Skip to content
← Back to explorer

Do No Harm: Exposing Hidden Vulnerabilities of LLMs via Persona-based Client Simulation Attack in Psychological Counseling

Qingyang Xu, Yaling Shen, Stephanie Fong, Zimu Wang, Yiwen Jiang, Xiangyu Zhao, Jiahe Liu, Zhongxing Xu, Vincent Lee, Zongyuan Ge · Apr 6, 2026 · Citations: 0

Medicine Red Team Simulation Env
Open arXiv Find Implementation RSS feed Shortlist (0)

Data freshness

Extraction: Fresh

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Apr 6, 2026, 4:43 PM

Recent

Extraction refreshed

Apr 9, 2026, 12:48 PM

Fresh

Extraction source

Persisted extraction

Confidence 0.70

Abstract

The increasing use of large language models (LLMs) in mental healthcare raises safety concerns in high-stakes therapeutic interactions. A key challenge is distinguishing therapeutic empathy from maladaptive validation, where supportive responses may inadvertently reinforce harmful beliefs or behaviors in multi-turn conversations. This risk is largely overlooked by existing red-teaming frameworks, which focus mainly on generic harms or optimization-based attacks. To address this gap, we introduce Personality-based Client Simulation Attack (PCSA), the first red-teaming framework that simulates clients in psychological counseling through coherent, persona-driven client dialogues to expose vulnerabilities in psychological safety alignment. Experiments on seven general and mental health-specialized LLMs show that PCSA substantially outperforms four competitive baselines. Perplexity analysis and human inspection further indicate that PCSA generates more natural and realistic dialogues. Our results reveal that current LLMs remain vulnerable to domain-specific adversarial tactics, providing unauthorized medical advice, reinforcing delusions, and implicitly encouraging risky actions.

HFEPX Relevance Assessment

This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.

Best use

Secondary protocol comparison source

Use if you need

A secondary eval reference to pair with stronger protocol papers.

Main weakness

No major weakness surfaced.

Trust level

Moderate

Eval-Fit Score

67/100 • Medium

Useful as a secondary reference; validate protocol details against neighboring papers.

Human Feedback Signal

Detected

Evaluation Signal

Detected

HFEPX Fit

Moderate-confidence candidate

Extraction confidence: Moderate

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

strong

Red Team

Confidence: Moderate Source: Persisted extraction evidenced

Directly usable for protocol triage.

Evidence snippet: The increasing use of large language models (LLMs) in mental healthcare raises safety concerns in high-stakes therapeutic interactions.

Evaluation Modes

strong

Simulation Env

Confidence: Moderate Source: Persisted extraction evidenced

Includes extracted eval setup.

Evidence snippet: The increasing use of large language models (LLMs) in mental healthcare raises safety concerns in high-stakes therapeutic interactions.

Quality Controls

missing

Not reported

Confidence: Low Source: Persisted extraction missing

No explicit QC controls found.

Evidence snippet: The increasing use of large language models (LLMs) in mental healthcare raises safety concerns in high-stakes therapeutic interactions.

Benchmarks / Datasets

missing

Not extracted

Confidence: Low Source: Persisted extraction missing

No benchmark anchors detected.

Evidence snippet: The increasing use of large language models (LLMs) in mental healthcare raises safety concerns in high-stakes therapeutic interactions.

Reported Metrics

strong

Perplexity

Confidence: Moderate Source: Persisted extraction evidenced

Useful for evaluation criteria comparison.

Evidence snippet: Perplexity analysis and human inspection further indicate that PCSA generates more natural and realistic dialogues.

Rater Population

missing

Unknown

Confidence: Low Source: Persisted extraction missing

Rater source not explicitly reported.

Evidence snippet: The increasing use of large language models (LLMs) in mental healthcare raises safety concerns in high-stakes therapeutic interactions.

Human Data Lens

  • Uses human feedback: Yes
  • Feedback types: Red Team
  • Rater population: Unknown
  • Unit of annotation: Unknown
  • Expertise required: Medicine
  • Extraction source: Persisted extraction

Evaluation Lens

  • Evaluation modes: Simulation Env
  • Agentic eval: None
  • Quality controls: Not reported
  • Confidence: 0.70
  • Flags: None

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

perplexity

Research Brief

Deterministic synthesis

The increasing use of large language models (LLMs) in mental healthcare raises safety concerns in high-stakes therapeutic interactions. HFEPX signals include Red Team, Simulation Env with confidence 0.70. Updated from current HFEPX corpus.

Generated Apr 9, 2026, 12:48 PM · Grounded in abstract + metadata only

Key Takeaways

  • The increasing use of large language models (LLMs) in mental healthcare raises safety concerns in high-stakes therapeutic interactions.
  • To address this gap, we introduce Personality-based Client Simulation Attack (PCSA), the first red-teaming framework that simulates clients in psychological counseling through…

Researcher Actions

  • Compare its human-feedback setup against pairwise and rubric hubs.
  • Identify benchmark choices from full text before operationalizing conclusions.
  • Validate metric comparability (perplexity).

Caveats

  • Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
  • Extraction confidence is probabilistic and should be validated for critical decisions.

Research Summary

Contribution Summary

  • The increasing use of large language models (LLMs) in mental healthcare raises safety concerns in high-stakes therapeutic interactions.
  • To address this gap, we introduce Personality-based Client Simulation Attack (PCSA), the first red-teaming framework that simulates clients in psychological counseling through coherent, persona-driven client dialogues to expose…
  • Perplexity analysis and human inspection further indicate that PCSA generates more natural and realistic dialogues.

Why It Matters For Eval

  • The increasing use of large language models (LLMs) in mental healthcare raises safety concerns in high-stakes therapeutic interactions.
  • To address this gap, we introduce Personality-based Client Simulation Attack (PCSA), the first red-teaming framework that simulates clients in psychological counseling through coherent, persona-driven client dialogues to expose…

Researcher Checklist

  • Pass: Human feedback protocol is explicit

    Detected: Red Team

  • Pass: Evaluation mode is explicit

    Detected: Simulation Env

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Gap: Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Pass: Metric reporting is present

    Detected: perplexity

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote