Large language models persistently produce literal translations of idiomatic expressions, but the source of this failure remains unclear. We introduce **IdiomDIT**, a diagnostic framework that jointly evaluates idiom **D**etection, idiom **I**nterpretation, and idiomatic **T**ranslation, attributing each error to a specific source. Across six language pairs and five models spanning 4B to 70B, IdiomDIT shows that literal translation error (LTE) can persist even after successful detection and interpretation, a know-but-error pattern we term Literal Translation Bias (LTB). This pattern is direction-specific: LTB dominates some directions, while others show greater knowledge deficits, likely reflecting lower idiom exposure in pretraining. We then use linear probing to test whether LTB is already reflected in the model’s pre-generation hidden state, recovering per-language literal translation directions with high accuracy, and ablating this direction reduces LTE. However, once we ensure no idiom’s data leaks across training and test, and subtract out each idiom’s mean hidden state before probing, accuracy collapses, confirming the probe was largely detecting which idiom it is looking at rather than a genuine bias signal. A matched random direction also reduces LTE just as much as the identified one. We release these controls as a reusable protocol for testing whether such hidden-state attribution claims in machine translation are genuine or confounded. The code is publicly available at https://github.com/NLP2CT/IdiomDIT.

A hallmark of advanced artificial intelligence is the capacity to progress from passive visual perception to the strategic modification of visual information to facilitate complex reasoning. This advanced capability, however, remains critically underdeveloped in current Large Multi-modal Models (LMMs). The deficiency is often masked by evaluation metrics that prioritize final-answer accuracy, creating an illusion of competence where genuine reasoning is absent. Using the domain of geometric problem-solving as a precise instrument, we probe this issue through tasks that require constructing visual aids.To this end, we introduce VisAidMath, a challenging benchmark, and our novel Three-Layered Funnel Evaluation Framework. This framework moves beyond simple accuracy (ACCU) to scrutinize the generation of valid visual aids (PVA) and the soundness of subsequent reasoning steps (SPRS). Our extensive experiments on state-of-the-art models, including Doubao-Seed-1.6 and o4, reveal a profound “Reasoning Illusion”. We observe that high surface-level accuracy conceals a catastrophic failure in the models’ ability to produce valid visual aids or to reason from them. Our findings expose a fundamental schism between visual perception and logical deduction in modern LMMs. We provide a public evaluation platform on CodaBench and release the project homepage.

The development of poetry generation system mainly focuses on enhancing the capacity of generation model. However, the demands of customization and polishing are generally ignored, which highly reduces the scope of application. In this work, we present Yu Sheng, a web-based poetry generation system that is featured a human-in-loop generation framework, providing various customization options for users with different backgrounds to engage in the process of poetry composition. To this end, we propose two methods and train the models that can perform constrained generation and fine-grained polishing. The automatic and human evaluation results show that our system has a strong ability to generate and polish poetry compared to other vanilla models. Our system is publicly accessible at: https://yusheng.cis.um.edu.mo.