New paper! Have you or a loved one been harmed by a bad multiple-choice benchmark? 😔
You may be entitled to a more reliable evaluation 🩺
At #ACL2026, we'll present BenchMarker: a toolkit to diagnose common flaws in MCQA benchmarks, inspired by best practices in education 🧑🏫🧵
Come join us! 2-year Postdoc opportunity at CMU's AI-Human Research Center on how LLMs can train workers in social skills across different envs. You'll work with Haiyi Zhu, Bob Kraut, Yi-Chia Wang, myself at CMU, and Diyi Yang at Stanford.
Apply here! apply.interfolio.com/180675
For MCQ Evaluation, he shows 5 commonly used automated evaluation metrics for MCQ quality by LLMs but also 19 criteria rubric for MCQ quality in general📑✍️
I am excited to share that today is my first day at 𝐆𝐞𝐨𝐫𝐠𝐞 𝐌𝐚𝐬𝐨𝐧 𝐔𝐧𝐢𝐯𝐞𝐫𝐬𝐢𝐭𝐲 as a tenure-track Assistant Professor in the 𝐈𝐧𝐟𝐨𝐫𝐦𝐚𝐭𝐢𝐨𝐧 𝐒𝐜𝐢𝐞𝐧𝐜𝐞𝐬 𝐚𝐧𝐝 𝐓𝐞𝐜𝐡𝐧𝐨𝐥𝐨𝐠𝐲 department under the College of Engineering and Computing!
I am seeking PhD students to join my research group starting Fall 2026, the position is fully funded! Our research explores areas such as:
• AI & NLP in Education
• Learning Science & Educational Technology
• Human-Computer Interaction
stevenjamesmoore.com/prospec…
There are less than 2 weeks left to take advantage of early bird rates for #las26ed, co-located with EDM 2025 and AIED 2025.
And remember, this year, one ticket gets you into both L@S and @EDMConf2025!
servizitalia.it/registration…
My Postdoc, @StevenJMoore, is conducting a 4 minute survey on how teachers or instructors generate assessment items. Please take a few minutes if you are someone who has written assessment questions before. forms.gle/kYNJRgv4GEdsQNbQ6
Interested in educational quality assessment? The paper "Assessing Educational Quality: Comparative Analysis of Crowdsourced, Expert, and AI-Driven Rubric Applications" will be presented at #HCOMP2024. #EdTech#AI#Crowdsourcing Full list: humancomputation.com/papers.…
Our tool is SAQUET: Scalable Automatic Question Usability Evaluation Toolkit
SAQUET provides a scalable, automated, and domain-agnostic method to evaluate the quality of educational multiple-choice questions.
#KAIST is starting a new presidential postdoc fellowship. @hcikaist, an on-campus HCI research community with 20 labs, is recruiting postdocs in all areas of #HCI. My group @kixlab_kaist has an open position too. Please share this broadly and recommend candidates! (1/2)