Bhaumik Patel
@bhaumikpatel
Bhaumik Patel
"Violation of Expectation via Metacognitive Prompting Reduces Theory of Mind Prediction Error in Large Language Models"
This paper investigates how Violation of Expectation (VoE) and metacognitive prompting can be used to reduce Theory of Mind prediction errors in Large Language Models (LLMs) in the context of human-AI interaction.
arxiv.org
Then, there’s the guilty-dysphoric type, which happens when your mind wander into a negative space. Here yoru critique is self-destructive, you delve into pessimistic thoughts, and end up diminishing your joy and increasing stress. Obviously, you don’t want that either.
Therefore, it’s best to practice positive-consgtructive daydreaming when you’re... See more
Therefore, it’s best to practice positive-consgtructive daydreaming when you’re... See more
Maria Deac • Bored and Brilliant Summary
🧠🚨New memory paper🚨🧠
A new paper from @Plastic_Labs combines concepts from developmental psychology with LLMs in order to simulate more complex memory
"Violation of Expectation via Metacognitive Prompting Reduces Theory of Mind Prediction Error in Large Language... See more
Harrison Chasetwitter.comOur current instructional design approaches assume that access to expertise is scarce, expensive, and delayed. That’s why we “capture” disciplinary expertise in “content” – so we can economically provide access to expertise to learners. But what if access to expertise was abundant, cheap, and immediate? If your students have access to the internet,... See more
opencontent • The Near-term Impact of Generative AI on Education, in One Sentence – improving learning
IFS is grounded in the observation that the mind is naturally multiple, housing a variety of subpersonalities, or parts . We experience this multiplicity when we feel torn between conflicting desires; maybe part of us wants to pursue a challenging opportunity, but another part fears the risk, while a third part feels exhausted by the inner debate.
T... See more
T... See more
Nick Barr • Enhancing Self-Therapy with Internal Family Systems and AI -
The crux of IFS theory: we are composed of parts (subpersonalities).
Participants in three experiments wrote gratitude letters and then predicted how surprised, happy, and awkward recipients would feel. Recipients then reported how receiving an expression of gratitude actually made them feel. Expressers significantly underestimated how surprised recipients would be about why expressers were grateful, overestimated... See more
Undervaluing Gratitude: Expressers Misunderstand the ...
A third paper looks at a related topic: helping others. When a person needs help & all someone can do is provide a little assistance, rather than solving the entire problem, the helper is often reluctant to do anything because they think partial help will not be valued. Again, people really appreciate even small amounts of help.