Ngā tūemi rite

• Understanding the Logic of Direct Preference Alignment through Logic
  mā: Richardson, Kyle, me ētahi atu.
  I whakaputaina: (2024)
• Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
  mā: Xu, Zhangchen, me ētahi atu.
  I whakaputaina: (2024)
• WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild
  mā: Lin, Bill Yuchen, me ētahi atu.
  I whakaputaina: (2024)
• SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMs
  mā: Gu, Yuling, me ētahi atu.
  I whakaputaina: (2024)
• MultiZebraLogic: A Multilingual Logical Reasoning Benchmark
  mā: Bruun, Sofie Helene, me ētahi atu.
  I whakaputaina: (2025)