Societal Alignment Frameworks Can Improve LLM Alignment Paper • 2503.00069 • Published 10 days ago • 16
How to Get Your LLM to Generate Challenging Problems for Evaluation Paper • 2502.14678 • Published 17 days ago • 16
CHASE Collection Generate challenging synthetic data to evaluate LLMs • 5 items • Updated 16 days ago • 4
view article Article Train 400x faster Static Embedding Models with Sentence Transformers Jan 15 • 156
VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment Paper • 2410.01679 • Published Oct 2, 2024 • 25
BM25S: Orders of magnitude faster lexical search via eager sparse scoring Paper • 2407.03618 • Published Jul 4, 2024 • 12
Learning Action and Reasoning-Centric Image Editing from Videos and Simulations Paper • 2407.03471 • Published Jul 3, 2024 • 31
AURORA Collection Repository: https://github.com/McGill-NLP/AURORA • 5 items • Updated Jul 9, 2024 • 4
LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders Paper • 2404.05961 • Published Apr 9, 2024 • 65
Improving Text-to-Image Consistency via Automatic Prompt Optimization Paper • 2403.17804 • Published Mar 26, 2024 • 18
Improving Automatic VQA Evaluation Using Large Language Models Paper • 2310.02567 • Published Oct 4, 2023 • 3
MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting Paper • 2210.07179 • Published Oct 13, 2022 • 3
Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrieval Paper • 2104.08801 • Published Apr 18, 2021 • 1