Topics

Bias, Fairness & Culture

AI systems learn from data that carries our biases, hierarchies and cultural assumptions. These conversations cover how researchers find, measure and reduce bias, and how to build models that work fairly for people across cultures.

6 episodes · 5 conference interviews

From Hate Speech to Best Paper: Building Safer AI Systems, with Dr. Saadia Gabriel (Part 1)

Episode 20

From Hate Speech to Best Paper: Building Safer AI Systems, with Dr. Saadia Gabriel (Part 1)

April 15, 2026 · 29 min · WiAIR Podcast • Season 2

What does it mean to build AI systems we can actually trust? In this first part of our conversation with Saadia Gabriel (UCLA), we explore the deeply personal and technical journey behind her work on AI safety, misuse, and responsible NLP. From experiencing targeted hate speech firsthand to receiving a best paper nomination, Saadia shares how her lived experience shaped her research — and why language models must be designed with both capability and risk in mind. 🧠 In this episode, we cover: • How personal experiences influence AI research directions • The intersection of NLP, security, and privacy • Why LLMs can be both powerful and dangerous • What it means to build trustworthy AI systems • Lessons from working across multiple research paradigms • How to pursue high-impact research as a PhD or early-career scientist Timestamps: 00:00 - Introduction of Saadia Gabriel and episode overview 00:54 - Influence of dual mentorship on research approach 03:42 - The purpose and vision of the MARS lab 06:23 - Women and underrepresented groups' focus on harm and toxicity issues 11:02 - AI safety vs. AI ethics: interconnected but distinct realms 14:33 - How the concept of AI safety is evolving with adversarial testing 15:56 - The origins of multi-turn jailbreaking research 19:21 - Why multi-turn attacks outperform single-turn methods 22:28 - Role and impact of optimization in attack depth and breadth 24:40 - Strategies for mitigating conversational and multi-turn system vulnerabilities Resources & Links: • X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents (arxiv.org/abs/2504.13203) Connect with Dr. Saadia Gabriel: • x.com/GabrielSaadia • bsky.app/profile/skgabrie.bsky.social

How Does AI Reflect Society, with Dr. Maria Antoniak

Episode 14

How Does AI Reflect Society, with Dr. Maria Antoniak

December 10, 2025 · 1 h 12 min · WiAIR Podcast • Season 1

AI doesn’t just process text — it takes in our cultures, reflects our hierarchies, and can make existing power structures even stronger. In this episode of Women in AI Research, Jekaterina Novikova and Malikeh Ehgaghi speak with Dr. Maria Antoniak (Assistant Professor at the University of Colorado Boulder) about inclusivity in AI, the dynamics of cultural representation, what trust in AI really means, why LLMs tend to homogenize research cultures, and what maternal healthcare reveals about the deepest ethical challenges in this field. Don't have time for the full episode? Watch it in parts: Part 1 - youtu.be/YLguztL14Y Part 2 - youtu.be/Io_syVZjYg8 Part 3 - youtu.be/UOy_Qsui5ag CHAPTERS: 00:00 Introduction to Women in AI Research Podcast 00:33 Guest introduction - Dr. Maria Antoniak 02:58 Inclusivity in AI 05:55 AI for Humanists: Bridging the Gap 08:29 Connection to Ukraine: Values and Lessons 13:45 Trust and Privacy in AI Interactions 14:39 Personal Disclosures in AI Conversations 22:38 Taxonomy of Sensitive Information 25:16 Researcher Perspectives on AI Usage 28:52 Cultural Representation in AI Systems 35:52 Cultural NLP and Its Challenges 37:42 Evaluating Cultural Alignment in AI 43:09 Cultural Evaluation Methods in Research 47:41 AI in Maternal and Reproductive Health 51:05 Guiding Principles for AI in Maternal Health 54:10 Engaging Stakeholders in Healthcare AI 01:02:35 Enhancing Agency in Healthcare AI 01:06:22 Learning from Maternal Health Traditions REFERENCES: 17:25 Trust No Bot (arxiv.org/abs/2407.11438) 24:14 A Large-Scale Analysis of Public-Facing, Community-Built Chatbots on Character.AI (arxiv.org/abs/2505.13354) 28:57 LLMs as Rsearch Tools (arxiv.org/abs/2411.05025) 36:03 Culture is Not Trivia (arxiv.org/abs/2502.12057) 37:48 Research Borderlands (arxiv.org/abs/2506.00784) 50:54 NLP for Maternal Healthcare (dl.acm.org/doi/abs/10.1145/3630106.3658982) 01:00:03 Data Feminism (data-feminism.mitpress.mit.edu/) 01:04:10 Epistemic Diversity and Knowledge Collapse in Large Language Models (arxiv.org/abs/2510.04226) 01:09:21 Empire of AI (penguinrandomhouse.com/books/743569/empire-of-ai-by-karen-hao/) 🎧 Subscribe to stay updated on new episodes spotlighting brilliant women shaping the future of AI. WiAIR website: ♾️ women-in-ai-research.github.io Follow us at: ♾️ LinkedIn: linkedin.com/company/women-in-ai-research/ ♾️ Bluesky: bsky.app/profile/wiair.bsky.social ♾️ X (Twitter): x.com/WiAIR_podcast #AI #NLP #LLMs #AIbias #WomenInAI #AIResearch #CulturalAnalytics #WomenInAIResearch #EthicalAI #wiair #wiairpodcast #SocietyAndAI

Why AI Doesn’t Understand Your Culture? Dr. Vered Shwartz on Cultural Bias in LLMs

Episode 12

Why AI Doesn’t Understand Your Culture? Dr. Vered Shwartz on Cultural Bias in LLMs

October 29, 2025 · 1 h 17 min · WiAIR Podcast • Season 1

Are today’s AI systems truly global — or just Western by design? 🌍 In this episode of Women in AI Research, Jekaterina Novikova and Malikeh Ehgaghi speak with Dr. Vered Shwartz (Assistant Professor at @UBC and CIFAR AI Chair at the @vectorinstituteai about the cultural blind spots in today’s large language and vision-language models. Don't have time for the full episode? Watch it in parts: Part 1 - "Lost in Automatic Translation": youtu.be/BeQFyY3Dld4 Part 2 - Hidden Cultural Codes in AI: youtu.be/Vfikq3wsULw Part 3 - When AI Can't "See" Your Culture: youtu.be/IwOxN8bssk4 CHAPTERS: 00:00 Introduction to Women in AI Research Podcast 00:33 Guest introduction - Dr. Vered Shwartz 02:32 The Importance of Communication Skills in Academia 04:15 Navigating Faculty Roles and Student Supervision 07:52 Personal Experiences with Language Technologies 14:39 Exploring Cultural Representation in AI 20:29 The InfoGap Method and Cultural Information Gaps 22:29 Technical Challenges in Cross-Language Representation 24:02 Cultural Completeness and Wikipedia's Role 26:42 User Interaction with Language Models 37:22 Cross-Cultural Evaluation of Social Norm Biases 38:16 Cultural Alignment of Language Models 49:11 Exploring Vision Language Models 01:02:51 Benchmarking Cultural Bias in AI 01:06:54 Decentralizing AI Development 01:12:01 Addressing Biases in AI Development 01:15:52 Future Directions in AI Research REFERENCES: 01:10 Vered Shwartz Google Scholar profile (scholar.google.ca/citations?user=bbe4ResAAAAJ&hl=en&oi=ao) 07:57 Book "Lost in Automatic Translation" (lostinautomatictranslation.com/) 19:25 Elevator Recognition, by The Scottish Comedy Channel (youtu.be/HbDnxzrbxn4?si=7YvUpZZ_earptBpN) 20:33 Locating Information Gaps and Narrative Inconsistencies Across Languages: A Case Study of LGBT People Portrayals on Wikipedia (arxiv.org/abs/2410.04282) 30:34 ECLeKTic: a Novel Challenge Set for Evaluation of Cross-Lingual Knowledge Transfer (arxiv.org/abs/2502.21228) 34:23 WikiGap: Promoting Epistemic Equity by Surfacing Knowledge Gaps Between English Wikipedia and other Language Editions (arxiv.org/abs/2505.24195) 37:24 Is It Bad to Work All the Time? Cross-Cultural Evaluation of Social Norm Biases in GPT-4 (arxiv.org/abs/2505.18322) 38:39 Towards Measuring the Representation of Subjective Global Opinions in Language Models (arxiv.org/abs/2306.16388) 48:09 I'm Afraid I Can't Do That: Predicting Prompt Refusal in Black-Box Generative Language Models (arxiv.org/abs/2306.03423) 50:43 From Local Concepts to Universals: Evaluating the Multicultural Understanding of Vision-Language Models (arxiv.org/pdf/2407.00263) 01:10:51 CulturalBench: A Robust, Diverse, and Challenging Cultural Benchmark by Human-AI CulturalTeaming (aclanthology.org/2025.acl-long.1247.pdf) 🎧 Subscribe to stay updated on new episodes spotlighting brilliant women shaping the future of AI. WiAIR website: ♾️ women-in-ai-research.github.io Follow us at: ♾️ LinkedIn: linkedin.com/company/women-in-ai-research/ ♾️ Bluesky: bsky.app/profile/wiair.bsky.social ♾️ X (Twitter): x.com/WiAIR_podcast #AI #NLP #LLMs #CulturalBias #WomenInAI #ExplainableAI #FairnessInAI #AIResearch #EthicalAI #wiair #wiairpodcast

Interpretable AI, with Dr. Faiza Khan Khattak

Episode 5

Interpretable AI, with Dr. Faiza Khan Khattak

June 4, 2025 · 58 min · WiAIR Podcast • Season 1

How can we build AI systems that are fair, explainable, and truly responsible? In this episode of the #WiAIR podcast, we sit down with Dr. Faiza Khan Khattak, the CTO of an innovative AI startup, with a rich background in both academia and industry. From fairness in machine learning to the realities of ML deployment in healthcare, this conversation is packed with insights, real-world challenges, and powerful reflections. ToC: [00:00] Intro [01:37] Faiza’s Journey in AI [07:50] Exploring Fairness in AI [11:17] The Role of Mentorship [13:27] Transitioning Between Academia, Industry, and Entrepreneurship [17:02] Challenges Faced by Women in AI [22:01] MLHOps in Healthcare [24:30] Operationalizing ML Models in Healthcare [27:25] Exploring Explainability in AI Models [31:31] Risks of AI in Healthcare [33:23] Addressing Social Bias in AI [38:40] The Role of Reasoning in Interpretability [41:04] Generalizability of Reasoning Across Models [46:25] Machine Unlearning and Bias Mitigation [52:57] Adversarial Attacks and Bias Induction REFERENCES: [21:40] MLHOps: Machine Learning Health Operations (ieeexplore.ieee.org/abstract/document/10811924) [33:33] Using Chain-of-Thought Prompting for Interpretable Recognition of Social Bias (openreview.net/forum?id=QyRganPqPz) [35:09] Dialectic Preference Bias in Large Language Models (ojs.aaai.org/index.php/AAAI-SS/article/view/35613) [41:42] The Impact of Unstated Norms in Bias Analysis of Language Models (arxiv.org/abs/2404.03471) [46:26] Can Machine Unlearning Reduce Social Bias in Language Models? (aclanthology.org/2024.emnlp-industry.71/) [52:58] BiasKG: Adversarial Knowledge Graphs to Induce Bias in Large Language Models (arxiv.org/abs/2405.04756v1) 👉 Whether you're an AI researcher, a developer working on LLMs, or someone passionate about Responsible AI, this episode is for you. 📌 Subscribe to hear more inspiring stories and cutting-edge ideas from women leading the future of AI. WiAIR website: ♾️ women-in-ai-research.github.io Follow us at: ♾️ LinkedIn: linkedin.com/company/women-in-ai-research ♾️ Bluesky: bsky.app/profile/wiair.bsky.social ♾️ X (Twitter): x.com/WiAIR_podcast #WomenInAI #WiAIR #WiAIRpodcast #ResponsibleAI #FairnessInAI #AIHealthcare #ExplainableAI #LLMs #AIethics #BiasMitigation #MachineUnlearning #InterpretableAI #AIstartup #AIforGood

Responsible AI for Health, with Aparna Balagopalan

Episode 3

Responsible AI for Health, with Aparna Balagopalan

April 23, 2025 · 39 min · WiAIR Podcast • Season 1

Aparna Balagopalan is a PhD student in the Department of Electrical Engineering and Computer Science (EECS) at @mit. In this episode, we present the intersection of AI and healthcare. Aparna shares her research on developing fair, interpretable, and robust models for healthcare applications. We explore the unique challenges of applying AI in medical contexts, including data quality, collaboration with clinicians, and the critical importance of model transparency. The conversation covers both technical innovations and ethical frameworks necessary for responsible AI deployment in healthcare settings. REFERENCES: [00:00:27] Aparna's Google Scholar profile (scholar.google.ca/citations?user=8Mlyv3oAAAAJ) [00:12:04] Machine learning for healthcare that matters: Reorienting from technical novelty to equitable impact (journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0000474) [00:19:58] Judging facts, judging norms: Training machine learning models to judge humans requires a modified approach to labeling data (science.org/doi/pdf/10.1126/sciadv.abq0701) [00:26:19] LEMoN: Label Error Detection using Multimodal Neighbors (arxiv.org/abs/2407.18941) ToC: [00:00:00] Introduction and Guest Background [00:01:05] Transition from Industry to Academia [00:04:42] Navigating Challenges in Research [00:07:15] Daily Life of a PhD Researcher [00:08:42] International Perspective in Research [00:12:02] Machine Learning for Healthcare that Matters [00:14:12] Data Quality and Bias in Machine Learning [00:17:42] Importance of Collaboration with Clinicians [00:19:55] Labelling and Annotation Challenges [00:23:16] Multimodal Data and Label Errors [00:30:06] Responsible Data Challenges in Healthcare [00:33:39] Advice for Women in AI [00:36:58] Future of AI in Healthcare WiAIR website: ♾️ women-in-ai-research.github.io Follow us at: ♾️ LinkedIn: / women-in-ai-research ♾️ Bluesky: bsky.app/profile/wiair.bsky.social ♾️ X (Twitter): x.com/WiAIR_podcast #WiAIRpodcast #WiAIR

Bias in AI, with Dr. Amanda Cercas Curry

Episode 2

Bias in AI, with Dr. Amanda Cercas Curry

April 2, 2025 · 49 min · WiAIR Podcast • Season 1

Dr. Amanda Cercas Curry is a researcher at CENTAI Institute, where she is working on applied NLP, fairness and evaluation. In this episode, we explore the critical issue of bias in AI systems. Amanda shares her expertise on identifying, measuring, and mitigating various forms of bias in language models and other AI applications. We discuss the social and ethical implications of biased AI, and how researchers are working to create more fair and inclusive systems. This episode highlights the importance of diverse perspectives in AI development and the ongoing challenges in the field. REFERENCES: [00:14:31] Let's Chat Ethics podcast on Spotify (open.spotify.com/show/6l66Xj18SDgI1V0ulfU4fU) [00:19:07] "How We Analyzed the COMPAS Recidivism Algorithm" by ProPublica (propublica.org/article/how-we-analyzed-the-compas-recidivism-algorithm) [00:21:04] Impoverished Language Technology: The Lack of (Social) Class in NLP (arxiv.org/abs/2403.03874) [00:26:19] Signs of Social Class: The Experience of Economic Inequality in Everyday Life (journals.sagepub.com/doi/10.1177/1745691616673192) [00:35:03] Angry Men, Sad Women: Large Language Models Reflect Gendered Stereotypes in Emotion Attribution (arxiv.org/abs/2403.03121) [00:45:43] How a chatbot encouraged a man who wanted to kill the Queen (bbc.com/news/technology-67012224) ToC: [00:00:00] Introduction and Guest Background [00:03:40] Feminism and AI Ethics: Challenges and Resistance [00:09:50] Structural Biases in NLP Systems [00:14:12] Let's Chat Ethics - Amanda's podcast [00:17:42] Evaluating Ethics in NLP Models [00:21:02] Social Class and Its Impact on NLP Systems [00:24:55] Language, Marginalization, and Social Class [00:30:12] Addressing Bias in NLP Systems [00:34:44] Emotional Stereotypes in Language Models [00:38:22] Interdisciplinary Approaches in AI Research [00:42:57] Understanding Human Emotions in AI [00:47:44] Advice to Early Career Researchers WiAIR website: ♾️ women-in-ai-research.github.io Follow us at: ♾️ LinkedIn: linkedin.com/company/women-in-ai-research ♾️ Bluesky: bsky.app/profile/wiair.bsky.social ♾️ X (Twitter): x.com/WiAIR_podcast #WiAIRpodcast #WiAIR

Researchers on this topic

From conferences and workshops

Interviews recorded on site

All topics