arXiv Computation and Language
Human-LLM Alignment in Language Attitudes Toward Non-Native Japanese
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
Hugging Face Trending Papers
Aug 3
Human-LLM Alignment in Language Attitudes Toward Non-Native Japanese
Large language models (LLMs) increasingly evaluate human writing in high-stakes domains such as hiring and academic assessment, putting non-native speakers at particular risk. Drawing on the language attitudes framework, we compared human and LLM evaluations of parallel L1- and L2-written Japanese emails on three dimensions: fluency, status, and solidarity.
arXiv Computation and Language
Aug 28
PragAlign: Evidence-Sensitive Reply Assistance Across Chinese and Japanese Appropriateness Judgments
PragAlign is a reply‑assistance system that separates context reading from selective clarification, designed for multilingual settings. In evaluations with native Chinese and Japanese speakers, PragAlign achieved better rankings than baseline methods in Chinese and the highest top‑rank rate in Japanese, while both groups often chose the same top condition. The study highlights both shared and language‑specific judgment patterns that can inform culturally aware reply‑assistance tools.
arXiv Computation and Language
Oct 22
Investigating the Impact of Learner Errors on Social Bias in Large Language Models
arXiv:2610.29896v1 Announce Type: new Abstract: Existing social bias benchmarks evaluate large language models mostly on fluent, well-formed English, reflecting native speaker usage and leaving non-n...
Hugging Face Trending Papers
Oct 21
Investigating the Impact of Learner Errors on Social Bias in Large Language Models
Existing social bias benchmarks evaluate large language models mostly on fluent, well-formed English, reflecting native speaker usage and leaving non-native writers unrepresented. To address this gap,...
arXiv Machine Learning
Aug 18
Interpretable Cross-Lingual Alignment in Small Language Models: Probing Cultural and Pragmatic Reasoning in Japanese-English Bilingual LLMs
arXiv:2608. 14896v1 Announce Type: cross Abstract: Large language models work well on English and behave in poorly understood ways on languages typologically far from it.
arXiv Computation and Language
Oct 27
Do Language Models Understand Igbo Culture? Beyond Multiple Choice
arXiv:2610.35168v1 Announce Type: new Abstract: The value of language models for any community depends on whether a model actually understands the culture of the people it intends to serve. We use th...