Picture for Jimmy Lin

Jimmy Lin

Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning

Add code
Mar 08, 2025
Viaarxiv icon

Teaching Dense Retrieval Models to Specialize with Listwise Distillation and LLM Data Augmentation

Add code
Feb 27, 2025
Viaarxiv icon

DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers

Add code
Feb 25, 2025
Viaarxiv icon

A Survey of Model Architectures in Information Retrieval

Add code
Feb 20, 2025
Viaarxiv icon

MMTEB: Massive Multilingual Text Embedding Benchmark

Add code
Feb 19, 2025
Viaarxiv icon

Illusions of Relevance: Using Content Injection Attacks to Deceive Retrievers, Rerankers, and LLM Judges

Add code
Jan 30, 2025
Figure 1 for Illusions of Relevance: Using Content Injection Attacks to Deceive Retrievers, Rerankers, and LLM Judges
Figure 2 for Illusions of Relevance: Using Content Injection Attacks to Deceive Retrievers, Rerankers, and LLM Judges
Figure 3 for Illusions of Relevance: Using Content Injection Attacks to Deceive Retrievers, Rerankers, and LLM Judges
Figure 4 for Illusions of Relevance: Using Content Injection Attacks to Deceive Retrievers, Rerankers, and LLM Judges
Viaarxiv icon

Document Screenshot Retrievers are Vulnerable to Pixel Poisoning Attacks

Add code
Jan 28, 2025
Viaarxiv icon

Musings About the Future of Search: A Return to the Past?

Add code
Dec 25, 2024
Viaarxiv icon

VISA: Retrieval Augmented Generation with Visual Source Attribution

Add code
Dec 19, 2024
Viaarxiv icon

CURE: A dataset for Clinical Understanding & Retrieval Evaluation

Add code
Dec 11, 2024
Viaarxiv icon