# Empathy Is Not What Changed: Clinical Assessment of Psychological Safety Across GPT Model Generations

arXiv: https://arxiv.org/abs/2603.09997 · HTML: https://mlsanity.com/paper/2603.09997/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 34 references that are in the map.
- First posted on arXiv 15 Feb 2026.

## Builds on (most cited first, 12 of 12)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [A Computational Approach to Understanding Empathy Expressed in Text-Based Mental Health Support](https://mlsanity.com/paper/2009.08441/) (2020)
- [SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversations](https://mlsanity.com/paper/2311.00273/) (2023)
- [LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Texts](https://mlsanity.com/paper/2501.00274/) (2024)
- [Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey](https://mlsanity.com/paper/2503.22458/) (2025)
- [Large Language Models Produce Responses Perceived to be Empathic](https://mlsanity.com/paper/2403.18148/) (2024)
- [Safer or Luckier? LLMs as Safety Evaluators Are Not Robust to Artifacts](https://mlsanity.com/paper/2503.09347/) (2025)
- [Are Large Language Models More Empathetic than Humans?](https://mlsanity.com/paper/2406.05063/) (2024)
- [Lessons From an App Update at Replika AI: Identity Discontinuity in Human-AI Relationships](https://mlsanity.com/paper/2412.14190/) (2024)
- [Understanding Risk and Dependency in AI Chatbot Use from User Discourse](https://mlsanity.com/paper/2602.09339/) (2026)

## Abstract (arXiv)

When OpenAI deprecated GPT-4o in early 2026, thousands of users protested under #keep4o, claiming newer models had "lost their empathy." No published study has tested this claim. We conducted the first clinical measurement, evaluating three OpenAI model generations (GPT-4o, o4-mini, GPT-5-mini) across 14 emotionally challenging conversational scenarios in mental health and AI companion domains, producing 2,100 scored AI responses assessed on six psychological safety dimensions using clinically-grounded rubrics. Empathy scores are statistically indistinguishable across all three models (Kruskal-Wallis H=4.33, p=0.115). What changed is the safety posture: crisis detection improved monotonically from GPT-4o to GPT-5-mini (H=13.88, p=0.001), while advice safety declined (H=16.63, p<0.001). Per-turn trajectory analysis -- a novel methodological contribution -- reveals these shifts are sharpest during mid-conversation crisis moments invisible to aggregate scoring. In a self-harm scenario involving a minor, GPT-4o scored 3.6/10 on crisis detection during early disclosure turns; GPT-5-mini never dropped below 7.8. What users perceived as "lost empathy" was a shift from a cautious model that missed crises to an alert model that sometimes says too much -- a trade-off with real consequences for vulnerable users, currently invisible to both the people who feel it and the developers who create it.