Women in AI Research (WiAIR)

WiAIR
  • 0.0 (0)
  • EDUCATION
  • UPDATED BIWEEKLY

Women in AI Research (WiAIR) is a podcast dedicated to celebrating the remarkable contributions of female AI researchers from around the globe. Our mission is to challenge the prevailing perception that AI research is predominantly male-driven. Our goal is to empower early career researchers, especially women, to pursue their passion for AI and make an impact in this rapidly growing field. You will learn from women at different career stages, stay updated on the latest research and advancements, and hear powerful stories of overcoming obstacles and breaking stereotypes.

  1. FEB 11

    Faithfulness and Hallucinations in Reasoning Models, with Dr. Letitia Parcalabescu

    Are reasoning models actually reasoning — or just producing convincing stories? Our guest in this episode of #WiAIRpodcast is Letitia Parcalabescu, the creator of the  @AICoffeeBreak  youtube channel. Letitia joins Jekaterina Novikova for a deep dive into the topics of faithfulness, self-consistency, hallucinations, and the reliability illusion in LLMs and multimodal reasoning models. We discuss why chain-of-thought explanations may not reflect what the model actually did, why RAG does not automatically fix hallucinations, and how vision–language models often rely far more on text than images. We also explore new approaches for grounding and rejection — and why models struggle to say "I don't know." Instead of focusing only on benchmark scores, this conversation asks: What kind of evidence do we need to truly trust reasoning models? REFERENCES: On Measuring Faithfulness or Self-consistency of Natural Language ExplanationsDo Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?Bounding Hallucinations: Information-Theoretic Guarantees for RAG Systems via Merlin-Arthur ProtocolsAI Coffee Break with Letitia https://www.youtube.com/c/AICoffeeBreakhttps://x.com/AICoffeeBreak 🎧 Subscribe to stay updated on new episodes spotlighting brilliant women shaping the future of AI. ⁠WiAIR website⁠Follow us at: ⁠LinkedIn⁠⁠Bluesky⁠⁠X (Twitter)

    1h 4m

  2. JAN 21

    AI Safety Beyond Benchmarks -- Dr. Swabha Swayamdipta on Evaluation, Personalization, and Control

    As language models become more capable, the hardest questions are no longer just about performance, but about safety, interpretation, and control. In this episode of Women in AI Research, we speak with Swabha Swayamdipta, Assistant Professor of Computer Science at the University of Southern California and co-Associate Director of the USC Center for AI and Society. Swabha’s research examines how the design and deployment of language models intersect with real-world risks — from how models behave in unexpected ways to how seemingly technical choices can have broader societal consequences. We talk about AI safety from multiple angles: what it means when hidden inputs to models can sometimes be inferred from their outputs, why personalization introduces new trade-offs around privacy and user agency, and how assumptions about model behavior can quietly shape downstream harms. Rather than focusing only on accuracy or benchmarks, the conversation asks what kinds of evidence we actually need to trust these systems in practice. REFERENCES Better Language Model Inversion by Compactly Representing Next-Token DistributionsImproving Language Model Personas via Rationalization with Psychological ScaffoldsOATH-Frames: Characterizing Online Attitudes Towards Homelessness with LLM AssistantsUncovering Intervention Opportunities for Suicide Prevention with Language Model Assistants 🎧 Subscribe to stay updated on new episodes spotlighting brilliant women shaping the future of AI. ⁠WiAIR website⁠Follow us at: ⁠LinkedIn⁠⁠Bluesky⁠⁠X (Twitter)

    1h 1m

  3. 12/31/2025

    Do LLMs Understand Meaning? Neuroscience, Evaluation, and the Future of AI, with Maria Ryskina

    Do large language models actually understand meaning — or are we over-interpreting impressive behavior? In this episode, we speak with Maria Ryskina, CIFAR AI Safety Postdoctoral Fellow at the Vector Institute for AI, whose research bridges neuroscience, cognitive science, and artificial intelligence. Together, we unpack what the brain can (and cannot) teach us about modern AI systems — and why current evaluation paradigms may be missing something fundamental. We explore how language models can predict brain activity in regions linked to visual processing, what this reveals about cross-modal knowledge, and why scale alone may not resolve deeper conceptual gaps in AI. The conversation also tackles the growing importance of interpretability, especially as AI systems become more embedded in high-stakes, real-world contexts. Beyond technical questions, Maria shares why community matters in AI research, particularly for underrepresented groups — and how diversity directly shapes the kinds of scientific questions we ask and the systems we ultimately build. REFERENCES Gender Shades: Intersectional Accuracy Disparities in Commercial Gender ClassificationStereotypes and Smut: The (Mis)representation of Non-cisgender Identities by Text-to-Image ModelsLanguage models align with brain regions that represent concepts across modalitiesElements of World Knowledge (EWoK): A Cognition-Inspired Framework for Evaluating Basic World Knowledge in Language ModelsPrompting is not a substitute for probability measurements in large language modelsAuxiliary task demands mask the capabilities of smaller language models 🎧 Subscribe to stay updated on new episodes spotlighting brilliant women shaping the future of AI. WiAIR websiteFollow us at: LinkedInBlueskyX (Twitter)

    1h 4m

  4. 12/10/2025

    How Does AI Reflect Society, with Dr. Maria Antoniak

    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. REFERENCES: ⁠Trust No Bot⁠⁠A Large-Scale Analysis of Public-Facing, Community-Built Chatbots on Character.AI⁠⁠LLMs as Rsearch Tools⁠⁠Culture is Not Trivia⁠⁠Research Borderlands⁠⁠NLP for Maternal Healthcare⁠⁠Data Feminism⁠⁠Epistemic Diversity and Knowledge Collapse in Large Language Models⁠⁠Empire of AI⁠ 🎧 Subscribe to stay updated on new episodes spotlighting brilliant women shaping the future of AI. ⁠⁠⁠⁠WiAIR website⁠⁠⁠⁠ Follow us at: ⁠⁠⁠⁠LinkedIn⁠⁠⁠⁠⁠⁠⁠⁠Bluesky⁠⁠⁠⁠⁠⁠⁠⁠X (Twitter)⁠

    1h 11m

  5. 11/19/2025

    Multilingual AI, with Dr. Annie En-Shiun Lee

    Is English just one of the languages you speak? If so, the AI tools you use might miss things that makes your voice multilingual. In this episode of Women in AI Research, Jekaterina Novikova speaks with Dr. Annie En-Shiun Lee about her work on multilingual and multicultural AI — from the widening language gap and the lack of benchmarks for underrepresented languages, to why domain-specific data matters more than just scaling up models. We talk about the limits of cross-lingual transfer, the risks of English-centric reasoning in AI, and the technical, ethical, and cultural challenges of building models that truly serve global communities. References: SIB-200: A simple, inclusive, and big evaluation dataset for topic classification in 200+ languages and dialectsURIEL+: Enhancing Linguistic Inclusion and Usability in a Typological and Multilingual Knowledge BasemR3: Multilingual Rubric-Agnostic Reward Reasoning ModelsProxyLM: Predicting language model performance on multilingual tasks via proxy modelsATAIGI: An AI-Powered Multimodal Learning App Leveraging Generative Models for Low-Resource Taiwanese HokkienEnhancing Taiwanese Hokkien Dual Translation by Exploring and Standardizing of Four Writing SystemsAlignFreeze: Navigating the Impact of Realignment on the Layers of Multilingual Models Across Diverse LanguagesIrokobench: A new benchmark for african languages in the age of large language models 🎧 Subscribe to stay updated on new episodes spotlighting brilliant women shaping the future of AI. ⁠⁠WiAIR website⁠⁠ Follow us at: ⁠⁠LinkedIn⁠⁠⁠⁠Bluesky⁠⁠⁠⁠X (Twitter)

    1h 20m

  6. 10/29/2025

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

    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 Vector Institute) about the cultural blind spots in today’s large language and vision-language models. REFERENCES: Vered Shwartz Google Scholar profileBook "Lost in Automatic Translation"Elevator Recognition, by The Scottish Comedy ChannelLocating Information Gaps and Narrative Inconsistencies Across Languages: A Case Study of LGBT People Portrayals on WikipediaECLeKTic: a Novel Challenge Set for Evaluation of Cross-Lingual Knowledge TransferWikiGap: Promoting Epistemic Equity by Surfacing Knowledge Gaps Between English Wikipedia and other Language EditionsIs It Bad to Work All the Time? Cross-Cultural Evaluation of Social Norm Biases in GPT-4Towards Measuring the Representation of Subjective Global Opinions in Language ModelsI'm Afraid I Can't Do That: Predicting Prompt Refusal in Black-Box Generative Language ModelsFrom Local Concepts to Universals: Evaluating the Multicultural Understanding of Vision-Language ModelsCulturalBench: A Robust, Diverse, and ChallengingCultural Benchmark by Human-AI CulturalTeaming 🎧 Subscribe to stay updated on new episodes spotlighting brilliant women shaping the future of AI. ⁠WiAIR website⁠ Follow us at: ⁠LinkedIn⁠⁠Bluesky⁠⁠X (Twitter)

    1h 17m

  7. 10/09/2025

    Can We Trust AI Explanations? Dr. Ana Marasović on AI Trustworthiness, Explainability & Faithfulness

    In this conversation, Jekaterina Novikova and Malikeh Ehgaghi interview Ana Marasović, an expert in AI trustworthiness, focusing on the complexities of explainability, the realities of academic research, and the dynamics of human-AI collaboration. We discuss the importance of intrinsic and extrinsic trust in AI systems, the challenges of evaluating AI performance, and the implications of synthetic evaluations. REFERENCES: On Evaluating Explanation Utility for Human-AI Decision Making in NLPEffective Human-AI Teams via Learned Natural Language Rules and OnboardingChain-of-Thought Unfaithfulness as Disguised AccuracyOn Measuring Faithfulness or Self-consistency of Natural Language ExplanationsWhat Has Been Lost with Synthetic Evaluation? 🎧 Subscribe to stay updated on new episodes spotlighting brilliant women shaping the future of AI. WiAIR website Follow us at: LinkedInBlueskyX (Twitter)

    1h 23m

  8. 09/17/2025

    Open Science and LLMs, with Dr. Valentina Pyatkin

    Can open-source large language models really outperform closed ones like Claude 3.5? 🤔 In this episode of the Women in AI Research podcast, Jekaterina Novikova and Malikeh Ehghaghi engage with Valentina Pyatkin, a postdoctoral researcher at the Allen Institute for AI. We dive deep into the future of open science, LLM research, and extending model capabilities. 🔑 Topics we cover: Why open-source LLMs sometimes beat closed modelsThe value of releasing datasets, recipes, and training infrastructureThe role of open science in accelerating NLP innovationInsights from Valentina’s award-winning research journey REFERENCES: ⁠Valentina's Google Scholar profile ⁠⁠Olmo: Accelerating the science of language models⁠⁠Tulu 3: Pushing Frontiers in Open Language Model Post-Training⁠⁠open-instruct⁠⁠Generalizing Verifiable Instruction Following⁠⁠RewardBench 2: Advancing Reward Model Evaluation⁠ 🎧 Subscribe to stay updated on new episodes spotlighting brilliant women shaping the future of AI. ⁠WiAIR website⁠⁠LinkedIn⁠⁠Bluesky⁠⁠X (Twitter)

    1h 12m
See All (18)

Trailer

About

Women in AI Research (WiAIR) is a podcast dedicated to celebrating the remarkable contributions of female AI researchers from around the globe. Our mission is to challenge the prevailing perception that AI research is predominantly male-driven. Our goal is to empower early career researchers, especially women, to pursue their passion for AI and make an impact in this rapidly growing field. You will learn from women at different career stages, stay updated on the latest research and advancements, and hear powerful stories of overcoming obstacles and breaking stereotypes.

Information