MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoning

  • 类型:arxiv
  • 标识:2607.11736
  • 链接:https://arxiv.org/abs/2607.11736
  • 主分类:evaluation
  • 形态:benchmark
  • 被引:0
  • 被引来源:Semantic Scholar + OpenAlex
  • S2被引:0
  • OpenAlex被引:0
  • 影响力被引:0
  • TLDR:This work introduces MCLASH, a multilingual moral decision-making benchmark to capture culturally situated moral intuitions and social norms across languages, and proposes MET (Multilingual Ethics with Theory-grounded reasoning), a two-step prompting method built on expert-curated, theory-based grounds drawn from psychology and philosophy.
  • OpenAlex ID:W7168286946
  • OpenAlex DOI:10.48550/arxiv.2607.11736
  • DOI:10.48550/arxiv.2607.11736
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://doi.org/10.48550/arxiv.2607.11736
  • OpenAlex更新:2026-07-19
  • 待LLM分类:否
  • 标题中文:MET:理论支撑且文化感知的多语言道德推理
  • TLDR中文:本文提出 MCLASH,一个多语言道德决策 benchmark,用于捕捉跨语言的文化情境化道德直觉和社会规范;并提出 MET(Multilingual Ethics with Theory-grounded reasoning),一种基于心理学与哲学专家策划的理论依据的两步提示方法。
  • 来源文件
  • /inbox/tom/_candidates/2026-07-15-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]