MilaNLP Lab
@milanlp.bsky.social
The Milan Natural Language Processing Group #NLProc #AI
milanlproc.github.io
milanlproc.github.io
#TBT #NLProc
'Detecting Misogynous Memes with Text & Image Modalities' by Attanasio, @deboranozza.bsky.social, Bianchi. Their novel system uses Perceiver IO, surpassing all previous benchmarks.
#AI #ScienceUpdate
aclanthology.org/2022.semeval...
'Detecting Misogynous Memes with Text & Image Modalities' by Attanasio, @deboranozza.bsky.social, Bianchi. Their novel system uses Perceiver IO, surpassing all previous benchmarks.
#AI #ScienceUpdate
aclanthology.org/2022.semeval...
MilaNLP at SemEval-2022 Task 5: Using Perceiver IO for Detecting Misogynous Memes with Text and Image Modalities
Giuseppe Attanasio, Debora Nozza, Federico Bianchi. Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022). 2022.
aclanthology.org
September 17, 2026 at 10:01 AM
#TBT #NLProc
'Detecting Misogynous Memes with Text & Image Modalities' by Attanasio, @deboranozza.bsky.social, Bianchi. Their novel system uses Perceiver IO, surpassing all previous benchmarks.
#AI #ScienceUpdate
aclanthology.org/2022.semeval...
'Detecting Misogynous Memes with Text & Image Modalities' by Attanasio, @deboranozza.bsky.social, Bianchi. Their novel system uses Perceiver IO, surpassing all previous benchmarks.
#AI #ScienceUpdate
aclanthology.org/2022.semeval...
#MemoryModay #NLProc #AI #MachineLearning #SafetyFirst
'Safety-Tuned LLaMAs: Improving LLMs Safety' by Bianchi et al. explores training LLMs for safe refusals, warns of over-tuning.
arxiv.org/pdf/2309.07875
'Safety-Tuned LLaMAs: Improving LLMs Safety' by Bianchi et al. explores training LLMs for safe refusals, warns of over-tuning.
arxiv.org/pdf/2309.07875
Verifying your browser | OpenReview
Please complete the verification above.
openreview.net
September 14, 2026 at 10:01 AM
#MemoryModay #NLProc #AI #MachineLearning #SafetyFirst
'Safety-Tuned LLaMAs: Improving LLMs Safety' by Bianchi et al. explores training LLMs for safe refusals, warns of over-tuning.
arxiv.org/pdf/2309.07875
'Safety-Tuned LLaMAs: Improving LLMs Safety' by Bianchi et al. explores training LLMs for safe refusals, warns of over-tuning.
arxiv.org/pdf/2309.07875
We're back with the reading group!
Today Lorena Calvo-Bartolomé presented "The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs"
Paper: aclanthology.org/2025.acl-lon...
#NLProc #LLMasajudge
Today Lorena Calvo-Bartolomé presented "The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs"
Paper: aclanthology.org/2025.acl-lon...
#NLProc #LLMasajudge
September 10, 2026 at 2:22 PM
We're back with the reading group!
Today Lorena Calvo-Bartolomé presented "The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs"
Paper: aclanthology.org/2025.acl-lon...
#NLProc #LLMasajudge
Today Lorena Calvo-Bartolomé presented "The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs"
Paper: aclanthology.org/2025.acl-lon...
#NLProc #LLMasajudge
#TBT #NLProc
'Understanding Political Discourse on Twitter through Election Manifestos' Maurer et al. (2024) present a method for predicting party positioning from tweets aclanthology.org/2024.finding...
'Understanding Political Discourse on Twitter through Election Manifestos' Maurer et al. (2024) present a method for predicting party positioning from tweets aclanthology.org/2024.finding...
https://arxiv.org/pdf/2403.04445
arxiv.org
September 10, 2026 at 6:00 AM
#TBT #NLProc
'Understanding Political Discourse on Twitter through Election Manifestos' Maurer et al. (2024) present a method for predicting party positioning from tweets aclanthology.org/2024.finding...
'Understanding Political Discourse on Twitter through Election Manifestos' Maurer et al. (2024) present a method for predicting party positioning from tweets aclanthology.org/2024.finding...
#MemoryModay #NLProc Outstanding Paper at ACL 2024! @paul-rottger.bsky.social et al. evaluate LLM values and opinions in 'Political Compass or Spinning Arrow?'
aclanthology.org/2024.acl-lon...
aclanthology.org/2024.acl-lon...
Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models
Paul Röttger, Valentin Hofmann, Valentina Pyatkin, Musashi Hinck, Hannah Kirk, Hinrich Schuetze, Dirk Hovy. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics…
aclanthology.org
September 7, 2026 at 10:01 AM
#MemoryModay #NLProc Outstanding Paper at ACL 2024! @paul-rottger.bsky.social et al. evaluate LLM values and opinions in 'Political Compass or Spinning Arrow?'
aclanthology.org/2024.acl-lon...
aclanthology.org/2024.acl-lon...
We are back with #TBT
#NLProc Best Paper at NeurIPS D&B 2024: Hanna Rose Kirk,
@paul-rottger.bsky.social et al. introduce 'The PRISM Alignment Dataset'
arxiv.org/pdf/2404.16019
#NLProc Best Paper at NeurIPS D&B 2024: Hanna Rose Kirk,
@paul-rottger.bsky.social et al. introduce 'The PRISM Alignment Dataset'
arxiv.org/pdf/2404.16019
arxiv.org
September 3, 2026 at 8:48 AM
We are back with #TBT
#NLProc Best Paper at NeurIPS D&B 2024: Hanna Rose Kirk,
@paul-rottger.bsky.social et al. introduce 'The PRISM Alignment Dataset'
arxiv.org/pdf/2404.16019
#NLProc Best Paper at NeurIPS D&B 2024: Hanna Rose Kirk,
@paul-rottger.bsky.social et al. introduce 'The PRISM Alignment Dataset'
arxiv.org/pdf/2404.16019
Reposted by MilaNLP Lab
Very happy that #IC2S22027 will be in Milan at Università Bocconi!
I’m really looking forward to welcoming the computational social science community to my university and to Milan, and excited to be part of the team organizing it.
See you in 2027! 🇮🇹✨
I’m really looking forward to welcoming the computational social science community to my university and to Milan, and excited to be part of the team organizing it.
See you in 2027! 🇮🇹✨
That's a wrap on IC2S2 2026... we'll see you next year in Milan! 😍
August 7, 2026 at 7:47 AM
Very happy that #IC2S22027 will be in Milan at Università Bocconi!
I’m really looking forward to welcoming the computational social science community to my university and to Milan, and excited to be part of the team organizing it.
See you in 2027! 🇮🇹✨
I’m really looking forward to welcoming the computational social science community to my university and to Milan, and excited to be part of the team organizing it.
See you in 2027! 🇮🇹✨
It was a pleasure to host @radamihalcea.bsky.social at our weekly lab seminar. Thank you for the inspiring talk and thought-provoking discussion on the importance of the long tail in NLP. We really enjoyed the conversation!
July 30, 2026 at 2:05 PM
It was a pleasure to host @radamihalcea.bsky.social at our weekly lab seminar. Thank you for the inspiring talk and thought-provoking discussion on the importance of the long tail in NLP. We really enjoyed the conversation!
#TBT #NLProc
"Narratives at Conflict" by Sinelnik and @dirkhovy.bsky.social looks at hidden tactics of disinformation campaigns! They analyzed 8,000 news articles across 4 languages to reveal how disinformation campaigns adapt narratives for different audiences. 🕵️♀️
aclanthology.org/2024.acl-srw...
"Narratives at Conflict" by Sinelnik and @dirkhovy.bsky.social looks at hidden tactics of disinformation campaigns! They analyzed 8,000 news articles across 4 languages to reveal how disinformation campaigns adapt narratives for different audiences. 🕵️♀️
aclanthology.org/2024.acl-srw...
Narratives at Conflict: Computational Analysis of News Framing in Multilingual Disinformation Campaigns
Antonina Sinelnik, Dirk Hovy. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop). 2024.
aclanthology.org
July 30, 2026 at 6:45 AM
#TBT #NLProc
"Narratives at Conflict" by Sinelnik and @dirkhovy.bsky.social looks at hidden tactics of disinformation campaigns! They analyzed 8,000 news articles across 4 languages to reveal how disinformation campaigns adapt narratives for different audiences. 🕵️♀️
aclanthology.org/2024.acl-srw...
"Narratives at Conflict" by Sinelnik and @dirkhovy.bsky.social looks at hidden tactics of disinformation campaigns! They analyzed 8,000 news articles across 4 languages to reveal how disinformation campaigns adapt narratives for different audiences. 🕵️♀️
aclanthology.org/2024.acl-srw...
#MemoryModay #NLProc
'My Answer is C' by Wang et al. (2024) underscores the scrutiny needed for full text responses in LLMs multi-choice evaluations.
aclanthology.org/2024.finding...
'My Answer is C' by Wang et al. (2024) underscores the scrutiny needed for full text responses in LLMs multi-choice evaluations.
aclanthology.org/2024.finding...
“My Answer is C”: First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models
Xinpeng Wang, Bolei Ma, Chengzhi Hu, Leon Weber-Genzel, Paul Röttger, Frauke Kreuter, Dirk Hovy, Barbara Plank. Findings of the Association for Computational Linguistics: ACL 2024. 2024.
aclanthology.org
July 27, 2026 at 8:01 AM
#MemoryModay #NLProc
'My Answer is C' by Wang et al. (2024) underscores the scrutiny needed for full text responses in LLMs multi-choice evaluations.
aclanthology.org/2024.finding...
'My Answer is C' by Wang et al. (2024) underscores the scrutiny needed for full text responses in LLMs multi-choice evaluations.
aclanthology.org/2024.finding...
Reposted by MilaNLP Lab
Detecting and explaining implicit misogyny, especially in Italian, is still challenging. Also, if you are looking for a truly implicit misogynistic dataset, here's one! 🚀
#TBT #NLProc
'Language is Scary when Over-Analyzed...' by @arimuti.bsky.social et al. explores argumentative reasoning in misogyny detection (2024). Detecting implicit misogyny proves challenging for language models.
aclanthology.org/2024.emnlp-m...
'Language is Scary when Over-Analyzed...' by @arimuti.bsky.social et al. explores argumentative reasoning in misogyny detection (2024). Detecting implicit misogyny proves challenging for language models.
aclanthology.org/2024.emnlp-m...
Language is Scary when Over-Analyzed: Unpacking Implied Misogynistic Reasoning with Argumentation Theory-Driven Prompts
Arianna Muti, Federico Ruggeri, Khalid Al Khatib, Alberto Barrón-Cedeño, Tommaso Caselli. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.
aclanthology.org
July 23, 2026 at 1:15 PM
Detecting and explaining implicit misogyny, especially in Italian, is still challenging. Also, if you are looking for a truly implicit misogynistic dataset, here's one! 🚀
#TBT #NLProc
'Language is Scary when Over-Analyzed...' by @arimuti.bsky.social et al. explores argumentative reasoning in misogyny detection (2024). Detecting implicit misogyny proves challenging for language models.
aclanthology.org/2024.emnlp-m...
'Language is Scary when Over-Analyzed...' by @arimuti.bsky.social et al. explores argumentative reasoning in misogyny detection (2024). Detecting implicit misogyny proves challenging for language models.
aclanthology.org/2024.emnlp-m...
Language is Scary when Over-Analyzed: Unpacking Implied Misogynistic Reasoning with Argumentation Theory-Driven Prompts
Arianna Muti, Federico Ruggeri, Khalid Al Khatib, Alberto Barrón-Cedeño, Tommaso Caselli. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.
aclanthology.org
July 23, 2026 at 1:11 PM
#TBT #NLProc
'Language is Scary when Over-Analyzed...' by @arimuti.bsky.social et al. explores argumentative reasoning in misogyny detection (2024). Detecting implicit misogyny proves challenging for language models.
aclanthology.org/2024.emnlp-m...
'Language is Scary when Over-Analyzed...' by @arimuti.bsky.social et al. explores argumentative reasoning in misogyny detection (2024). Detecting implicit misogyny proves challenging for language models.
aclanthology.org/2024.emnlp-m...
For today's reading group, @veraneplenbroek.bsky.social presented "Old Habits Die Hard: How Conversational History Geometrically Traps LLMs" by Simhi et al. (2026)
Paper: arxiv.org/abs/2603.03308
#NLProc
Paper: arxiv.org/abs/2603.03308
#NLProc
July 16, 2026 at 1:45 PM
For today's reading group, @veraneplenbroek.bsky.social presented "Old Habits Die Hard: How Conversational History Geometrically Traps LLMs" by Simhi et al. (2026)
Paper: arxiv.org/abs/2603.03308
#NLProc
Paper: arxiv.org/abs/2603.03308
#NLProc
Reposted by MilaNLP Lab
Great question. Yes, this should be possible, and we are currently experimenting with this as well in a project. Happy to follow up once we have indications. Feel free to DM
July 13, 2026 at 3:19 PM
Great question. Yes, this should be possible, and we are currently experimenting with this as well in a project. Happy to follow up once we have indications. Feel free to DM
Reposted by MilaNLP Lab
Could not be prouder of @zeerak.bsky.social for this accomplishment: from first paper ever (based on an MSc thesis) to 10-year ToT award.
We could not have anticipated the lasting impact of this paper, but it's a great honor – and a wonderful story for any student/advisor team (see Zee's thread).
We could not have anticipated the lasting impact of this paper, but it's a great honor – and a wonderful story for any student/advisor team (see Zee's thread).
Thrilled to have been awarded the Association for Computational Linguistics 2016 test of time award for my first ever paper, written with/under the guidance of @dirkhovy.bsky.social
A couple of cute things about the paper/its genesis/its outcomes
A couple of cute things about the paper/its genesis/its outcomes
July 11, 2026 at 1:05 PM
Could not be prouder of @zeerak.bsky.social for this accomplishment: from first paper ever (based on an MSc thesis) to 10-year ToT award.
We could not have anticipated the lasting impact of this paper, but it's a great honor – and a wonderful story for any student/advisor team (see Zee's thread).
We could not have anticipated the lasting impact of this paper, but it's a great honor – and a wonderful story for any student/advisor team (see Zee's thread).
#MemoryModay #NLProc
Fornaciari et al.'s 2022 'Hard and Soft Evaluation of NLP models with BOOtSTrap SAmpling - BooStSa' is a useful Python tool for benchmarking NLP predictions with bootstrapped sampling.
aclanthology.org/2022.acl-dem...
Fornaciari et al.'s 2022 'Hard and Soft Evaluation of NLP models with BOOtSTrap SAmpling - BooStSa' is a useful Python tool for benchmarking NLP predictions with bootstrapped sampling.
aclanthology.org/2022.acl-dem...
Hard and Soft Evaluation of NLP models with BOOtSTrap SAmpling - BooStSa
Tommaso Fornaciari, Alexandra Uma, Massimo Poesio, Dirk Hovy. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations. 2022.
aclanthology.org
July 13, 2026 at 10:01 AM
#MemoryModay #NLProc
Fornaciari et al.'s 2022 'Hard and Soft Evaluation of NLP models with BOOtSTrap SAmpling - BooStSa' is a useful Python tool for benchmarking NLP predictions with bootstrapped sampling.
aclanthology.org/2022.acl-dem...
Fornaciari et al.'s 2022 'Hard and Soft Evaluation of NLP models with BOOtSTrap SAmpling - BooStSa' is a useful Python tool for benchmarking NLP predictions with bootstrapped sampling.
aclanthology.org/2022.acl-dem...
🧠🤖 It was a pleasure to host @andreadevarda.bsky.social for his talk, "Large Language Models as Models of Human Language(s) and Higher-Level Cognition." A truly inspiring talk!
#NLProc
#NLProc
July 13, 2026 at 9:48 AM
🧠🤖 It was a pleasure to host @andreadevarda.bsky.social for his talk, "Large Language Models as Models of Human Language(s) and Higher-Level Cognition." A truly inspiring talk!
#NLProc
#NLProc
🏆 Congrats to @zeerak.bsky.social and @dirkhovy.bsky.social on the 2016 Test of Time Award! 🎉
"Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter" has shaped research on #hatespeech!
Paper: aclanthology.org/N16-2013/
#NLProc
"Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter" has shaped research on #hatespeech!
Paper: aclanthology.org/N16-2013/
#NLProc
July 13, 2026 at 9:27 AM
🏆 Congrats to @zeerak.bsky.social and @dirkhovy.bsky.social on the 2016 Test of Time Award! 🎉
"Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter" has shaped research on #hatespeech!
Paper: aclanthology.org/N16-2013/
#NLProc
"Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter" has shaped research on #hatespeech!
Paper: aclanthology.org/N16-2013/
#NLProc
July 10, 2026 at 3:20 PM
For our last reading group, @pranav-nlp.bsky.social presented "Enhancing University Curricula with Integrated AI Ethics Education: A Comprehensive Approach" by Deb et al. (2025)
Link: dl.acm.org/doi/10.1145/...
#AIEthics #NLProc
Link: dl.acm.org/doi/10.1145/...
#AIEthics #NLProc
July 10, 2026 at 8:38 AM
For our last reading group, @pranav-nlp.bsky.social presented "Enhancing University Curricula with Integrated AI Ethics Education: A Comprehensive Approach" by Deb et al. (2025)
Link: dl.acm.org/doi/10.1145/...
#AIEthics #NLProc
Link: dl.acm.org/doi/10.1145/...
#AIEthics #NLProc
#TBT #NLProc
Bergman et al.'s 'Guiding the Release of Safer E2E Conversational AI through Value Sensitive Design' explores AI launch with a value-sensitive lens.
aclanthology.org/2022.sigdial...
Bergman et al.'s 'Guiding the Release of Safer E2E Conversational AI through Value Sensitive Design' explores AI launch with a value-sensitive lens.
aclanthology.org/2022.sigdial...
Guiding the Release of Safer E2E Conversational AI through Value Sensitive Design
A. Stevie Bergman, Gavin Abercrombie, Shannon Spruit, Dirk Hovy, Emily Dinan, Y-Lan Boureau, Verena Rieser. Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and…
aclanthology.org
July 9, 2026 at 10:01 AM
#TBT #NLProc
Bergman et al.'s 'Guiding the Release of Safer E2E Conversational AI through Value Sensitive Design' explores AI launch with a value-sensitive lens.
aclanthology.org/2022.sigdial...
Bergman et al.'s 'Guiding the Release of Safer E2E Conversational AI through Value Sensitive Design' explores AI launch with a value-sensitive lens.
aclanthology.org/2022.sigdial...
#MemoryMonday #NLProc
'Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists' by Attanasio et al. redefines bias reduction in #AI, sans prior term knowledge.
#2022Publication aclanthology.org/2022.finding...
'Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists' by Attanasio et al. redefines bias reduction in #AI, sans prior term knowledge.
#2022Publication aclanthology.org/2022.finding...
Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists
Giuseppe Attanasio, Debora Nozza, Dirk Hovy, Elena Baralis. Findings of the Association for Computational Linguistics: ACL 2022. 2022.
aclanthology.org
July 6, 2026 at 10:02 AM
#MemoryMonday #NLProc
'Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists' by Attanasio et al. redefines bias reduction in #AI, sans prior term knowledge.
#2022Publication aclanthology.org/2022.finding...
'Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists' by Attanasio et al. redefines bias reduction in #AI, sans prior term knowledge.
#2022Publication aclanthology.org/2022.finding...
Reposted by MilaNLP Lab
Very happy to have given my first keynote at an #NLProc related conference!
This morning at CORIA-TALN 2026 in Nantes, I talked about emerging risks and research directions around the everyday use of LLMs.
coria-taln-2026.ls2n.fr/conferences-...
This morning at CORIA-TALN 2026 in Nantes, I talked about emerging risks and research directions around the everyday use of LLMs.
coria-taln-2026.ls2n.fr/conferences-...
July 2, 2026 at 2:59 PM
Very happy to have given my first keynote at an #NLProc related conference!
This morning at CORIA-TALN 2026 in Nantes, I talked about emerging risks and research directions around the everyday use of LLMs.
coria-taln-2026.ls2n.fr/conferences-...
This morning at CORIA-TALN 2026 in Nantes, I talked about emerging risks and research directions around the everyday use of LLMs.
coria-taln-2026.ls2n.fr/conferences-...
For today's reading group, @esradonmez.bsky.social presented "RLHF May Not Reflect Genuine Preferences" by Ghafouri et al. (2026).
Interesting thoughts on whether annotations are actually real preferences!
Paper: arxiv.org/abs/2604.03238
#NLProc #RLHF
Interesting thoughts on whether annotations are actually real preferences!
Paper: arxiv.org/abs/2604.03238
#NLProc #RLHF
July 2, 2026 at 10:36 AM
For today's reading group, @esradonmez.bsky.social presented "RLHF May Not Reflect Genuine Preferences" by Ghafouri et al. (2026).
Interesting thoughts on whether annotations are actually real preferences!
Paper: arxiv.org/abs/2604.03238
#NLProc #RLHF
Interesting thoughts on whether annotations are actually real preferences!
Paper: arxiv.org/abs/2604.03238
#NLProc #RLHF
#TBT #NLProc
Hessenthaler et al.'s 2022 work delves into AI's link with fairness & energy reduction in English NLP models, challenging bias reduction theories. #AI #NLP #sustainability aclanthology.org/2022.emnlp-m...
Hessenthaler et al.'s 2022 work delves into AI's link with fairness & energy reduction in English NLP models, challenging bias reduction theories. #AI #NLP #sustainability aclanthology.org/2022.emnlp-m...
Bridging Fairness and Environmental Sustainability in Natural Language Processing
Marius Hessenthaler, Emma Strubell, Dirk Hovy, Anne Lauscher. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022.
aclanthology.org
July 2, 2026 at 10:01 AM
#TBT #NLProc
Hessenthaler et al.'s 2022 work delves into AI's link with fairness & energy reduction in English NLP models, challenging bias reduction theories. #AI #NLP #sustainability aclanthology.org/2022.emnlp-m...
Hessenthaler et al.'s 2022 work delves into AI's link with fairness & energy reduction in English NLP models, challenging bias reduction theories. #AI #NLP #sustainability aclanthology.org/2022.emnlp-m...