Federico Bianchi

Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory EACL 2026 h4rm3l: A Language for Composable Jailbreak Attack Synthesis ICLR 2025 How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis ICML 2024 Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions ICLR 2024 Scalable Safe Policy Improvement for Factored Multi-Agent MDPs ICML 2024 XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models NAACL 2024 Scalable Safe Policy Improvement via Monte Carlo Tree Search ICML 2023 When and Why Vision-Language Models Behave like Bags-Of-Words, and What to Do About It? ICLR 2023 Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages EMNLP 2022 “Does it come in black?” CLIP-like models are zero-shot recommenders ACL 2022 HATE-ITA: Hate Speech Detection in Italian Social Media Text NAACL 2022 “It’s Not Just Hate”: A Multi-Dimensional Perspective on Detecting Harmful Speech Online EMNLP 2022 Language Invariant Properties in Natural Language Processing ACL 2022 Measuring Harmful Sentence Completion in Language Models for LGBTQIA+ Individuals ACL 2022 MilaNLP at SemEval-2022 Task 5: Using Perceiver IO for Detecting Misogynous Memes with Text and Image Modalities SemEval 2022 Pipelines for Social Bias Testing of Large Language Models ACL 2022 SocioProbe: What, When, and Where Language Models Learn about Sociodemographics EMNLP 2022 Twitter-Demographer: A Flow-based Tool to Enrich Twitter Data EMNLP 2022 XLM-EMO: Multilingual Emotion Prediction in Social Media Text ACL 2022 BERTective: Language Models and Contextual Information for Deception Detection EACL 2021 BERT Goes Shopping: Comparing Distributional Models for Product Representations ACL 2021 Cross-lingual Contextualized Topic Models with Zero-shot Learning EACL 2021 FEEL-IT: Emotion and Sentiment Classification for the Italian Language EACL 2021 HONEST: Measuring Hurtful Sentence Completion in Language Models NAACL 2021 Language in a (Search) Box: Grounding Language Learning in Real-World Human-Machine Interaction NAACL 2021 MilaNLP @ WASSA: Does BERT Feel Sad When You Cry? EACL 2021 On the Gap between Adoption and Understanding in NLP ACL 2021 Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence ACL 2021 Query2Prod2Vec: Grounded Word Embeddings for eCommerce NAACL 2021 SWEAT: Scoring Polarization of Topics across Different Corpora EMNLP 2021 Universal Joy A Data Set and Results for Classifying Emotions Across Languages EACL 2021 “You Sound Just Like Your Father” Commercial Machine Translation Systems Include Stylistic Biases ACL 2020 Training Temporal Word Embeddings with a Compass AAAI 2019