec 2024

NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models

Mengyao Xu

875

466

27 May 2024