Tootfinder

Personalized Auto-Grading and Feedback System for Constructive Geometry Tasks Using Large Language Models on an Online Math Platform
Yong Oh Lee, Byeonghun Bang, Joohyun Lee, Sejun Oh
https://arxiv.org/abs/2509.25529

Personalized Auto-Grading and Feedback System for Constructive Geometry Tasks Using Large Language Models on an Online Math Platform
As personalized learning gains increasing attention in mathematics education, there is a growing demand for intelligent systems that can assess complex student responses and provide individualized feedback in real time. In this study, we present a personalized auto-grading and feedback system for constructive geometry tasks, developed using large language models (LLMs) and deployed on the Algeomath platform, a Korean online tool designed for interactive geometric constructions. The proposed sys…

🤦🏽‍♀️ Overconfidence persists even where regular feedback should discourage it, chess study finds
https://phys.org/news/2025-10-overconfidence-persists-regular-feedback-discourage.html

Overconfidence persists even where regular feedback should discourage it, chess study finds
The late psychologist Daniel Kahneman once said if he could wave a magic wand and get rid of any bias, he would choose overconfidence. However, overconfidence is here to stay. In a recent study in Psychological Science, researchers examined this bias among tournament chess players, to investigate if overconfidence is prevalent in an environment that should discourage it.

London

Feedback Forensics: A Toolkit to Measure AI Personality
Arduin Findeis, Timo Kaufmann, Eyke H\"ullermeier, Robert Mullins
https://arxiv.org/abs/2509.26305 https://

Feedback Forensics: A Toolkit to Measure AI Personality
Some traits making a "good" AI model are hard to describe upfront. For example, should responses be more polite or more casual? Such traits are sometimes summarized as model character or personality. Without a clear objective, conventional benchmarks based on automatic validation struggle to measure such traits. Evaluation methods using human feedback such as Chatbot Arena have emerged as a popular alternative. These methods infer "better" personality and other desirable traits implicitly by ra…

of course PSV scores again during the 30 seconds it took me to go pee
#fedifc

We're selling an Xbox Series S toaster in the Company Store. If you're a friend of mine, guess what you're getting for Christmas? 🤣
#xbox #toaster #microsoft

Delicious lunch in the famous Karczma Polska in Szczecin. Always very good food 🤤

my brains officially cooked bc I looked at this and my immediate thought was this is the flag of a St. Pauli vs Dortmund match
#fedifc

just saw the absolute worst miss of all time and the commentators just kept saying like "your eyes aren't deceiving you, that really was the worst miss you've ever seen" "what an embarrassment to the fella"
lmao I can't wait to see the villareal highlights
#fedifc