paper-with-me

Papers

Can Large Language Models Develop Gambling Addiction?

2025-09-26 · Seungpil Lee, Donghyeon Shin, Yunjeong Lee, Sundong Kim arxiv

This study identifies the specific conditions under which large language models exhibit human-like gambling addiction patterns, providing critical insights into their decision-making mechanisms and AI safety. We analyze LLM decision-making at cognitive-behavioral and neural levels based on human addiction research. In slot machine experiments, we identified cognitive features such as illusion of control and loss chasing, observing that greater autonomy in betting parameters substantially amplified irrational behavior and bankruptcy rates. Neural circuit analysis using a Sparse Autoencoder confirmed that model behavior is controlled by abstract decision-making features related to risk, not merely by prompts. These findings suggest LLMs internalize human-like cognitive biases beyond simply mimicking training data.

📄 PDF Abstract BibTeX arXiv:2509.22818

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Addictive Auctions: using lucky-draw and gambling addiction to increase participation during auctioning

2019-06-07 · Ravin Kumar

Auction theories are believed to provide a better selling opportunity for the resources to be allocated. Various organizations have taken measures to increase trust among participants towards their auction system, but tr…

Fairness

Early Risk Detection of Pathological Gambling, Self-Harm and Depression Using BERT

2021-06-30 · Ana-Maria Bucur, Adrian Cosma, Liviu P. Dinu

Early risk detection of mental illnesses has a massive positive impact upon the well-being of people. The eRisk workshop has been at the forefront of enabling interdisciplinary research in developing computational method…

Tackling a Challenging Corpus for Early Detection of Gambling Disorder: UNSL at MentalRiskES 2025

2025-11-28 · Horacio Thompson, Marcelo Errecalde arxiv

Gambling disorder is a complex behavioral addiction that is challenging to understand and address, with severe physical, psychological, and social consequences. Early Risk Detection (ERD) on the Web has become a key task…

An End-to-End Set Transformer for User-Level Classification of Depression and Gambling Disorder

2022-07-02 · Ana-Maria Bucur, Adrian Cosma, Liviu P. Dinu, Paolo Rosso

This work proposes a transformer architecture for user-level classification of gambling addiction and depression that is trainable end-to-end. As opposed to other methods that operate at the post level, we process a set …

Sentence

Who is Gambling? Finding Cryptocurrency Gamblers Using Multi-modal Retrieval Methods

2022-11-27 · Zhengjie Huang, Zhenguang Liu, Jianhai Chen, Qinming He 외

With the popularity of cryptocurrencies and the remarkable development of blockchain technology, decentralized applications emerged as a revolutionary force for the Internet. Meanwhile, decentralized applications have al…

Retrieval