Reading Between the Prompts: How Stereotypes Shape LLM's Implicit Personalization

Documenti analoghi

• MBBQ: A Dataset for Cross-Lingual Comparison of Stereotypes in Generative LLMs
  di: Neplenbroek, Vera, et al.
  Pubblicazione: (2024)
• Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation
  di: Neplenbroek, Vera, et al.
  Pubblicazione: (2024)
• One Persona, Many Cues, Different Results: How Sociodemographic Cues Impact LLM Personalization
  di: Weeber, Franziska, et al.
  Pubblicazione: (2026)
• On the Consistency of Multilingual Context Utilization in Retrieval-Augmented Generation
  di: Qi, Jirui, et al.
  Pubblicazione: (2025)
• Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models
  di: Qi, Jirui, et al.
  Pubblicazione: (2023)