New video in the Women in AI Research @ EACL 2026 series.

We speak with @reasyaay.bsky.social from CMU about her work done during her research internship at NVIDIA:
"Nemotron-CrossThink: Scaling Self-Learning beyond Math Reasoning"

🎥 Watch it here: youtu.be/-cPYHmxwN14

#WiAIR #EACL2026

🚨 New series launch: WiAIR @ EACL 2026

First episode with @anganaborah.bsky.social:
"Persuasion at Play: Understanding Misinformation Dynamics in Demographic-Aware Human-LLM Interactions"

🎥 Watch it here: youtu.be/xcec0EpJQJ4

#EACL2026 #NLProc #WiAIR

Can't make it to @eaclmeeting.bsky.social? We've got you covered.

#WiAIR is bringing you direct access to the research. We're sitting down with authors of accepted papers to break down their work on LLMs, reasoning, dialogue systems, AI safety, and more: youtu.be/n7qyUK5uVis

#EACL2026

✨ How can we test how pretraining data affects language model behavior through direct intervention? In our latest #WiAIR episode, we host Dr. Hila Gonen to discuss “Rewriting History.” (1/5 🧵)

Happy International Women's Day, and happy birthday to #WiAIR!

#wiair_podcast

✨ How can we reliably detect harmful prompts across languages, images, and audio?
In our latest #WiAIR episode, we host Dr. Hila Gonen to discuss “OMNIGUARD: An Efficient Approach for AI Safety Moderation Across Languages and Modalities”. (1/5 🧵)

Remember "Lipstick on a Pig", where they showed that many embedding debiasing methods don't remove bias, just hide it.
In the upcoming #WiAIR episode, I speak with its author Hila Gonen about taking this further into LLMs: semantic leakage and other hidden failures.

✨ Can we give formal, information-theoretic guarantees against hallucinations in RAG systems?

In our latest #WiAIR episode, we host Dr. Letitia Parcalabescu to discuss "Bounding Hallucinations: Information-Theoretic Guarantees for RAG Systems via Merlin-Arthur Protocols". (1/5 🧵)

🎬 Watch or listen to the full episode:

YouTube ▶️ youtu.be/gzQiDCG_j7A?...
Spotify 🎙 open.spotify.com/episode/5BmX...
Apple 🎧 podcasts.apple.com/ca/podcast/f...

#WiAIR #WomenInAI #AIResearch (8/8🧵)

AI is becoming deeply embedded in how we work, decide, and create. But this question often gets overlooked: 𝐇𝐨𝐰 𝐝𝐨 𝐰𝐞 𝐭𝐞𝐚𝐜𝐡 𝐩𝐞𝐨𝐩𝐥𝐞 𝐰𝐡𝐞𝐧 𝐭𝐨 𝐫𝐞𝐥𝐲 𝐨𝐧 𝐀𝐈 — 𝐚𝐧𝐝 𝐰𝐡𝐞𝐧 𝐧𝐨𝐭 𝐭𝐨?

Full conversation:
🎬 YouTube: youtu.be/rSC7L5WikcE

#wiair

✨ How can language models assist suicide prevention research, without replacing experts?
In our latest #WiAIR episode, we host Dr. Swabha Swayamdipta (@swabhs.bsky.social) to discuss “Uncovering Intervention Opportunities for Suicide Prevention with Language Model Assistants”. (1/6 🧵)

Watch/listen to the full episode 🎧
YouTube: youtu.be/rSC7L5WikcE?...
Spotify: open.spotify.com/episode/37YB...
Apple: podcasts.apple.com/ca/podcast/a...
Paper: arxiv.org/abs/2504.17993
#WiAIR #WomenInAI #AIResearch #LLMs #AISafety #Interpretability (8/8🧵)

🔐 How vulnerable are hidden prompts?
In our latest #WiAIR episode, Dr. Swabha Swayamdipta (@swabhs.bsky.social) discusses her NeurIPS 2025 paper on recovering prompts using next-token probability sequences. (1/6 🧵)

How do language models align with conceptual meaning in the human brain?
In our latest #WiAIR episode, we discuss COLM 2025 paper “Language models align with brain regions that represent concepts across modalities” with Dr. Maria Ryskina (@mryskina.bsky.social). 👇 (1/5 🧵)

Elements of World Knowledge (EWoK): A Cognition-Inspired Framework for Evaluating Basic World Knowledge in Language Models Abstract. The ability to build and reason about models of the world is essential for situated language understanding. But evaluating world modeling capabilities in modern AI systems—especially those b...

📄 Paper: direct.mit.edu/tacl/article...
🎧 Full episode:
YouTube: www.youtube.com/@WomeninAIRe...
Spotify: open.spotify.com/show/51RJNlZ...
Apple Podcast: podcasts.apple.com/ca/podcast/w...
#WiAIR #WomenInAI #AIResearch #LLMs (8/8🧵)

🤔 Do LLMs really understand the world — or are they mostly predicting what sounds likely in text? In our latest #WiAIR podcast we explore this exact question with Maria Ryskina. (1/8🧵)

We're excited to welcome @mryskina.bsky.social, CIFAR AI Safety postdoc at Vector Institute for AI @vectorinstitute.ai, as our next guest on Women in AI Research.

#wiair #wiairpodcast

✨ Why it matters: AI in academic writing can reinforce dominant norms and silence interdisciplinary voices.
📄 Paper: arxiv.org/pdf/2506.00784
🎬 YouTube: youtu.be/P-R0mU8_0U0
🎧 Spotify: open.spotify.com/episode/705U...
🍏 Apple Podcasts: podcasts.apple.com/ca/podcast/w... (7/7🧵)
#WiAIR #WomenInAI

How are researchers actually using large language models today, and who benefits most?
In our latest WiAIR episode, we speak with Dr Maria Antoniak (@mariaa.bsky.social) about a large-scale survey on LLM use across academia. 👇 (1/6 🧵)
#WiAIR

We cover all this with Maria in our new WiAIR episode — from AI inclusivity to cultural and ethical issues. Watch or listen:
🎬 YouTube: youtu.be/P-R0mU8_0U0?...
🎙 Spotify: open.spotify.com/episode/705U...
🎧 Apple: podcasts.apple.com/ca/podcast/w...
(8/8🧵)
#WiAIR #WomenInAI #AIResearch #AI #AIEthics

🎙️ New #WiAIR episode!

We talk with @mariaa.bsky.social (@colorado.edu) about AI, culture, and power.

🎬 YouTube: youtu.be/P-R0mU8_0U0
🎙️ Spotify: open.spotify.com/show/51RJNlZ...
🍎 Apple Podcasts: podcasts.apple.com/ca/podcast/w...

🎙️ New WiAIR Episode Incoming!

We're excited to welcome @mariaa.bsky.social, Assistant Professor of Computer Science at the @colorado.edu, as our next guest on #WiAIRpodcast.

Subscribe to our Youtube and don't miss the upcoming episode: www.youtube.com/@WomeninAIRe...

#wiair #wiairpodcast

If you're not yet following my podcast on youtube, it's time to subscribe now - I'm covering the ##neurips2025 conference in San Diego there

youtu.be/1vAJdWiWLAg?...

#wiair #wiairpodcast

🎧 Full conversation:
🎬 YouTube: www.youtube.com/watch?v=L9Sp...
🎙️ Spotify: open.spotify.com/episode/2Kq7...
🍎 Apple Podcasts: podcasts.apple.com/ca/podcast/m...
📄 Paper: arxiv.org/abs/2406.03368
#WiAIR #WomenInAI #AIResearch #MultilingualNLP #Typology #LanguageDiversity

Don’t miss this #WiAIR episode with Dr. Annie Lee!
🎬 YouTube: www.youtube.com/watch?v=L9Sp...
🎙️ Spotify: open.spotify.com/episode/2Kq7...
🍎 Apple: podcasts.apple.com/ca/podcast/w...
#WomenInAI #KnowledgeBase #MultilingualNLP #AIResearch #Linguistics

✨ In the latest #WiAIR episode, Dr. Annie Lee discusses URIEL+, a massive enhancement to a multilingual knowledge base. It expands coverage and improves handling of missing data for better language-distance calculations. (1/6🧵)
📄 arxiv.org/abs/2409.18472

WiAIR is heading to @neuripsconf.bsky.social 2025 in San Diego! Will you be there next week?

Subscribe our Youtube channel for daily highlights during the conference: www.youtube.com/@WomeninAIRe...

#neurips2025 #wiair #wiairpodcast

In Cantonese & Taiwanese, the greeting isn’t "hello" - it’s "Have you eaten?"
Not about food, but about care. 💛

Dr. Annie Lee explains why LLMs often miss these cultural meanings - and why multilingual AI needs more than translation. More in the full episode!

#wiair #wiairpodcast

🎙️ New #WiAIR episode!

We talk with Dr. Annie En-Shiun Lee (@ontariotechu.bsky.social) about multilingual & multicultural AI — the language gap, missing benchmarks, and why domain-specific data matters.

#wiairpodcast

🎙️ New #WiAIR episode coming soon!

We talk with Dr. Annie En-Shiun Lee (@ontariotechu.bsky.social & @utoronto.ca) about multilingual AI, inclusion in research - and proving you can build an amazing career while raising a family.

#wiairpodcast