Debora Nozza
@deboranozza.bsky.social
Assistant Professor at Bocconi University in MilaNLP group • Working in #NLP, #CSS and #Ethics • She/her • #ERCStG PERSONAE
Reposted by Debora Nozza
This week at reading group 📚
@pranav-nlp.bsky.social presented "You Cannot Sound Like GPT": Signs of language discrimination and resistance in computer science publishing.
Paper: arxiv.org/abs/2505.08127
#NLProc
@pranav-nlp.bsky.social presented "You Cannot Sound Like GPT": Signs of language discrimination and resistance in computer science publishing.
Paper: arxiv.org/abs/2505.08127
#NLProc
January 23, 2026 at 1:35 PM
This week at reading group 📚
@pranav-nlp.bsky.social presented "You Cannot Sound Like GPT": Signs of language discrimination and resistance in computer science publishing.
Paper: arxiv.org/abs/2505.08127
#NLProc
@pranav-nlp.bsky.social presented "You Cannot Sound Like GPT": Signs of language discrimination and resistance in computer science publishing.
Paper: arxiv.org/abs/2505.08127
#NLProc
Reposted by Debora Nozza
Thank you @belindazli.bsky.social for the great talk "Solving the Specification Problem through Interaction” at our weekly seminar!
#NLProc
#NLProc
January 23, 2026 at 4:26 PM
Thank you @belindazli.bsky.social for the great talk "Solving the Specification Problem through Interaction” at our weekly seminar!
#NLProc
#NLProc
Reposted by Debora Nozza
⏳ Deadline approaching! We’re hiring 2 fully funded postdocs in #NLP.
Join the MilaNLP team and contribute to our upcoming research projects (SALMON & TOLD)
🔗 Details + how to apply: milanlproc.github.io/open_positio...
⏰ Deadline: Jan 31, 2026
Join the MilaNLP team and contribute to our upcoming research projects (SALMON & TOLD)
🔗 Details + how to apply: milanlproc.github.io/open_positio...
⏰ Deadline: Jan 31, 2026
January 19, 2026 at 5:24 PM
⏳ Deadline approaching! We’re hiring 2 fully funded postdocs in #NLP.
Join the MilaNLP team and contribute to our upcoming research projects (SALMON & TOLD)
🔗 Details + how to apply: milanlproc.github.io/open_positio...
⏰ Deadline: Jan 31, 2026
Join the MilaNLP team and contribute to our upcoming research projects (SALMON & TOLD)
🔗 Details + how to apply: milanlproc.github.io/open_positio...
⏰ Deadline: Jan 31, 2026
Reposted by Debora Nozza
January 20, 2026 at 11:15 AM
Reposted by Debora Nozza
New year, new job? If that is your current mantra, check the open postdoc positions with Debora Nozza and me at our lab. Deadline is January 31st.
milanlproc.github.io/open_positio...
milanlproc.github.io/open_positio...
Postdoctoral Researcher – NLP (2 positions) | MilaNLP Lab @ Bocconi University
Two Postdoctoral Researcher positions – Deadline January 31st, 2026
milanlproc.github.io
January 19, 2026 at 4:13 PM
New year, new job? If that is your current mantra, check the open postdoc positions with Debora Nozza and me at our lab. Deadline is January 31st.
milanlproc.github.io/open_positio...
milanlproc.github.io/open_positio...
Reposted by Debora Nozza
We're also back with the lab's seminar! Today we had Eleonora Mancini presenting her doctoral research "Multimodal AI for Human Expression Understanding".
#NLP #multimodality #speech
#NLP #multimodality #speech
January 16, 2026 at 4:47 PM
We're also back with the lab's seminar! Today we had Eleonora Mancini presenting her doctoral research "Multimodal AI for Human Expression Understanding".
#NLP #multimodality #speech
#NLP #multimodality #speech
Reposted by Debora Nozza
Holidays over, reading group resumes 📖
Today Henning Hoffmann presented the paper "Music for All: Representational Bias and Cross-Cultural Adaptability of Music Generation Models"
Paper: arxiv.org/pdf/2502.07328
#NLProc
Today Henning Hoffmann presented the paper "Music for All: Representational Bias and Cross-Cultural Adaptability of Music Generation Models"
Paper: arxiv.org/pdf/2502.07328
#NLProc
January 15, 2026 at 11:50 AM
Holidays over, reading group resumes 📖
Today Henning Hoffmann presented the paper "Music for All: Representational Bias and Cross-Cultural Adaptability of Music Generation Models"
Paper: arxiv.org/pdf/2502.07328
#NLProc
Today Henning Hoffmann presented the paper "Music for All: Representational Bias and Cross-Cultural Adaptability of Music Generation Models"
Paper: arxiv.org/pdf/2502.07328
#NLProc
Reposted by Debora Nozza
#MemoryModay #NLProc Countering Hateful and Offensive Speech Online - Open Challenges" by Plaza-Del-Arco, @debora_nozza, Guerini, Sorensen, Zampieri, 2024 is a tutorial on the challenges and solutions for detecting and mitigating hate speech.
Countering Hateful and Offensive Speech Online - Open Challenges
Flor Miriam Plaza-del-Arco, Debora Nozza, Marco Guerini, Jeffrey Sorensen, Marcos Zampieri. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts.…
aclanthology.org
December 22, 2025 at 4:03 PM
#MemoryModay #NLProc Countering Hateful and Offensive Speech Online - Open Challenges" by Plaza-Del-Arco, @debora_nozza, Guerini, Sorensen, Zampieri, 2024 is a tutorial on the challenges and solutions for detecting and mitigating hate speech.
Reposted by Debora Nozza
For today's reading group, Serena Pugliese presented the paper “Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models" by Piercosma Bisconti et al. (2025).
Paper: arxiv.org/pdf/2511.15304
#NLProc
#LLMs #jailbreaking
Paper: arxiv.org/pdf/2511.15304
#NLProc
#LLMs #jailbreaking
December 18, 2025 at 11:32 AM
For today's reading group, Serena Pugliese presented the paper “Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models" by Piercosma Bisconti et al. (2025).
Paper: arxiv.org/pdf/2511.15304
#NLProc
#LLMs #jailbreaking
Paper: arxiv.org/pdf/2511.15304
#NLProc
#LLMs #jailbreaking
Reposted by Debora Nozza
🚀 We’re opening 2 fully funded postdoc positions in #NLP!
Join the MilaNLP team and contribute to our upcoming research projects.
🔗 More details: milanlproc.github.io/open_positio...
⏰ Deadline: Jan 31, 2026
Join the MilaNLP team and contribute to our upcoming research projects.
🔗 More details: milanlproc.github.io/open_positio...
⏰ Deadline: Jan 31, 2026
December 18, 2025 at 3:29 PM
🚀 We’re opening 2 fully funded postdoc positions in #NLP!
Join the MilaNLP team and contribute to our upcoming research projects.
🔗 More details: milanlproc.github.io/open_positio...
⏰ Deadline: Jan 31, 2026
Join the MilaNLP team and contribute to our upcoming research projects.
🔗 More details: milanlproc.github.io/open_positio...
⏰ Deadline: Jan 31, 2026
Reposted by Debora Nozza
#TBT #NLProc #MachineLearning #SafetyFirst 'Safety-Tuned LLaMAs: Improving LLMs Safety' by Bianchi et al. explores training LLMs for safe refusals, warns of over-tuning.
Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large...
Training large language models to follow instructions makes them perform better on a wide range of tasks and generally become more helpful. However, a perfectly helpful model will follow even the most...
arxiv.org
December 18, 2025 at 4:02 PM
#TBT #NLProc #MachineLearning #SafetyFirst 'Safety-Tuned LLaMAs: Improving LLMs Safety' by Bianchi et al. explores training LLMs for safe refusals, warns of over-tuning.
Reposted by Debora Nozza
Huge thanks to our speakers at last Friday’s lab seminar!
🗣️ @penzo-nicolo.bsky.social on multi-party conversations
🌍 @patriciachiril.bsky.social on NLP for socially grounded research
#NLProc
🗣️ @penzo-nicolo.bsky.social on multi-party conversations
🌍 @patriciachiril.bsky.social on NLP for socially grounded research
#NLProc
December 16, 2025 at 3:43 PM
Huge thanks to our speakers at last Friday’s lab seminar!
🗣️ @penzo-nicolo.bsky.social on multi-party conversations
🌍 @patriciachiril.bsky.social on NLP for socially grounded research
#NLProc
🗣️ @penzo-nicolo.bsky.social on multi-party conversations
🌍 @patriciachiril.bsky.social on NLP for socially grounded research
#NLProc
Reposted by Debora Nozza
#MemoryModay #NLProc Uma, A. N. et al. examine AI model training in 'Learning from Disagreement: A Survey'. Disagreement-handling methods' performance is shaped by evaluation methods & dataset traits.
jair.org
December 15, 2025 at 4:02 PM
#MemoryModay #NLProc Uma, A. N. et al. examine AI model training in 'Learning from Disagreement: A Survey'. Disagreement-handling methods' performance is shaped by evaluation methods & dataset traits.
Reposted by Debora Nozza
At today’s lab reading group @carolin-holtermann.bsky.social presented ‘Fairness through Difference Awareness: Measuring Desired Group Discrimination in LLMs’ by @angelinawang.bsky.social et al. (2025).
Lots to think about how we evaluate fairness in language models!
#NLProc #fairness #LLMs
Lots to think about how we evaluate fairness in language models!
#NLProc #fairness #LLMs
December 11, 2025 at 11:55 AM
At today’s lab reading group @carolin-holtermann.bsky.social presented ‘Fairness through Difference Awareness: Measuring Desired Group Discrimination in LLMs’ by @angelinawang.bsky.social et al. (2025).
Lots to think about how we evaluate fairness in language models!
#NLProc #fairness #LLMs
Lots to think about how we evaluate fairness in language models!
#NLProc #fairness #LLMs
Reposted by Debora Nozza
#TBT #NLProc 'Respectful or Toxic?' by Plaza-del-Arco, @debora & @dirkhovy.bsky.social (2023) explores zero-shot learning for multilingual hate speech detection. Highlights prompt & model choice for accuracy. #AI #LanguageModels #HateSpeechDetection
Respectful or Toxic? Using Zero-Shot Learning with Language Models to Detect Hate Speech
Flor Miriam Plaza-del-arco, Debora Nozza, Dirk Hovy. The 7th Workshop on Online Abuse and Harms (WOAH). 2023.
aclanthology.org
December 11, 2025 at 4:03 PM
#TBT #NLProc 'Respectful or Toxic?' by Plaza-del-Arco, @debora & @dirkhovy.bsky.social (2023) explores zero-shot learning for multilingual hate speech detection. Highlights prompt & model choice for accuracy. #AI #LanguageModels #HateSpeechDetection
Reposted by Debora Nozza
For our weekly reading group last week, @a-lauscher.bsky.social presented the paper “Shape it Up! Restoring LLM Safety during Finetuning" by ShengYun Peng et al. (2025)
#NLProc
#NLProc
December 9, 2025 at 10:24 AM
For our weekly reading group last week, @a-lauscher.bsky.social presented the paper “Shape it Up! Restoring LLM Safety during Finetuning" by ShengYun Peng et al. (2025)
#NLProc
#NLProc
Reposted by Debora Nozza
#MemoryModay #NLProc 'Leveraging Social Interactions to Detect Misinformation on Social Media' by Fornaciari et al. (2023) uses combined text and network analysis to spot unreliable threads.
arxiv.org
December 8, 2025 at 4:03 PM
#MemoryModay #NLProc 'Leveraging Social Interactions to Detect Misinformation on Social Media' by Fornaciari et al. (2023) uses combined text and network analysis to spot unreliable threads.
Reposted by Debora Nozza
#TBT #NLProc 'Compromesso! Italian Many-Shot Jailbreaks Undermine LLM Safety' by Pernisi, @dirkhovy.bsky.social, @paul-rottger.bsky.social (2024). Paper highlights LLM vulnerability through Italian demos, more demos = more attack chances.
Compromesso! Italian Many-Shot Jailbreaks undermine the safety of Large Language Models
Fabio Pernisi, Dirk Hovy, Paul Röttger. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop). 2024.
aclanthology.org
December 4, 2025 at 4:02 PM
#TBT #NLProc 'Compromesso! Italian Many-Shot Jailbreaks Undermine LLM Safety' by Pernisi, @dirkhovy.bsky.social, @paul-rottger.bsky.social (2024). Paper highlights LLM vulnerability through Italian demos, more demos = more attack chances.
Reposted by Debora Nozza
I will be @euripsconf.bsky.social this week to present our paper as non-archival at the PAIG workshop (Beyong Regulation:
Private Governance & Oversight Mechanisms for AI). Very much looking forward to the discussions!
If you are at #EurIPS and want to chat about LLM's training data. Reach out!
Private Governance & Oversight Mechanisms for AI). Very much looking forward to the discussions!
If you are at #EurIPS and want to chat about LLM's training data. Reach out!
📣 New Preprint!
Have you ever wondered what the political content in LLM's training data is? What are the political opinions expressed? What is the proportion of left- vs right-leaning documents in the pre- and post-training data? Do they correlate with the political biases reflected in models?
Have you ever wondered what the political content in LLM's training data is? What are the political opinions expressed? What is the proportion of left- vs right-leaning documents in the pre- and post-training data? Do they correlate with the political biases reflected in models?
December 2, 2025 at 9:47 PM
I will be @euripsconf.bsky.social this week to present our paper as non-archival at the PAIG workshop (Beyong Regulation:
Private Governance & Oversight Mechanisms for AI). Very much looking forward to the discussions!
If you are at #EurIPS and want to chat about LLM's training data. Reach out!
Private Governance & Oversight Mechanisms for AI). Very much looking forward to the discussions!
If you are at #EurIPS and want to chat about LLM's training data. Reach out!
Reposted by Debora Nozza
#MemoryModay #NLProc 'Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models' by @paul-rottger.bsky.social et al. (2022). A suite of tests for 10 languages.
Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models
Paul Röttger, Haitham Seelawi, Debora Nozza, Zeerak Talat, Bertie Vidgen. Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH). 2022.
aclanthology.org
December 1, 2025 at 4:03 PM
#MemoryModay #NLProc 'Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models' by @paul-rottger.bsky.social et al. (2022). A suite of tests for 10 languages.
Reposted by Debora Nozza
LECTURERS
- @theoaraujo.bsky.social , University of Amsterdam (theoaraujo.eu)
- Carlos Castillo, Universitat Pompeu Fabra (chato.cl)
- @deboranozza.bsky.social , Bocconi University (lnkd.in/dnGJH-Pd)
- More to be announced...
- @theoaraujo.bsky.social , University of Amsterdam (theoaraujo.eu)
- Carlos Castillo, Universitat Pompeu Fabra (chato.cl)
- @deboranozza.bsky.social , Bocconi University (lnkd.in/dnGJH-Pd)
- More to be announced...
November 27, 2025 at 5:21 PM
LECTURERS
- @theoaraujo.bsky.social , University of Amsterdam (theoaraujo.eu)
- Carlos Castillo, Universitat Pompeu Fabra (chato.cl)
- @deboranozza.bsky.social , Bocconi University (lnkd.in/dnGJH-Pd)
- More to be announced...
- @theoaraujo.bsky.social , University of Amsterdam (theoaraujo.eu)
- Carlos Castillo, Universitat Pompeu Fabra (chato.cl)
- @deboranozza.bsky.social , Bocconi University (lnkd.in/dnGJH-Pd)
- More to be announced...
Reposted by Debora Nozza
Happy to announce the 2nd edition of our Summer School in Computational Social Science that will take place in the beautiful Villa del Grumello on Lake Como between June 22-26, 2026!
*** DEADLINE FOR APPLICATION: February 15, 2026 (firm deadline) ***
More details here:
css2.lakecomoschool.org
*** DEADLINE FOR APPLICATION: February 15, 2026 (firm deadline) ***
More details here:
css2.lakecomoschool.org
November 27, 2025 at 5:21 PM
Happy to announce the 2nd edition of our Summer School in Computational Social Science that will take place in the beautiful Villa del Grumello on Lake Como between June 22-26, 2026!
*** DEADLINE FOR APPLICATION: February 15, 2026 (firm deadline) ***
More details here:
css2.lakecomoschool.org
*** DEADLINE FOR APPLICATION: February 15, 2026 (firm deadline) ***
More details here:
css2.lakecomoschool.org
Reposted by Debora Nozza
#TBT #NLProc '@donyarn.bsky.social & @dirkhovy.bsky.social's 2024 paper, 'Conversations as a Source for Teaching Scientific Concepts' turns video dialogues into effective teaching tools.'
arxiv.org
November 27, 2025 at 4:03 PM
#TBT #NLProc '@donyarn.bsky.social & @dirkhovy.bsky.social's 2024 paper, 'Conversations as a Source for Teaching Scientific Concepts' turns video dialogues into effective teaching tools.'
Reposted by Debora Nozza
Another exhausting day in the lab… conducting very rigorous panettone analysis. Pandoro was evaluated too, because we believe in fair experimental design.
November 27, 2025 at 4:06 PM
Another exhausting day in the lab… conducting very rigorous panettone analysis. Pandoro was evaluated too, because we believe in fair experimental design.
Reposted by Debora Nozza
We're happy to have @veraneplenbroek.bsky.social at our lab this week! She presented her #EMNLP2025 work "Reading Between the Prompts: How Stereotypes Shape LLM's Implicit Personalization" and shared more of her exciting ongoing work.
#NLProc
#NLProc
November 26, 2025 at 1:17 PM
We're happy to have @veraneplenbroek.bsky.social at our lab this week! She presented her #EMNLP2025 work "Reading Between the Prompts: How Stereotypes Shape LLM's Implicit Personalization" and shared more of her exciting ongoing work.
#NLProc
#NLProc