News

• I enjoyed contributing to the European AI Office report on frontier LLMs: competitiveness, sovereignty and security
• A theory of emergence in LLM ? paper
• Great blog post about the current challenges of NLP benchmarking: https://ruder.io/nlp-benchmarking/ towards dynamic benchmarking.
  • You want to benchmark your NLP model ? You may want to have a look at GEM or DynaBench or BigBench.