arXiv Computation and Language August 28, 2026 By Xin Zhong, Satori Hachisuka

PragAlign: Evidence-Sensitive Reply Assistance Across Chinese and Japanese Appropriateness Judgments

Read the original on arXiv Computation and Language →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv Computation and Language

Sep 17

TeochewBench: A Human-Reviewed Benchmark for Teochew Hanzi Translation

arXiv:2609.18156v1 Announce Type: new Abstract: Teochew has a substantial speaker community and exhibits distinctive lexical, syntactic, and pragmatic features, yet textual resources for evaluating l...

By Jianan Wu

llms benchmarks

Hugging Face Trending Papers

Sep 16

TeochewBench: A Human-Reviewed Benchmark for Teochew Hanzi Translation

Teochew has a substantial speaker community and exhibits distinctive lexical, syntactic, and pragmatic features, yet textual resources for evaluating large language models remain limited. We present T...

llms benchmarks

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.

llms safety

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.

By Florian Braun

llms benchmarks safety

arXiv Computation and Language

Aug 31

CultureConverse: A Multilingual Multi-turn Simulation Harness for Culturally Grounded Assistance in East and Southeast Asia

arXiv:2608.28405v1 Announce Type: new Abstract: Current cultural evaluations for large language models (LLMs) often reduce culture to single-turn factual recall via MCQs, failing to capture a common...

By Bryan Chen Zhengyu Tan, Weihua Zheng, Thong T. Doan, Bich Ngoc Doan, Jia Wang Peh, Xiaoyuan Yi, Jing Yao, Xing Xie, Nancy F. Chen, Zhengyuan Liu, JinYeong Bak, Wafi Shamdi, Soo Kai Chie, Liew Yu Siong, Aina Azyyati Binti Mohamad Rezal, Lew Yan Yan Vanessa, Huadan Wu, Dylan Raharja, Nadya Yuki Wangsajaya, Akane Fukushige, Kazushi Kato, Koji Inoue, Tatsuya Kawahara, Jaehyung Seo, Dongjun Kim, Seungyoon Lee, Zi Haur Pang, Rui Yang Tan, Charibeth Ko Cheng, Maria Regina Justina Estuar, Jann Railey Montalan, Pham Minh Duc, Roy Ka-Wei Lee

llms fine-tuning benchmarks safety

arXiv AI

Jul 3

Challenges and Recommendations for LLMs-as-a-Judge in Multilingual Settings and Low-Resource Languages

arXiv:2607. 02235v1 Announce Type: cross Abstract: LLM-as-a-Judge has become the dominant evaluation paradigm for many natural language generation tasks, due to shortcomings of conventional metrics and high correlations with human judgment, albeit mostly in English.

By A. Seza Do\u{g}ru\"oz, Xixian Liao, Verena Blaschke, Jakob Prange, Senyu Li, David Ifeoluwa Adelani

llms nlp

One email a morning, machine-written

Related stories

TeochewBench: A Human-Reviewed Benchmark for Teochew Hanzi Translation

TeochewBench: A Human-Reviewed Benchmark for Teochew Hanzi Translation

Human-LLM Alignment in Language Attitudes Toward Non-Native Japanese

Interpretable Cross-Lingual Alignment in Small Language Models: Probing Cultural and Pragmatic Reasoning in Japanese-English Bilingual LLMs

CultureConverse: A Multilingual Multi-turn Simulation Harness for Culturally Grounded Assistance in East and Southeast Asia

Challenges and Recommendations for LLMs-as-a-Judge in Multilingual Settings and Low-Resource Languages