There are two interleaved high-level goals for the EXCITEMENT project. The first is to set up, for the first time, a generic architecture and a comprehensive implementation for a multilingual textual inference platform and to make it available to the scientific and technological communities. The second goal of the project is to develop a new generation of inference-based industrial text exploration applications for customer interactions, which enables businesses to better analyze and make sense of their diverse and often unpredicted client content. These goals were be achieved for three languages, i.e. English, German and Italian, and for three customer interaction channels, i.e. speech (transcriptions), email and social media.
Our pick of the week by @beomseok_lee_: "ALAS: Measuring Latent Speech-Text Alignment For Spoken Language Understanding In Multimodal LLMs" by Pooneh Mousavi, @yingzhi_wang, @mirco_ravanelli, and @CemSubakan (2025)
#SLU #speech #multimodal #LLM
Speech-language models show promise in multimodal tasksโbut how well are speech & text actually aligned? ๐ค
This paper https://arxiv.org/abs/2505.19937 proposes a new metric to measure layer-wise correlation between the two, with a focus on SLU tasks. ๐๐ฃ๏ธ๐
๐ Ciao! Stiamo studiando come l'AI viene usata in Italia e per farlo abbiamo costruito un sondaggio!
๐https://bocconi.eu.qualtrics.com/jfe/form/SV_2nTelXaXvJlinbg (รจ anonimo, dura ~10 m, se partecipi o lo diffondi ci aiuti un sacco๐)
Ci interessa anche raggiungere persone che non si occupano di AI!
Our pick of the week by @apierg: "Agree to Disagree? A Meta-Evaluation of LLM Misgendering" by Arjun Subramonian, Vagrant Gautam, Preethi Seshadri, Dietrich Klakow, @kaiwei_chang, @YizhouSun (2025).
#LLM #misgendering #gender
Super interesting paper by Subramonian et al: "Agree to Disagree? A Meta-Evaluation of LLM Misgendering" https://arxiv.org/abs/2504.17075
Turns out, misgendering is messier than just pronouns. I'd love to see this analysis extended to grammatical gender languages! #LLM #AI #ethics @fbk_mt
๐ New tech report out! Meet FAMA, our open-science speech foundation model family for both ASR and ST in ๐ฌ๐ง English and ๐ฎ๐น Italian.
The models are live and ready to try on @huggingface ๐
๐
#ASR #ST #OpenScience #MultilingualAI