Assistant Professor @coastalcph @DIKU_Institut, University of Copenhagen. Interests: meaning, multiculturalism and promoting responsible behavior with #NLProc
Copenhagen, Denmark
Joined October 2008
- Tweets385
- Following1.7K
- Followers1K
- Likes1.7K
How good are LLMs at cultural reasoning? Can we make them better? And what does “better” even mean when interpretation is ambiguous and people disagree?
I’m hiring a PhD to work on this with literary scholars.
Deadline: 8 Nov 2026
Start: 1 Feb 2027
candidate.hr-manager.net/App…
Daniel Hershcovich retweeted
📢 Can AI understand how to persuades us?
We are excited to announce the Visual Persuasion (VisPer) workshop at @eccvconf
📄 Submit your work and join us in Malmö 🇸🇪!
⏳Deadline: July 15, 2026
🔗sites.google.com/view/eccv-2…
Topics include (but not limited to):
✨ Visual persuasion & communication
✨ Multimodal reasoning
✨ Personalization
✨ Persuasive image & video generation
✨ Creativity, symbolism & metaphor
✨ Evaluation and benchmarks for visual persusion
✨ Advertisement understanding and generation
✨ Ethics and cultural impact in persuasion
✨ Detection of manipulative content
#ECCV2026
Daniel Hershcovich retweeted
📢 Paper submissions are still open for the Visual Persuasion Workshop @eccvconf! Deadline extended to July 29.
We welcome archival & non-archival papers on persuasive AI, personalization, creativity, visual misinformation & fake news, cross-cultural persuasion, fairness, and more.
Submit your work, we'd love to see it!
📢 Can AI understand how to persuades us?
We are excited to announce the Visual Persuasion (VisPer) workshop at @eccvconf
📄 Submit your work and join us in Malmö 🇸🇪!
⏳Deadline: July 15, 2026
🔗sites.google.com/view/eccv-2…
Topics include (but not limited to):
✨ Visual persuasion & communication
✨ Multimodal reasoning
✨ Personalization
✨ Persuasive image & video generation
✨ Creativity, symbolism & metaphor
✨ Evaluation and benchmarks for visual persusion
✨ Advertisement understanding and generation
✨ Ethics and cultural impact in persuasion
✨ Detection of manipulative content
#ECCV2026
Daniel Hershcovich retweeted
📚 Please also stay tuned to hear from our incredible authors on the latest in cross cultural NLP research as they discuss:
🔹 Whose Culture? Representing Values, Norms, and Lived Knowledge in AI
🔹 Building and Benchmarking Culturally-Aware Systems
#C3NLP2026
Daniel Hershcovich retweeted
📢 Joining #ACL2026 tomorrow? Don't miss the C3NLP Workshop!
We've got an incredible lineup of talks, panels, and papers scheduled. Come chat, connect, and collaborate with us!
🗓️ Check out the full schedule & plan your day here: c3nlp.github.io/#schedule
#NLP #NLProc
Daniel Hershcovich retweeted
We’re extending our direct submission deadline to March 27, 2026!
Workshop details: c3nlp.github.io/
#NLProc #CulturalNLP #ACL2026
The direct submission deadline is this Friday! Looking forward to receiving your submissions 🤗
@c3_nlp We are back for the 4th year in a row with the Workshop on Cross-Cultural Considerations in NLP at #ACL2026NLP!
c3nlp.github.io/
Our workshop brings a real interdisciplinary exchange, to figure out how to build models that don't just erase cultural differences.
Daniel Hershcovich retweeted
@c3_nlp We are back for the 4th year in a row with the Workshop on Cross-Cultural Considerations in NLP at #ACL2026NLP!
c3nlp.github.io/
Our workshop brings a real interdisciplinary exchange, to figure out how to build models that don't just erase cultural differences.
Daniel Hershcovich retweeted
Our paper ImageChain (with @IngoZiegler & @delliott) was accepted at #WACV2026!
We explore how multimodal LLMs reason over sequences of images
I’ll present it at the @_LXAI Workshop @NeurIPS 🇲🇽 (Nov 30 ~10:45 Mex City).
Come chat if you’re there! 🫶
📄 arxiv.org/abs/2502.19409
Daniel Hershcovich retweeted
Can we find weight directions to modify LLM's behaviors?
Our new paper proposes contrastive weight steering, an alternative to activation steering for modifying behaviors using small narrow distribution data 🕹️
🧵👇
Daniel Hershcovich retweeted
New preprint: "Decoding Alignment: A Critical Survey of LLM Development Initiatives through Value-setting and Data-centric Lens" 🔍 Beyond a survey, this is a presentation of a series of concerns on what we could frame as "corporate" alignment #llms #ai arxiv.org/abs/2508.16982
Daniel Hershcovich retweeted
New Preprint 🎉: "Cultural Evaluations of Vision-Language Models Have a Lot to Learn from Cultural Theory". We review recent works on culture in VLMs and argue for deeper grounding in cultural theory to enable more inclusive evaluations.
Paper 🔗: arxiv.org/pdf/2505.22793
This talk and panel are starting now - crucial anthropological insights for NLP!
This incredible workshop is starting now! Join at room "Pecos" if you're at @naaclmeeting
📣 Excited about our Cross Cultural Considerations in NLP workshop! @c3_nlp @ @naaclmeeting coming up in no time—just two weeks to go!
Full program here: c3nlp.github.io
Co-org. w/ @sunipa17 @LucianaBenotti @daniel_hers @vinodkpg @YongCaoPlus @LiZhou21 @IfeAdebara ❤️
Daniel Hershcovich retweeted
@YongCaoPlus Haijiang Liu, @rnav_arora @IAugenstein @paul_rottger @daniel_hers
Specializing Large Language Models to Simulate Survey Response Distributions for Global Populations.
arxiv.org/abs/2502.07068
#NAACL2025 #NLProc
xitter.cf/YongCaoPlus/status/189…
🎉 Excited to share our NAACL main paper on simulating survey response distributions via first-token alignment fine-tuning. Many thanks to our collaborators: Haijiang Liu, @rnav_arora @IAugenstein @paul_rottger and @daniel_hers. More details, paper link and code, see below👇
Daniel Hershcovich retweeted
📣 Excited about our Cross Cultural Considerations in NLP workshop! @c3_nlp @ @naaclmeeting coming up in no time—just two weeks to go!
Full program here: c3nlp.github.io
Co-org. w/ @sunipa17 @LucianaBenotti @daniel_hers @vinodkpg @YongCaoPlus @LiZhou21 @IfeAdebara ❤️
We are hiring a law+NLP postdoc in Copenhagen! Deadline April 7:
jobportal.ku.dk/videnskabeli…
Daniel Hershcovich retweeted
🎉 Excited to share our NAACL main paper on simulating survey response distributions via first-token alignment fine-tuning. Many thanks to our collaborators: Haijiang Liu, @rnav_arora @IAugenstein @paul_rottger and @daniel_hers. More details, paper link and code, see below👇
Daniel Hershcovich retweeted
📢Happy to share our paper "Does Mapo Tofu Contain Coffee? Probing LLMs for Food-related Cultural Knowledge" has been accepted to #NAACL2025 main!
Work with Taelin Karidi, Wanlong Liu, @nGarneau @YongCaoPlus , Wenyu Chen, Haizhou Li, @daniel_hers
arxiv.org/pdf/2404.06833
