Tag
这篇论文审计了三类非生成式决策模型（编码器打分器、解码器打分器和闭源 API）在孟加拉语习语上的表现，发现当选项列表中包含字面释义时，模型会强烈偏向字面含义，且这种"字面吸引"在孟加拉语测试中比英语高 1.9 到 6.4 倍，同时校准性全面下降。
This paper introduces VIVID, the first systematic benchmark for evaluating culturally grounded figurative language understanding in Vietnamese, comprising 1,636 idioms and proverbs. Evaluation of eight state-of-the-art models reveals significant gaps, with Vietnamese-specialized models drastically underperforming multilingual systems and even top models achieving less than 50% correctness on average.
This paper presents an interpretable network-based framework for representing idiomatic expressions across eight languages using binary conceptual features. Community detection reveals that idioms cluster by conceptual schema rather than language, and the framework improves downstream idiom detection and cross-lingual transfer over embedding-based baselines.
Introduces IdioLink, a retrieval benchmark of 10,700 documents and 2,140 queries across 107 idioms that tests whether models can link idiomatic expressions to conceptually equivalent literal or paraphrased meanings. Evaluations show current embedding models struggle with this task, highlighting gaps in idiom-aware semantic retrieval.