
Postdoc at @Cambridge_CL, studying HRI and conversational AI for well-being 🤖🧠 Incoming Assistant Professor at @bengurionu Engineering.
Cambridge, UK
Joined July 2012
- Tweets1.1K
- Following1.1K
- Followers736
- Likes4.6K
Guy Laban retweeted
In 225 clinical scenarios based on Choosing Wisely recommendations, LLMs aligned with evidence-based guidance, recommending potentially unnecessary tests or treatments in just 5.4% of responses and rarely withholding appropriate care. Researchers found that LLMs were more likely to suggest unnecessary care in scenarios where clinical guidance is debated or symptoms could reasonably justify additional testing.
These findings suggest that commercial LLMs generally align with evidence-based principles of medical restraint while highlighting opportunities for targeted improvement. bit.ly/3UevlnQ @deanarielmd @ClalitHealth @GuyLaban @bengurionu
Guy Laban retweeted
Thank you @GuyLaban for helping us understand the human side of AI!
Israel continues to lead the way in artificial intelligence, with groundbreaking research at @bengurionu of the Negev helping shape the country's future. Dr. Guy Laban explains how Al can improve everyday life and why continued investment in innovation is essential for Israel. 🇮🇱
Support @A4BGU groundbreaking research: iltvisrael.com/wayforward-a4…
Guy Laban retweeted
This week we hosted Guy Laban for a fascinating talk as part of the Sagol School of Neuroscience seminar series. Thank you for an insightful and thought-provoking lecture!
@GuyLaban
Guy Laban retweeted
Can a robot help you cope with emotional challenges? 🤖
New research led by Prof. @GuyLaban (BGU) with collaborators at Cambridge shows that structured conversations with a social robot improved students’ emotional understanding, sense of control, and mood over time.
Guy Laban retweeted
SPASM: Stable Persona-driven Agent Simulation for Multi-turn Dialogue Generation
Han Luo, Guy Laban
arxiv.org/abs/2604.09212 [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙼𝙰]
💬Accepted to Findings of the Association for Computational Linguistics (ACL 2026)
Guy Laban retweeted
DialogGuard: Multi-Agent Psychosocial Safety Evaluation of Sensitive LLM Responses. arxiv.org/abs/2512.02282
Guy Laban retweeted
A chatbot’s introduction can influence how much users open up. When a chatbot is framed as a human, people tend to disclose more and feel more comforted—even if they suspect it’s not actually a person. dlvr.it/TPCMX1
Guy Laban retweeted
It's been a summer of accolades for our researchers. Work by several members of this Department was honoured by leading conferences and organisations in fields ranging from #AI to #cybersecurity to #socialrobotics. Congratulations to our colleagues! cst.cam.ac.uk/news/summer-ac…
Guy Laban retweeted
The #CUI2025 PROCEEDINGS are now LIVE in the ACM Digital Library! 📖🔍 Dive into the papers here: dl.acm.org/doi/proceedings/1…
The conference kicks off TOMORROW (July 8) — just one sleep away!! Looking forward to a great week ahead! See you soon! 👏👏👏
Guy Laban retweeted
🚨 New paper out w @ValMorrisonProf @ArvidKappas
@brain_on_dance!➡️doi.org/10.1007/s12369-024-0… We studied how talking to a robot overtime can help caregivers cope with emotional distress. Key finding: Overtime, caregivers disclosed more, felt better, & coped better @ITN_ENTWINE
Guy Laban retweeted
📢 Call for Papers
Join us at the Bias and Fairness in Conversational User Interfaces workshop 💬
🗓️ July 8–10, 2025
📍 Waterloo, Canada (AT @CUI_Conference @ACM_CUI)
Keynotes: Dorian Peters & @micol_spitale
🔗 Submit your work, demos, or provocations!➡️ sites.google.com/view/cuibnf…
Guy Laban retweeted
Hot off the press: Laban, G., Morrison, V., Kappas, A. et al. Coping with Emotional Distress via Self-Disclosure to Robots: An Intervention with Caregivers. Int J of Soc Robotics (2025). doi.org/10.1007/s12369-024-0…
#socialrobotics #pepperrobot
audio: notebooklm.google.com/notebo…
Guy Laban retweeted
What People Share With a Robot When Feeling Lonely and Stressed and How It Helps Over Time. arxiv.org/abs/2504.02991
Guy Laban retweeted
Join us for the REACT 2025 Challenge on Multiple Appropriate Facial Reaction Generation (MAFRG). Developing digital human/virtual agent that can express human-style facial reactions using our recently established MARS dataset (video, audio & EEG).
lnkd.in/egrUga42
Guy Laban retweeted
📢 New publication with @affectivebrain in @NatureHumBehav
Key finding: Human-AI interactions create feedback loops, where AI amplifies human biases, which are then further internalized by humans across perceptual, emotional & social domains.
nature.com/articles/s41562-0…
🧵1/6
Guy Laban retweeted
Exciting news! Our book chapter, "Cognitive Mechanisms of Being Imitated," is now published! We explore various approaches to studying the effects of being mimicked. Check it out! 📘 @antoniahamilton @PsychFarmer link.springer.com/chapter/10…
Guy Laban retweeted
Paper with Yael Millgram & @mk_nock: Using two EMA studies, we found that participants with current suicidal thoughts knew less about the sources of their emotions compared to those with no suicidal thoughts, and comp to controls with other psych symptoms.
psycnet.apa.org/record/2025-…
Guy Laban retweeted
Past, Present, and Future: A Survey of The Evolution of Affective Robotics For Well-being. arxiv.org/abs/2407.02957
Guy Laban retweeted
Oh wow, new research showing how effective robotics and AI to human well-being. Maybe a few social robots wouldn't all that bad after all?
arxiv.org/html/2407.02957v1
Guy Laban retweeted
Excited to share that my & @brain_on_dance's paper has been accepted to IEEE Transactions on Affective Computing! 🤖💬 We review studies addressing self-disclosure in HRIs and its impact on emotional well-being. Check it out here: ieeexplore.ieee.org/document…

























