Debora Nozza

deboranozza.bsky.social

22 October 2026 02:05

Couldn't be prouder of our @milanlp.bsky.social team and all the amazing work behind these papers! I'll be at #EMNLP2026 in Budapest and I'm also looking for a postdoc to join our lab! If you're interested, feel free to DM me so we can meet and chat! 🔗 jobmarket.unibocconi.eu?id=1004

MilaNLP Lab

milanlp.bsky.social

22 October 2026 02:05

WildSEEK: Evaluating Language Models for Information-Seeking 🔎 A dataset and evaluation framework for assessing the reliability, fairness and safety of LLMs in information-seeking. 📍 Hall H 🎤 Tanise Ceron 🗓️ 26 October 2026, 16:45–18:15 📄 arxiv.org/abs/2608.30683

MilaNLP Lab

milanlp.bsky.social

22 October 2026 02:05

The Role of Implicit and Explicit Demographic Signals in LLM-based Student Assessment 🎓 Explicit demographic information and cues inferred from conversation history can systematically change LLM assessments. 📍 Hall H 🎤 Donya Rooein 🗓️ 26 October 2026, 16:45–18:15 📄 arxiv.org/pdf/2609.16993

MilaNLP Lab

milanlp.bsky.social

22 October 2026 02:05

Can LLMs Model Incorrect Student Reasoning? 🧩 A reasoning taxonomy applied to math/science LLM traces reveals domain adaptation, learning-science alignment, and failures in solution recovery. 📍 Hall H 🎤 Yanick Zengaffinen 🗓️ 26 October 2026, 11:00–12:30 📄 openreview.net/forum?id=sQ4...

MilaNLP Lab

milanlp.bsky.social

22 October 2026 02:05

Overreliance on AI in Information-seeking from Video Content 📺 AI-mediated information access improves accuracy and efficiency, but users quickly become overreliant, leaving them vulnerable. 📍 Hall H 🎤 Elisa Bassignana · Poster 🗓️ 27 October 2026, 11:00–12:30 📄 arxiv.org/abs/2603.19843