{"total":19,"rows":[{"id":"2411.12990","title":"BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices","created":"2024-11-20","cited_by_count":114,"area":null},{"id":"2504.18412","title":"Expressing stigma and inappropriate responses prevents LLMs from safely replacing mental health providers","created":"2025-04-25","cited_by_count":69,"area":null},{"id":"2506.08584","title":"CounselBench: A Large-Scale Expert Evaluation and Adversarial Benchmarking of Large Language Models in Mental Health Question Answering","created":"2025-06-10","cited_by_count":21,"area":null},{"id":"2412.05520","title":"More than Marketing? On the Information Value of AI Benchmarks for Practitioners","created":"2024-12-07","cited_by_count":17,"area":null},{"id":"2409.09041","title":"Acceptable Use Policies for Foundation Models","created":"2024-08-29","cited_by_count":12,"area":null},{"id":"2410.13218","title":"CBT-Bench: Evaluating Large Language Models on Assisting Cognitive Behavior Therapy","created":"2024-10-17","cited_by_count":12,"area":null},{"id":"2410.13204","title":"Measuring Free-Form Decision-Making Inconsistency of Language Models in Military Crisis Simulations","created":"2024-10-17","cited_by_count":11,"area":null},{"id":"2510.23845","title":"CRADLE Bench: A Clinician-Annotated Benchmark for Multi-Faceted Mental Health Crisis and Safety Risk Detection","created":"2025-10-27","cited_by_count":8,"area":null},{"id":"2506.05073","title":"Just a Scratch: Enhancing LLM Capabilities for Self-harm Detection through Intent Differentiation and Emoji Interpretation","created":"2025-06-05","cited_by_count":7,"area":null},{"id":"2504.10359","title":"DICE: A Framework for Dimensional and Contextual Evaluation of Language Models","created":"2025-04-14","cited_by_count":3,"area":null},{"id":"2604.02359","title":"Using LLM-as-a-Judge/Jury to Advance Scalable, Clinically-Validated Safety Evaluations of Model Responses to Users Demonstrating Psychosis","created":"2026-03-20","cited_by_count":3,"area":null},{"id":"2512.23859","title":"Seeking Late Night Life Lines: Experiences of Conversational AI Use in Mental Health Crisis","created":"2025-12-29","cited_by_count":2,"area":null},{"id":"2602.09339","title":"Understanding Risk and Dependency in AI Chatbot Use from User Discourse","created":"2026-02-10","cited_by_count":2,"area":null},{"id":"2609.26579","title":"Receptiveness, Not Sycophancy: Distinguishing Engagement from Deference in Language Models","created":"2026-09-22","cited_by_count":2,"area":null},{"id":"2603.01630","title":"SEED-SET: Scalable Evolving Experimental Design for System-level Ethical Testing","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2503.23566","title":"When LLM Therapists Become Salespeople: Evaluating Large Language Models for Ethical Motivational Interviewing","created":"2025-03-30","cited_by_count":0,"area":null},{"id":"2510.08365","title":"Two-Stage Voting for Robust and Efficient Suicide Risk Detection on Social Media","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2607.25057","title":"Psychological Influences of Conversational AI: Research and Design Directions for Reducing Harm and Promoting Well-Being","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2609.35953","title":"Right Words, Wrong Moment: A Clinician-Grounded Analysis of Distress in 19,930 Conversations between Young People and ChatGPT","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}