CoSToM:Causal-oriented Steering for Intrinsic Theory-of-Mind Alignment in Large Language Models

Documenti analoghi

• RecToM: A Benchmark for Evaluating Machine Theory of Mind in LLM-based Conversational Recommender Systems
  di: Li, Mengfan, et al.
  Pubblicazione: (2025)
• On the Limitations of Steering in Language Model Alignment
  di: Niranjan, Chebrolu, et al.
  Pubblicazione: (2025)
• Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Models
  di: Kim, Hyunwoo, et al.
  Pubblicazione: (2025)
• Theory of Mind in Large Language Models: Assessment and Enhancement
  di: Chen, Ruirui, et al.
  Pubblicazione: (2025)
• Probing the Robustness of Theory of Mind in Large Language Models
  di: Nickel, Christian, et al.
  Pubblicazione: (2024)