Women in AI Research (WiAIR)
by WiAIR
Can AI Learn Languages Humans Can't? Impossible Languages &…
About this podcast
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.
Episodes
The newest 20 of 35 episodes
- Can AI Learn Languages Humans Can't? Impossible Languages & Tokenization, with Julie Kallini · 1 h 16 min · Season 2 Episode 9Can a language model learn a language no human ever could? Stanford PhD researcher Julie Kallini put Noam Chomsky's claim to the test, and won the ACL 2024 Best Paper Award for…
- What Makes a Sentence Memorable? Inside Language, Memory and LLMs, with Dr. Greta Tuckute · 1 h 16 min · Season 2 Episode 8Why don't bigger LLMs look more like the human brain? In the brain's language network, today's large models explain only slightly more variance than GPT-2 XL - and the reason…
- Is an Image Worth a Thousand Words? Hidden Failures of Multimodal Metrics, with Dr. Elisa Kreiss · 1 h 17 min · Season 2 Episode 7An image is not worth a thousand words - it's worth an indefinite number of them. So why do the metrics we use to evaluate AI-generated image descriptions still assume there's…
- Is Your AI Just Flattering You? Sycophancy, AI Policies, and More, with Dr. Malihe Alikhani · 1 h 7 min · Season 2 Episode 6Only 19% of Americans say AI has actually improved their productivity - so why the gap between the hype and reality? In this episode of Women in AI Research, Dr. Malihe Alikhani…
- Can Language Alone Create Intelligence? Insights from Neuroscience and AI, with Dr. Anna Ivanova · 1 h 11 min · Season 2 Episode 2Do large language models truly understand language—or are they sophisticated pattern matchers? In this conversation, Dr. Anna Ivanova (Asst. Prof. at Georgia Tech) explores one…
- 100% Jailbreak Success? The Hard Truth About AI Safety, with Dr. Saadia Gabriel (Part 2) · 34 min · Season 2 Episode 4What actually happens when AI systems fail in the real world? In this final part of our conversation with Saadia Gabriel (UCLA), we unpack one of the most urgent challenges in…
- From Hate Speech to Best Paper: Building Safer AI Systems, with Dr. Saadia Gabriel (Part 1) · 29 min · Season 2 Episode 4What 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…
- EACL 2026: LLMs Can Hear… But Can They Reason? A New Benchmark for Audio Intelligence · 18 minWhat does it actually mean for a model to understand audio Paper: https://arxiv.org/abs/2601.19673 In this episode, I talk with Iwona Christop, a PhD student at Adam Mickiewicz…
- EACL 2026: LLMs Can Call Tools -- But Can They Understand Them? · 22 minLLM-based agents are everywhere, but most research focuses on just one step: getting the model to call the right tool. What happens after that? Paper…
- EACL 2026: Reasoning Can Hurt LLM Safety?! Rethinking Accuracy in AI Systems · 22 minIn this episode of #WiAIRpodcast, we dive into a subtle but critical question: Does adding reasoning actually make LLMs safer and more reliable? Paper…
- EACL 2026: Why LLMs Hallucinate, and How to Make Them Say "I Don't Know" · 15 minLLMs are notoriously overconfident, but can we teach them to admit uncertainty? In this episode, Maor Juliet Lavi (Tel Aviv University) presents her EACL 2026 paper on Detecting…
- EACL 2026: From Paraphrases to Diagnostics: A Fine-Grained Framework for LLM Auditing · 17 minLLMs often give different answers to the same question, just phrased differently. But how do we measure and understand this behaviour rigorously? In this episode of the…
- EACL 2026: You're Using Persona Prompting Wrong · 16 minHow much control do persona prompts actually give us over LLM behaviour? In this episode of #WiAIRpodcast, Jing Yang (TU Berlin) speaks about the study on persona prompting in…
- EACL 2026: Why Your LLM Needs Math to Think Better · 19 minWhat if adding math data actually improves reasoning in non-math tasks? In this episode of #WiAIRpodcast, Syeda from the Carnegie Mellon University and NVIDIA presents Nemotron…
- EACL 2026: Inference-Time Steering Is Riskier Than You Think · 10 minAre the techniques we use to control language models quietly making them less safe? Paper: https://arxiv.org/abs/2602.06256 In this EACL 2026 paper, Navita Goyal (University of…
- EACL 2026: Do LLMs Spread Misinformation Better Than Humans? · 15 minWhat happens when humans and large language models try to persuade each other? In this episode of Women in AI Research, we sit down with Angana Borah (University of Michigan) to…
- Does Liking Yellow Make You a School Bus Driver? Hidden Failures in LLMs, with Dr. Hila Gonen · 60 min · Season 2 Episode 3In this conversation, Dr. Hila Gonen (Assistant Professor at the University of British Columbia) joins us to explore the deep insights into how large language models (LLMs) leak…
- Faithfulness and Hallucinations in Reasoning Models, with Dr. Letitia Parcalabescu · 1 h 3 min · Season 2 Episode 2Are reasoning models actually reasoning — or just producing convincing stories? Our guest in this episode of #WiAIRpodcast is Letitia Parcalabescu, the creator of the…
- AI Safety Beyond Benchmarks -- Dr. Swabha Swayamdipta on Evaluation, Personalization, and Control · 1 h 1 min · Season 2 Episode 1As 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…
- Do LLMs Understand Meaning? Neuroscience, Evaluation, and the Future of AI, with Dr. Maria Ryskina · 1 h 3 min · Season 1 Episode 15Do large language models actually understand meaning — or are we over-interpreting impressive behavior? In this episode, we speak with Dr. Maria Ryskina, CIFAR AI Safety…








