Untangling Input Language from Reasoning Language: A Diagnostic Framework for Cross-Lingual Moral Alignment in LLMs

Documenti analoghi

• Your Next State-of-the-Art Could Come from Another Domain: A Cross-Domain Analysis of Hierarchical Text Classification
  di: Li, Nan, et al.
  Pubblicazione: (2024)
• Cards Against LLMs: Benchmarking Humor Alignment in Large Language Models
  di: Fettach, Yousra, et al.
  Pubblicazione: (2026)
• Building and Measuring Trust between Large Language Models
  di: Buyl, Maarten, et al.
  Pubblicazione: (2025)
• Cross-Lingual Consistency: A Novel Inference Framework for Advancing Reasoning in Large Language Models
  di: Yu, Zhiwei, et al.
  Pubblicazione: (2025)
• Building Data-Driven Occupation Taxonomies: A Bottom-Up Multi-Stage Approach via Semantic Clustering and Multi-Agent Collaboration
  di: Li, Nan, et al.
  Pubblicazione: (2025)