Natural Language Processing has seen impressive gains in recent years. This research includes the demonstration by NLP models to have turned into useful technologies with improved capabilities, measured in terms of how well they match human behavior captured in web-scale language data or through annotations. However, human behavior is inherently shaped by the cultural contexts humans are embedded in, the values and beliefs they hold, and the social practices they follow, part of which will be reflected in the data used to train NLP models, and the behavior these NLP models exhibit. Not accounting for this factor could cause incongruencies and misalignments between the cultural contexts that underpin the NLP model development process and the multi-cultural ecosystems they are expected to operate in. These misalignments may result in various harms, including barriers to those from under-represented cultures, violating cultural norms and values, and erasure of cultural knowledge.
While recent work in the field has started to acknowledge this issue, it is important to build a long-term research agenda for the NLP community around (1) deeper understanding of how global cultures and NLP technologies intersect, in a way that goes beyond multi-lingual and cross-lingual research, (2) how to detect, measure, and attempt to mitigate potential biases and harms in NLP technology in ways that reflect local cultures and values, and (3) how to build more cross-culturally competent NLP systems. This agenda requires looking beyond the NLP community, bringing in multi-disciplinary expertise to shape the inquiries in this important area.
We propose this workshop as a way to bring together the growing number of NLP researchers interested in this topic, along with a community of scholars with multi-disciplinary expertise spanning linguistics, social sciences, and cultural anthropology. Our aim is to build this important inquiry within NLP on a solid basis of cultural theories from social sciences. To this end, the workshop program will focus on the following themes: Inclusivity and Representation of cultures in NLP, Cultural harms of NLP technologies, and Culture Sensitive lens on Social Biases and Harms in NLP. We invite papers on topics including the following (but not limited to):
Requirements for Direct Submission: Both short papers and long papers are welcome, and must follow all of the NAACL paper submission requirements.
Submission Link:
Event | Date |
---|---|
Full peer-review (Archival and Non-archival) | Submission deadline: |
Notification of acceptance: March 1, 2025 | |
Camera-ready paper due: March 10, 2025 | |
Already peer-reviewed through ARR | Last ARR submission deadline: Dec 15th, 2024 |
Commitment deadline: February 20, 2025 | |
Notification of acceptance: |
|
paper due: |
|
Already accepted/published (Non-archival) | Submission deadline: March 18, 2025 |
Notification of acceptance: March 25, 2025 | |
Workshop | Registration: Link (Early registration deadline: April 7, 2025) |
Workshop: May 4, 2025 |
All deadlines are 23:59 UTC -12h (anywhere on earth) unless stated otherwise.
Elisabeth A. Mager Hois holds a Bachelor's degree in Pedagogy (University of Munich, 1971), a Bachelor’s degree in Social Anthropology (ENAH, 2004), a Master's degree in Mexico-United States Studies (UNAM, 2001), and a PhD in Anthropology (UNAM, 2008). She is a national researcher at the SNI (National Institute of National Research) and a Professor-Researcher of German at the FES Acatlán-UNAM. She won the CISAN Award (2009) and the Honorable Mention of the Aguirre Beltrán Chair by CIESAS of the Gulf and the University of Veracruz (2010). She has published several books: Struggle and Resistance of the Kickapoo Tribe, Kickapoo, Casinos and Power: The Kickapoo Lucky Eagle Casino Case, and Relationship between Dialectics and Social Consciousness in the Poetry of Bertolt Brecht, among others. She has written several articles and book chapters on group cohesion, assimilation, cultural assimilation, resistance and ethnic consciousness, migration, ideology and power, and polysynthetic languages, among others.
Title: Cultural Differences and Changes Among Native Americans and Their Importance for NLP
Abstract: In this talk, we present the cultural differences and changes among indigenous peoples compared to Western cultures. We will begin with a broad overview of key indigenous cultural aspects before focusing on specific case studies: the Kickapoo, Cahuilla, Wixárika, and Rarámuri communities. Here, we analyze some aspects of the political-religious structure (relationship between spirituality and politics), the social-ceremonial structure, and the socioeconomic activity of these peoples, as well as their changes over time. Ethical considerations are also of great importance when it comes to research on indigenous peoples. This also applies to research done for NLP. The traditions and beliefs of the different tribes and communities must be taken into account. The key is not to consider indigenous peoples as objects of research but rather to create a balance and integrate them into projects. Therefore, it is important that the researcher understands the culture of the indigenous communities to achieve objective results.
Monojit Choudhury is a professor of Natural Language Processing at Mohommed Bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi. Prior to this, he was a principal scientist at Microsoft Research India and Microsoft Turing. Prof Choudhury's research interests lie in the intersection of NLP, Social and Cultural aspects of Technology use, and Ethics. In particular, he has been working on multilingual and multicultural aspects of large language models (LLMs), their use in low resource languages and making LLMs more inclusive and safer. Prof Choudhury takes a keen interest in popularizing linguistics and AI through puzzle solving; he is the general chair of Indian national linguistics Olympiad, the founding co-chair of Asia-Pacific linguistics Olympiad, and a founding board-member of International AI Olympiad. He holds a BTech and PhD degree in Computer Science and Engineering from IIT Kharagpur.
Title: Culturally Aware Machines: Why and when are they useful?
Abstract: Language, culture, and technology are deeply intertwined; any technology that aims to process or generate language must have a nuanced understanding of culture. Yet, culture is elusive, often defying concrete definition, which poses a profound challenge to NLP and AI research. While the NLP community has acknowledged this fact and taken initial steps by developing culture-specific benchmarks and identifying biases in large language models (LLMs), there remains a gap in addressing why cultural understanding matters for machines, and the real-world impact on users of culturally (un)aware machines. In this talk, I will ask and attempt to answer the following three questions: (1) What can we do better with AI systems that are culturally aware? (2) Why is modeling culture so complex, and what can we learn from psychology and anthropology? (3) How can LLMs, in turn, be leveraged as tools for studying and enhancing our understanding of cultures?
Lise M. Dobrin received her PhD in Linguistic from the University of Chicago in 1999. Her 2012 book Concreteness in Grammar: The Noun Class Systems of the Arapesh Languages is based on fifteen months of dissertation field research in Wautogik village, Papua New Guinea. While continuing to build a documentary linguistic corpus for Arapesh (archived texts and lexicon; see www.arapesh.org), Dobrin publishes on the role of culture in endangered language linguistics, field methods, ethics, and language shift; representations of Arapesh culture in the history of anthropology; and Arapesh ethnohistory and ethnography. She teaches in the Department of Anthropology and Linguistics Program at the University of Virginia. She edits the journal Language Documentation and Description.
Title: Engagement and Access in Language Work Across Cultures
Abstract: Language research and development now often aim to proceed in a community-engaged way out of an awareness that local linguistic communities are diverse and disempowered. But what will it take to make the products of language work truly accessible across the world’s full range of settings and cultures? In this presentation I share insights gained through nearly thirty years work with Arapesh people in the Pacific island nation of Papua New Guinea (PNG). PNG is famous for its dramatic linguistic diversity while also being ill-positioned to take advantage of even the most basic linguistic resources and services, and this despite nearly a century of eager missionary and academic linguistic attention. The reasons for this are both infrastructural and cultural, in surprising ways that I will elucidate. Challenges to access are especially unfortunate in PNG, where language shift from local vernaculars like Arapesh to languages of wider communication is now “rampant” (Evans 2010, Kulick and Dobrin in press). Building from the PNG case study, I argue that linguists need an expanded imagination of what community engagement and cultural access might really require.
Ekaterina Shutova is an Associate Professor at the ILLC, University of Amsterdam and a Visiting Associate Professor at Stanford University. At the ILLC, she leads the Amsterdam Natural Language Understanding Lab and the Natural Language Processing & Digital Humanities research unit. She received her PhD from the University of Cambridge, and then worked as a research scientist at the University of California, Berkeley. Ekaterina’s current research focuses on multilingual and multicultural NLP, generalisability and robustness of NLP models and LLM alignment. Her prominent service roles include Program Chair of ACL 2025, Senior Action Editor of ACL Rolling Review, Action Editor of Computational Linguistics and Demonstrations chair at EMNLP 2022. She is also an ELLIS scholar.
Title: Cultural value alignment in multilingual and multimodal language models
Abstract: Multilingual language models (MLMs) are trained on the concatenation of text from a wide variety of languages spoken in the world, and thus we can expect different, and perhaps opposing, cultural values to be encoded in them simultaneously. This necessitates MLMs to become inherently multicultural as well in order to appropriately serve culturally diverse communities. In this talk, I will discuss our recent research on cultural value alignment in MLMs, addressing this topic from two perspectives: (1) investigating cultural value shifts during MLM fine-tuning in different languages; and (2) steering cultural value alignment via in-context learning at inference time. In the final study, I will shift the focus to vision-language models, investigating the role of visual information in encoding cultural cues relevant to alignment. I will then discuss the implications of our findings for the design of LLM alignment methods.
Isabelle Augenstein is a Professor at the University of Copenhagen, Department of Computer Science, where she heads the Copenhagen Natural Language Understanding research group as well as the Natural Language Processing section. Her main research interests are fair and accountable NLP, including challenges such as explainability, factuality and bias detection. Prior to starting a faculty position, she was a postdoctoral researcher at University College London, and before that a PhD student at the University of Sheffield. In October 2022, Isabelle Augenstein became Denmark’s youngest ever female full professor. She currently holds a prestigious ERC Starting Grant on 'Explainable and Robust Automatic Fact Checking', as well as the Danish equivalent of that, a DFF Sapere Aude Research Leader fellowship on 'Learning to Explain Attitudes on Social Media’. She is a member of the Royal Danish Academy of Sciences and Letters, and co-leads the Danish Pioneer Centre for AI.
Title: Measuring cultural biases in LLM generations
Abstract: TBD
Staff Research Scientist
Google Research
Senior Research Scientist
Google Research
Associate Professor
Universidad Nacional de Córdoba
Assistant Professor
University of Copenhagen
PhD Student
University of Copenhagen
Postdoc Researcher
University of Tübingen
PhD Student
University of British Columbia
Postdoc Researcher
The Chinese University of Hong Kong, Shenzhen
Nikola Ljubešić - Jožef Stefan Institute
Nithish Kannen - Google DeepMind
Michael Bloodgood - The College of New Jersey
Aida Mostafazadeh Davani - Research, Google
Kevin Robinson - Google
Bin Wang - I2R, A*STAR
Shravan Nayak - Université de Montréal
Steven R Wilson - University of Michigan - Flint
Mehar Bhatia - Mila - Quebec Artificial Intelligence Institute
Charvi Rastogi - Google
Agrima Seth - University of Michigan - Ann Arbor
Kiki Ferawati - Universitas Sebelas Maret
Sunny Rai - University of Pennsylvania
Aubrie Amstutz - Apple
Sidney Wong - University of Canterbury
A. Seza Doğruöz - Ghent University
Partha Talukdar - Google Research
Preetam Prabhu Srikar Dammu - University of Washington
Taelin Karidi - Hebrew University of Jerusalem
Guijin Son - Yonsei University
Razan Baltaji - University of Illinois at Urbana Champaign
Alice Oh - KAIST
Nathan Oken Hodas - Information Sciences Institute
Kristen Johnson - Michigan State University
Luis Chiruzzo - Universidad de la República - Uruguay
Dan Simonson - BlackBoiler, Inc.
Laura Alonso Alemany - Universidad Nacional de Córdoba
Shangrui Nie - Universität Bonn
Rifki Afina Putri - Universitas Gadjah Mada
Junho Myung - KAIST
Valerio Basile - University of Turin
Dipankar Srirag - University of New South Wales
Nisansa de Silva - University of Moratuwa
Siddhesh Milind Pawar - Copenhagen University
Dan Goldwasser - Purdue University
Yuu Jinnai - CyberAgent, Inc.
Nayeon Lee - KAIST
Akhila Yerukola - Carnegie Mellon University
Shreya Havaldar - University of Pennsylvania
Nedjma Ousidhoum - Cardiff University
Shaily Bhatt - Carnegie Mellon University
Steve DeNeefe - RWS Language Weaver
Platinum ($3,000)
This is a great way to position your company or organisation as a thought leader in the field of cross-cultural considerations in NLP,
signalling to researchers, civil society, competitors and buyers your commitment to furthering social-oriented research that benefits all of us.
Your company name will feature in our recordings, on the website and in the Proceedings. We will explicitly acknowledge and thank you for your support of
C3NLP@NAACL.
Gold ($2,000)
This is our mid-tiered package and will still give you great exposure to our attendees. Unlike Platinum, the company logos will be sized slightly smaller. But you will still get access to the community and be able to demonstrate your commitment to the topic.
Silver ($1,000)
This is our smallest package and is an excellent way to first explore the C3NLP community and learn more about our exciting programme of research. With all packages, you are able to meet with the Workshop organisers and find out more about how to position your company within C3NLP, which can be particularly useful for first-time sponsors.
LLM Alignment for the Arabs: A Homogenous Culture or Diverse Ones.
Multi-Step Reasoning in Korean and the Emergent Mirage
Fair Summarization: Bridging Quality and Diversity in Extractive Summaries
InspAIred: Cross-cultural Inspiration Detection and Analysis in Real and LLM-generated Social Media Data
DaKultur: Evaluating the Cultural Awareness of Language Models for Danish with Native Speakers
Korean Stereotype Content Model: Translating Stereotypes Across Cultures
LLM-C3MOD: A Human-LLM Collaborative System for Cross-Cultural Hate Speech Moderation
One world, one opinion? The superstar effect in LLM responses
Towards Region-aware Bias Evaluation Metrics
Cross-Cultural Differences in Mental Health Expressions on Social Media
WHEN TOM EATS KIMCHI: Evaluating Cultural Awareness of Multimodal Large Language Models in Cultural Mixture Contexts
Diffusion Models Through a Global Lens: Are They Culturally Inclusive?
Detecting Offensive Memes with Social Biases in Singapore Context Using Multimodal Large Language Model
Hire Your Anthropologist! Towards Cultural Benchmarks Through an Anthropological Lens
Uplifting Lower-Income Data: Strategies for Socioeconomic Perspective Shifts in Large Multi-modal Models
Evaluating Cultural and Social Awareness of LLM Web Agents
Specializing Large Language Models to Simulate Survey Response Distributions for Global Populations
Culture-TRIP: Culturally-Aware Text-to-Image Generation with Iterative Prompt Refinement
Multi3Hate: Multimodal, Multilingual, and Multicultural Hate Speech Detection with Vision-Language Models
Designing Speech Technologies for Australian Aboriginal English: Opportunities, Risks and Participation
IndoCulture: Exploring Geographically Influenced Cultural Commonsense Reasoning Across Eleven Indonesian Provinces
Beyond Words: Exploring Cultural Value Sensitivity in Multimodal Models
Mind the Gesture: Evaluating AI Sensitivity to Culturally Offensive Non-Verbal Gestures
HistoryRE: A Reasoning-Guided and Knowledge-Enhanced Prompt Learning Approach for Relation Extraction in Ancient Chinese Documents
Check out the proceedings from previous years!
Feel free to reach out if you have any questions or suggestions.
c3nlp.committee@gmail.com
yong.cao@uni-tuebingen.de
on Twitter
on Bluesky