ArXiv TLDR

Fuheng Zhao

2 papers · Latest:

Information Retrieval

Dual-View Training for Instruction-Following Information Retrieval

This paper introduces a dual-view data synthesis method using polarity reversal to train instruction-following information retrieval systems, significantly improving performance.

2604.18845
Information Retrieval

Code-Switching Information Retrieval: Benchmarks, Analysis, and the Limits of Current Retrievers

This paper introduces new benchmarks (CSR-L, CS-MTEB) to show how code-switching severely degrades information retrieval performance, even for multilingual models.

2604.17632

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.