Beyond RAG: Task-Aware KV Cache Compression for Comprehensive Knowledge Reasoning Paper β’ 2503.04973 β’ Published Mar 6 β’ 24
NevIR: Negation in Neural Information Retrieval Paper β’ 2305.07614 β’ Published May 12, 2023 β’ 1
MegaWika: Millions of reports and their sources across 50 diverse languages Paper β’ 2307.07049 β’ Published Jul 13, 2023
Defending Against Poisoning Attacks in Open-Domain Question Answering Paper β’ 2212.10002 β’ Published Dec 20, 2022
Learning to Reason via Program Generation, Emulation, and Search Paper β’ 2405.16337 β’ Published May 25, 2024
CLERC: A Dataset for Legal Case Retrieval and Retrieval-Augmented Analysis Generation Paper β’ 2406.17186 β’ Published Jun 24, 2024 β’ 2
Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models Paper β’ 2409.11136 β’ Published Sep 17, 2024 β’ 25
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference Paper β’ 2412.13663 β’ Published Dec 18, 2024 β’ 152
FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions Paper β’ 2403.15246 β’ Published Mar 22, 2024 β’ 11