The consortium studies, designs, and implements innovative methodologies for KM based on the use of IE. From the scientific point of view, we focus on two aspects that are symmetric: how the use in KM poses requirements and challenges to IE and how the use of IE changes KM. From the practical point of view, we define tools and methodologies for IE-based KM.
3️⃣ "Cross-Attention is Half Explanation in Speech-to-Text Models"
👥 @sarapapi, @DennisFucci, @mgaido91, @negri_teo, @luisabentivogli
🇪🇺 DVPS EU project
📄
1️⃣ "Do What I Say: A Spoken Prompt Dataset for Instruction-Following"
👥 @MaikeZufle, @sarapapi, Fabian Retkowski, Szymon Mazurek, @mkasztelnik, Alexander Waibel, @luisabentivogli, @_janius_
🇪🇺 Meetween EU project
📄
Our pick of the week by
@lina_conti
: "Greater accessibility can amplify discrimination in generative AI" by
@CarolinHolterm, @minhducbui_nlp, @KaitlynZhou, @vjhofmann, @kelina1124, @anne_lauscher
📰
#GenderBias #SpeechLLM
Pick of the week @fbk_mt: "Greater accessibility can amplify discrimination in generative AI"
Gender bias in speech-based LLMs examined from multiple angles: a user survey, automatic bias measurement, and pitch manipulation experiments.
https://arxiv.org/pdf/2603.22260