# Towards Understanding and Measuring COGNITIVE ATROPHY in LLM Behaviour

arXiv: https://arxiv.org/abs/2606.18129 · HTML: https://mlsanity.com/paper/2606.18129/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 62 references that are in the map.
- First posted on arXiv 16 Jun 2026.

## Builds on (most cited first, 14 of 14)

- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling](https://mlsanity.com/paper/2405.16433/) (2024)
- [Expressing stigma and inappropriate responses prevents LLMs from safely replacing mental health providers](https://mlsanity.com/paper/2504.18412/) (2025)
- [MentalChat16K: A Benchmark Dataset for Conversational Mental Health Assistance](https://mlsanity.com/paper/2503.13509/) (2025)
- [Speaker and Time-aware Joint Contextual Learning for Dialogue-act Classification in Counselling Conversations](https://mlsanity.com/paper/2111.06647/) (2021)
- [Do Large Language Models Align with Core Mental Health Counseling Competencies?](https://mlsanity.com/paper/2410.22446/) (2024)
- [When Can We Trust LLMs in Mental Health? Large-Scale Benchmarks for Reliable LLM Evaluation](https://mlsanity.com/paper/2510.19032/) (2025)
- [PsyEval: A Suite of Mental Health Related Tasks for Evaluating Large Language Models](https://mlsanity.com/paper/2311.09189/) (2023)
- [CBT-Bench: Evaluating Large Language Models on Assisting Cognitive Behavior Therapy](https://mlsanity.com/paper/2410.13218/) (2024)
- [MHQA: A Diverse, Knowledge Intensive Mental Health Question Answering Challenge for Language Models](https://mlsanity.com/paper/2502.15418/) (2025)
- [Assessing the Quality of Mental Health Support in LLM Responses through Multi-Attribute Human Evaluation](https://mlsanity.com/paper/2601.18630/) (2026)
- [Exploring Safety Alignment Evaluation of LLMs in Chinese Mental Health Dialogues via LLM-as-Judge](https://mlsanity.com/paper/2508.08236/) (2025)
- [Position: Beyond Assistance -- Reimagining LLMs as Ethical and Adaptive Co-Creators in Mental Health Care](https://mlsanity.com/paper/2503.16456/) (2025)
- [Being Kind Isn't Always Being Safe: Diagnosing Affective Hallucination in LLMs](https://mlsanity.com/paper/2508.16921/) (2025)

## Abstract (arXiv)

Recent incidents involving LLMs used for mental-health support reveal a critical evaluation gap: surface-level safety scores do not capture how models behave across realistic, emotionally sensitive interactions over time. Existing benchmarks measure knowledge, safety, or static response quality, but miss whether LLM interactions help users keep reflecting, coping, and making decisions themselves. We formalize this missing dimension as COGNITIVE ATROPHY, a process-level behavioural measure in AI-mediated mental-health support distinct from safety and helpfulness. To measure it, we introduce COGNITIVE ATROPHY BENCH, a clinically grounded benchmark built from 1,576 fully human-generated counseling conversations, 15,680 turns, and 42,230 responses from five LLMs. Three clinical and neuropsychology experts developed a 20-attribute schema spanning user context, response behaviour, and global risk flags; six trained clinical reviewers applied it with span-grounded evidence, producing 5,324 reviewer judgments. We further introduce the User-Input Risk Index (UIRI), the Cognitive Atrophy Risk Index (ARI), and trajectory summaries. Across five LLMs, models show a consistent moderate-to-high level of atrophy-aligned behaviour across single and multi-turn settings. While models generally respond to overt safety cues, they adapt less reliably when users seek solutions or decisions. The dominant recurring patterns are directive advice, problem-solving, recommendation responses, topic shifts, and forms of validation that may reinforce dependence rather than reflection. Our work makes COGNITIVE ATROPHY measurable and provides a foundation for auditing model behaviour in sensitive LLM conversations.