5 papers
Shieldstral
Antonia Calvi, Avinash Sooriyarachchi, Giada Pistilli +274
We introduce Shieldstral, a 3B-parameter policy-adaptive multimodal safety classifier that matches or outperforms models nearly 7 its size on text safety benchmarks and set…
Voxtral TTS
Mistral-AI, :, Alexander H. Liu +186
We introduce Voxtral TTS, an expressive multilingual text-to-speech model that generates natural speech from as little as 3 seconds of reference audio. Voxtral TTS adopts a hybrid…
When Models Know More Than They Say: Probing Analogical Reasoning in LLMs
Hope McGovern, Caroline Craig, Thomas Lippincott +1
Analogical reasoning is a core cognitive faculty essential for narrative understanding. While LLMs perform well when surface and structural cues align, they struggle in cases where…
Computational Discovery of Chiasmus in Ancient Religious Text
Hope McGovern, Hale Sirin, Tom Lippincott
Chiasmus, a debated literary device in Biblical texts, has captivated mystics while sparking ongoing scholarly discussion. In this paper, we introduce the first computational appro…
Characterizing the Effects of Translation on Intertextuality using Multilingual Embedding Spaces
Hope McGovern, Hale Sirin, Tom Lippincott
Rhetorical devices are difficult to translate, but they are crucial to the translation of literary documents. We investigate the use of multilingual embedding spaces to characteriz…