LLMs refuse ambiguous queries that look harmful but aren't. Can they recover once users clarify, while staying safe? Our new interactive multi-turn benchmark measures both. 🚨 Turns out: not both at once.

Reading social media stories evokes a wide range of contextual reader reactions—inferential, affective, evaluative—yet we lack methods to study these at scale. Excited to share our new paper that builds a framework for analyzing storytelling practices across online communities!

How and when should LLM guardrails be deployed to balance safety and user experience? Our #EMNLP2025 paper reveals that crafting thoughtful refusals rather than detecting intent is the key to human-centered AI safety. 📄 arxiv.org/abs/2506.00195 🧵[1/9]

Why do some emails get a reply and not others? Does it have more to do with how you write it or who you are—or maybe both? In our new #NAACL2025 paper we looked at 11M emails to causally test what factors will help you get a reply. 📬

When interacting with ChatGPT, have you wondered if they would ever "lie" to you? We found that under pressure, LLMs often choose deception. Our new #NAACL2025 paper, "AI-LIEDAR ," reveals models were truthful less than 50% of the time when faced with utility-truthfulness conflicts! 🤯 1/

Did you know? Gestures used to express universal concepts—like wishing for luck—vary DRAMATICALLY across cultures? 🤞means luck in US but deeply offensive in Vietnam 🚨 📣 We introduce MC-SIGNS, a test bed to evaluate how LLMs/VLMs/T2I handle such nonverbal behavior! 📜: arxiv.org/abs/2502.17710