Uncovering Gaps in How Humans and LLMs Interpret Subjective Language

Documenti analoghi

• Mass-Producing Failures of Multimodal Systems with Language Models
  di: Tong, Shengbang, et al.
  Pubblicazione: (2023)
• How do Language Models Bind Entities in Context?
  di: Feng, Jiahai, et al.
  Pubblicazione: (2023)
• Feedback Loops With Language Models Drive In-Context Reward Hacking
  di: Pan, Alexander, et al.
  Pubblicazione: (2024)
• LatentQA: Teaching LLMs to Decode Activations Into Natural Language
  di: Pan, Alexander, et al.
  Pubblicazione: (2024)
• Monitoring Latent World States in Language Models with Propositional Probes
  di: Feng, Jiahai, et al.
  Pubblicazione: (2024)