Vanessa Cheung's Avatar

Vanessa Cheung

@vanessachg.bsky.social

PhD student at UCL | cognitive science, moral judgment and decision-making

54 Followers  |  45 Following  |  3 Posts  |  Joined: 03.12.2024  |  1.5125

Latest posts by vanessachg.bsky.social on Bluesky

Logo of Behavioural Public Policy (BPP) featuring an abstract brain-like diagram made of interconnected icons representing various elements such as a clock, person, lightbulb, and gears on a dark blue background.

Logo of Behavioural Public Policy (BPP) featuring an abstract brain-like diagram made of interconnected icons representing various elements such as a clock, person, lightbulb, and gears on a dark blue background.

#OpenAccess from @bppjournal.bsky.social -

Negative anecdotes reduce policy support: evidence from three experimental studies on communicating policy (in)effectiveness - https://cup.org/4jDoXyD

- A.Rodger, G.A.Sanna, @vanessachg.bsky.social, @nicholaraihani.bsky.social & D.Lagnado

#FirstView

13.01.2026 06:20 β€” πŸ‘ 2    πŸ” 2    πŸ’¬ 0    πŸ“Œ 0

Now officially out:

"Re-evaluating Theory of Mind evaluation in large language models"

royalsocietypublishing.org/doi/10.1098/...

(by Hu, Sosa, & me)

18.08.2025 13:01 β€” πŸ‘ 40    πŸ” 9    πŸ’¬ 1    πŸ“Œ 0

Our new research paper is out in NHB, which we apparently coauthored with acclaimed actor Ryan Reynolds. Critics are calling it his best work since Deadpool.

12.08.2025 10:45 β€” πŸ‘ 6    πŸ” 4    πŸ’¬ 0    πŸ“Œ 0

Excited to share that this paper is now published in PNAS! (With @maxmaier.bsky.social & Falk Lieder) www.pnas.org/doi/10.1073/...

20.06.2025 20:57 β€” πŸ‘ 8    πŸ” 4    πŸ’¬ 0    πŸ“Œ 0
Post image

Suppose Person A orders Person B to hurt you. Then Person B does exactly what she was ordered to do. Who would you see as the main cause of what happened to you - Person A or Person B?

Intriguing new work from @vanessachg.bsky.social

osf.io/preprints/ps...

12.03.2025 14:40 β€” πŸ‘ 25    πŸ” 13    πŸ’¬ 3    πŸ“Œ 2
Post image

We updated our preprint on moral decision-making in LLMs (osf.io/preprints/ps...) with a new study investigating sources of the yes-no framing bias and amplified omission bias. Results show that they likely arise from fine-tuning for chatbot applications. (w/ @maxmaier.bsky.social and Falk Lieder)

11.12.2024 16:15 β€” πŸ‘ 1    πŸ” 2    πŸ’¬ 0    πŸ“Œ 1

@vanessachg is following 20 prominent accounts