What Helps Language Models Predict Human Beliefs: Demographics or Prior Stances?

Documenti analoghi

• A semantic embedding space based on large language models for modelling human beliefs
  di: Lee, Byunghwee, et al.
  Pubblicazione: (2024)
• Can we trust the evaluation on ChatGPT?
  di: Aiyappa, Rachith, et al.
  Pubblicazione: (2023)
• Benchmarking zero-shot stance detection with FlanT5-XXL: Insights from training data, prompting, and decoding strategies into its near-SoTA performance
  di: Aiyappa, Rachith, et al.
  Pubblicazione: (2024)
• LLMs Can Infer Political Alignment from Online Conversations
  di: Lee, Byunghwee, et al.
  Pubblicazione: (2026)
• Vulnerability of LLMs' Stated Beliefs? LLMs Belief Resistance Check Through Strategic Persuasive Conversation Interventions
  di: Huang, Fan, et al.
  Pubblicazione: (2026)