Maarten Sap
@maartensap.bsky.social
Working on #NLProc for social good.
Currently at LTI at CMU. 🏳🌈
Currently at LTI at CMU. 🏳🌈
I’m ✨ super excited and grateful ✨to announce that I'm part of the 2025 class of #PackardFellows (www.packard.org/2025fellows). The @packardfdn.bsky.social and this fellowship will allow me to explore exciting research directions towards culturally responsible and safe AI 🌍🌈
October 15, 2025 at 1:06 PM
I’m ✨ super excited and grateful ✨to announce that I'm part of the 2025 class of #PackardFellows (www.packard.org/2025fellows). The @packardfdn.bsky.social and this fellowship will allow me to explore exciting research directions towards culturally responsible and safe AI 🌍🌈
That's a lot of people! Fall Sapling lab outing, welcoming our new postdoc Vasudha, and visitors Tze Hong and Chani! (just missing Jocelyn)
August 26, 2025 at 5:53 PM
That's a lot of people! Fall Sapling lab outing, welcoming our new postdoc Vasudha, and visitors Tze Hong and Chani! (just missing Jocelyn)
We have been studying these questions of how models should refuse in our recent paper accepted to EMNLP Findings (arxiv.org/abs/2506.00195) led by my wonderful PhD student
@mingqian-zheng.bsky.social
@mingqian-zheng.bsky.social
![Snippet of the Forbes article, with highlighted text.
A recent study by Allen Institute for AI (Ai2), titled “Let Them Down Easy! Contextual Effects of LLM Guardrails on User Perceptions and Preferences,” found that refusal style mattered more than user intent. The researchers tested 3,840 AI query-response pairs across 480 participants, comparing direct refusals, explanations, redirection, partial compliance and full compliance.
Partial compliance, sharing general but not specific information, reduced dissatisfaction by over 50% compared to outright denial, making it the most effective safeguard.
“We found that [start of highlight] direct refusals can cause users to have negative perceptions of the LLM: users consider these direct refusals significantly less helpful, more frustrating and make them significantly less likely to interact with the system in the future,” [end of highlight] Maarten Sap, AI safety lead at Ai2 and assistant professor at Carnegie Mellon University, told me. “I do not believe that model welfare is a well-founded direction or area to care about.”](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:jqtp2hdnr5g7giblg57wbd7e/bafkreieqlgyx5cr22fdgz6qq5w55yw4q74rqhglnf2qmzjaieigsbw7hka@jpeg)
August 22, 2025 at 1:00 PM
We have been studying these questions of how models should refuse in our recent paper accepted to EMNLP Findings (arxiv.org/abs/2506.00195) led by my wonderful PhD student
@mingqian-zheng.bsky.social
@mingqian-zheng.bsky.social
Saplings Raclette night was a success 🥰
February 1, 2025 at 2:34 PM
Saplings Raclette night was a success 🥰