Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond Paper • 2503.10460 • Published 24 days ago • 27
CoRe^2: Collect, Reflect and Refine to Generate Better and Faster Paper • 2503.09662 • Published 25 days ago • 33
CompAct: Compressing Retrieved Documents Actively for Question Answering Paper • 2407.09014 • Published Jul 12, 2024 • 1
IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information Retrieval Paper • 2503.04644 • Published Mar 6 • 20
Does Time Have Its Place? Temporal Heads: Where Language Models Recall Time-specific Information Paper • 2502.14258 • Published Feb 20 • 26
Does Time Have Its Place? Temporal Heads: Where Language Models Recall Time-specific Information Paper • 2502.14258 • Published Feb 20 • 26
Does Time Have Its Place? Temporal Heads: Where Language Models Recall Time-specific Information Paper • 2502.14258 • Published Feb 20 • 26 • 2
System Message Generation for User Preferences using Open-Source Models Paper • 2502.11330 • Published Feb 17 • 15
Improving Medical Reasoning through Retrieval and Self-Reflection with Retrieval-Augmented Large Language Models Paper • 2401.15269 • Published Jan 27, 2024 • 1
Improving Medical Reasoning through Retrieval and Self-Reflection with Retrieval-Augmented Large Language Models Paper • 2401.15269 • Published Jan 27, 2024 • 1
System Message Generation for User Preferences using Open-Source Models Paper • 2502.11330 • Published Feb 17 • 15
System Message Generation for User Preferences using Open-Source Models Paper • 2502.11330 • Published Feb 17 • 15 • 2
Minbyul/selfbiorag-7b-1e-6-wo-kqa_silver_wogold-iter-sft-step1_lr Text Generation • Updated Aug 1, 2024 • 4
Minbyul/biomistral-7b-1e-6-wo-kqa_silver_wogold-iter-sft-step1_lr Text Generation • Updated Aug 1, 2024 • 5