2001.08

,

QuRating: Selecting High-Quality Data for Training Language Models

2001.07

,

Longformer: The Long-Document Transformer

2001.07

,

Generating Long Sequences with Sparse Transformers

2001.07

,

When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards

2001.07

,

RouteLLM: Learning to Route LLMs with Preference Data