Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction Paper • 2303.04132 • Published Mar 7, 2023
MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance Paper • 1909.02622 • Published Sep 5, 2019
Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning Paper • 2305.13971 • Published May 23, 2023 • 5
Flows: Building Blocks of Reasoning and Collaborating AI Paper • 2308.01285 • Published Aug 2, 2023 • 2
REFINER: Reasoning Feedback on Intermediate Representations Paper • 2304.01904 • Published Apr 4, 2023
Date Fragments: A Hidden Bottleneck of Tokenization for Temporal Reasoning Paper • 2505.16088 • Published May 22 • 3
zip2zip: Inference-Time Adaptive Vocabularies for Language Models via Token Compression Paper • 2506.01084 • Published Jun 1 • 7
EuroBERT: Scaling Multilingual Encoders for European Languages Paper • 2503.05500 • Published Mar 7 • 79