The Grounding Gap: How LLMs Anchor the Meaning of Abstract Concepts Differently from Humans

Documenti analoghi

• Local Explanations and Self-Explanations for Assessing Faithfulness in black-box LLMs
  di: Fragkathoulas, Christos, et al.
  Pubblicazione: (2024)
• LAR-ECHR: A New Legal Argument Reasoning Task and Dataset for Cases of the European Court of Human Rights
  di: Chlapanis, Odysseas S., et al.
  Pubblicazione: (2024)
• GOSt-MT: A Knowledge Graph for Occupation-related Gender Biases in Machine Translation
  di: Mastromichalakis, Orfeas Menis, et al.
  Pubblicazione: (2024)
• Deep Ensemble Art Style Recognition
  di: Menis-Mastromichalakis, Orfeas, et al.
  Pubblicazione: (2024)
• Beyond One-Size-Fits-All: Adapting Counterfactual Explanations to User Objectives
  di: Mastromichalakis, Orfeas Menis, et al.
  Pubblicazione: (2024)