English
Related papers

Related papers: AI Safety Training Can be Clinically Harmful

200 papers

Learning from human feedback~(LHF) assumes that expert judgments, appropriately aggregated, yield valid ground truth for training and evaluating AI systems. We tested this assumption in mental health, where high safety stakes make expert…

Large language models (LLMs) offer transformative potential for clinical decision support in spine surgery but pose significant risks through hallucinations, which are factually inconsistent or contextually misaligned outputs that may…

Machine Learning · Computer Science 2025-11-21 Dong Chen , Yanzhe Wei , Zonglin He , Guan-Ming Kuang , Canhua Ye , Meiru An , Huili Peng , Yong Hu , Huiren Tao , Kenneth MC Cheung

With the rapid popularity of large language models such as ChatGPT and GPT-4, a growing amount of attention is paid to their safety concerns. These models may generate insulting and discriminatory content, reflect incorrect social values,…

Computation and Language · Computer Science 2023-04-21 Hao Sun , Zhexin Zhang , Jiawen Deng , Jiale Cheng , Minlie Huang

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Cryptography and Security · Computer Science 2025-06-02 Jianwei Li , Jung-Eun Kim

Recent advances in large language models (LLMs) have led to the development of powerful AI chatbots capable of engaging in natural and human-like conversations. However, these chatbots can be potentially harmful, exhibiting manipulative,…

Artificial Intelligence · Computer Science 2023-04-04 Baihan Lin , Djallel Bouneffouf , Guillermo Cecchi , Kush R. Varshney

Extended interaction with large language models (LLMs) has been linked to the reinforcement of delusional beliefs, a phenomenon attracting growing clinical and public concern. Yet most empirical work evaluates model safety in brief…

Human-Computer Interaction · Computer Science 2026-04-24 Luke Nicholls , Robert Hutto , Zephrah Soto , Hamilton Morrin , Thomas Pollak , Raj Korpan , Cheryl Carmichael

Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluations are conducted by designing inputs that elicit harmful…

The proliferation of Large Language Models (LLMs) and Intelligent Virtual Agents acting as psychotherapists presents significant opportunities for expanding mental healthcare access. However, their deployment has also been linked to serious…

Computation and Language · Computer Science 2025-09-23 Ian Steenstra , Timothy W. Bickmore

Large Language Models (LLMs) have demonstrated impressive capabilities across various specialist domains and have been integrated into high-stakes areas such as medicine. However, as existing medical-related benchmarks rarely stress-test…

Computation and Language · Computer Science 2026-03-26 Lin Yang , Yuancheng Yang , Xu Wang , Changkun Liu , Haihua Yang

Background: As large language models (LLMs) are increasingly used in healthcare and medical consultation settings, a growing concern is whether these models can respond to medical inquiries in a manner that is ethically…

Computers and Society · Computer Science 2026-02-02 Hanhui Xu , Jiacheng Ji , Haoan Jin , Han Ying , Mengyue Wu

Demand for mental health support through AI chatbots is surging, though current systems present several limitations, like sycophancy or overvalidation, and reinforcement of maladaptive beliefs. A core obstacle to the creation of better…

Computation and Language · Computer Science 2025-12-08 José Pombal , Maya D'Eon , Nuno M. Guerreiro , Pedro Henrique Martins , António Farinhas , Ricardo Rei

Many people suffer from mental health problems but not everyone seeks professional help or has access to mental health care. AI chatbots have increasingly become a go-to for individuals who either have mental disorders or simply want…

Other Quantitative Biology · Quantitative Biology 2025-11-03 Aditya Naik , Jovi Thomas , Teja Sree Mandava , Himavanth Reddy Vemula

Large Language Models (LLMs) have shown promise in various domains, including healthcare, with significant potential to transform mental health applications by enabling scalable and accessible solutions. This study aims to provide a…

Artificial Intelligence · Computer Science 2025-11-25 Abdelrahman Hanafi , Mohammed Saad , Noureldin Zahran , Radwa J. Hanafy , Mohammed E. Fouda

Understanding how large language models (LLMs) process emotionally sensitive content is critical for building safe and reliable systems, particularly in mental health contexts. We investigate the scaling behavior of LLMs on two key tasks:…

Computation and Language · Computer Science 2025-09-08 Edoardo Pinzuti , Oliver Tüscher , André Ferreira Castro

As AI systems advance in capabilities, measuring their safety and alignment to human values is becoming paramount. A fast-growing field of AI research is devoted to developing such assessments. However, most current advances therein may be…

Computers and Society · Computer Science 2026-03-17 Max Hellrigel-Holderbaum , Edward James Young

Millions of users turn to consumer AI chatbots to discuss mental health and behavioral concerns. While this presents unprecedented opportunities to deliver population-level support, it also highlights an urgent need for rigorous and…

Neurons and Cognition · Quantitative Biology 2026-03-10 Veith Weilnhammer , Kevin YC Hou , Lennart Luettgau , Christopher Summerfield , Raymond Dolan , Matthew M Nour

As large language models (LLMs) become increasingly deployed, understanding the complexity and evolution of jailbreaking strategies is critical for AI safety. We present a mass-scale empirical analysis of jailbreak complexity across over 2…

Computation and Language · Computer Science 2026-05-28 Aldan Creo , Raul Castro Fernandez , Manuel Cebrian

Various AI safety datasets have been developed to measure LLMs against evolving interpretations of harm. Our evaluation of five recently published open-source safety benchmarks reveals distinct semantic clusters using UMAP dimensionality…

Machine Learning · Computer Science 2025-05-26 Jonathan Bennion , Shaona Ghosh , Mantek Singh , Nouha Dziri

Safety risks of AI models have been widely studied at deployment time, such as jailbreak attacks that elicit harmful outputs. In contrast, safety risks emerging during training remain largely unexplored. Beyond explicit reward hacking that…

Computation and Language · Computer Science 2026-02-05 Zhexin Zhang , Yida Lu , Junfeng Fang , Junxiao Yang , Shiyao Cui , Hao Zhou , Fandong Meng , Jie Zhou , Hongning Wang , Minlie Huang , Tat-Seng Chua

To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, Frontier AI Risk Management Framework in Practice presents a comprehensive assessment of their frontier risks. As Large…