arXiv:2606. 12392v1 Announce Type: cross Abstract: Recently, large language models (LLMs) have achieved promising progress in the fields of classical Chinese translation and the generation of classical poetry.
By Haotao Xie
Neo-Classic is a new benchmark designed to evaluate linguistic‑aesthetic reasoning in Classical Chinese poetry. It uses an out‑of‑sample dataset of strictly metrical poems written by contemporary experts and a set of reverse‑understanding probes, avoiding reliance on historical corpora. Experiments with leading LLMs show a 20–50% performance drop on contemporary texts and low accuracy (0–13%) on discourse‑level ordering, indicating that current models excel at local patterns but struggle with global hierarchical planning.
By Han Zhang, Zihan Gu, Zhiyuan Wang, Tianyi Ma, Jiacheng Lu, Xinyan Zhang, Yuhao Wei, Cheng Hua
arXiv:2608. 11452v1 Announce Type: cross Abstract: Text-to-image (T2I) models are increasingly asked to illustrate literary and cultural content, yet we cannot measure how well an image renders the meaning of a poem.
By Haoqi Hu, Tongji Luo, Li Zhang, Boning Zhou
arXiv:2609.23951v1 Announce Type: new
Abstract: Expressive speech synthesis has advanced through prosody modeling, yet generating structured poetic speech, such as haiku, remains challenging. Prior w...
By Devangi Sharma, Sophia Judicke, Glenda Tan, Conrad Schaumburg, Shinji Watanabe
The paper introduces Peony, a benchmark designed to evaluate large language models’ ability to comprehend the ‘poetic logic’ of modern Chinese poetry. It defines this logic through four tasks across stanza, line, and imagery levels and tests six mainstream LLMs under both non‑thinking and thinking configurations. Results show current LLMs struggle with this literary reasoning, highlighting Peony’s role in revealing these limitations.
By Tian Lan, Shanshan Wang, Zehua Duo, Jiang Li, Guanglai Gao, Derek F. Wong, Xiangdong Su
LuxIT is a monolingual instruction‑tuning dataset for Luxembourgish, created by synthesizing instruction‑answer pairs from native texts using the DeepSeek‑R1‑0528 model and a quality‑assurance LLM‑as‑judge process. The resulting 227,507 high‑quality pairs were used to fine‑tune 14 LLMs (≤15 B parameters), yielding an average accuracy increase of +5.37 percentage points on standardized Luxembourgish proficiency exams and improvements in macro‑averaged F1 on nine of the fourteen downstream NLP tasks. These findings demonstrate that synthetic monolingual data can effectively enhance LLM performance in low‑resource languages and reveal the complex relationship between exam performance and practical NLP gains.
By Julian Valline, Cedric Lothritz, Siwen Guo, Jordi Cabot