Skip to content
← Back to explorer

Detecting Stealth Sycophancy in Mental-Health Dialogue with Dynamic Emotional Signature Graphs

Tianze Han, Beining Xu, Hanbo Zhang, Yongming Lu · May 5, 2026 · Citations: 0

How to use this page

Moderate trust

Use this for comparison and orientation, not as your only source.

Best use

Background context only

What to verify

Validate the exact study setup in the full paper before operational use.

Evidence quality

Moderate

Derived from extracted protocol signals and abstract evidence.

Abstract

As conversational AI therapists are increasingly used in psychological support settings, reliable offline evaluation of therapeutic response quality remains an open problem. This paper studies multi-domain support-dialogue evaluation without relying on large language models as final judges. We use a direct LLM judge as a baseline that reads raw dialogue text and predicts whether the target response is harmful, productive, or neutral. We find that direct LLM judges and symmetric text-similarity metrics are poorly aligned with therapeutic quality because the target label depends on clinical direction: whether the response moves the user state toward regulation or reframing, leaves it broadly unchanged, or reinforces deterioration through higher risk affect or cognitive-distortion mass. To address this issue, we propose Dynamic Emotional Signature Graphs (DESG), a model-agnostic evaluator that represents dialogue windows with decoupled clinical states and scores them using asymmetric clinical geometry. We evaluate DESG on a constructed diagnostic stress-test benchmark of 3{,}000 dialogue windows from EmpatheticDialogues, ESConv, and CRADLE-Dialogue, covering peer support, counseling dialogue, and crisis-oriented interaction. On the 600-window held-out test aggregate, DESG-Ensemble achieves 0.9353 macro-F1, exceeding ConcatANN by 1.51 percentage points, BERTScore by 19.63 points, and TRACT by 33.81 points. Feature ablations, artifact controls, a 100-window blinded adjudicator audit, and qualitative disagreement cases indicate that the clinical state manifold is the main discriminative substrate, while graph-based trajectory components provide asymmetric scoring and interpretable diagnostics rather than serving as the sole source of performance.

Should You Rely On This Paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

Main weakness

No major weakness surfaced.

Trust level

Moderate

Usefulness score

35/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

Usefulness for eval research

Adjacent candidate

Extraction confidence 55%

What We Could Verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"As conversational AI therapists are increasingly used in psychological support settings, reliable offline evaluation of therapeutic response quality remains an open problem."

Evaluation Modes

strong

Automatic Metrics

Includes extracted eval setup.

"As conversational AI therapists are increasingly used in psychological support settings, reliable offline evaluation of therapeutic response quality remains an open problem."

Quality Controls

strong

Adjudication

Calibration/adjudication style controls detected.

"As conversational AI therapists are increasingly used in psychological support settings, reliable offline evaluation of therapeutic response quality remains an open problem."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"As conversational AI therapists are increasingly used in psychological support settings, reliable offline evaluation of therapeutic response quality remains an open problem."

Reported Metrics

strong

F1, F1 macro, Bertscore

Useful for evaluation criteria comparison.

"On the 600-window held-out test aggregate, DESG-Ensemble achieves 0.9353 macro-F1, exceeding ConcatANN by 1.51 percentage points, BERTScore by 19.63 points, and TRACT by 33.81 points."

Human Feedback Details

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Not reported
  • Unit of annotation: Trajectory
  • Expertise required: Medicine

Evaluation Details

  • Evaluation modes: Automatic Metrics
  • Agentic eval: Long Horizon
  • Quality controls: Adjudication
  • Evidence quality: Moderate
  • Use this page as: Background context only

Protocol And Measurement Signals

Benchmarks / Datasets

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

Reported Metrics

f1f1 macrobertscore

Research Brief

Metadata summary

As conversational AI therapists are increasingly used in psychological support settings, reliable offline evaluation of therapeutic response quality remains an open problem.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key Takeaways

  • As conversational AI therapists are increasingly used in psychological support settings, reliable offline evaluation of therapeutic response quality remains an open problem.
  • This paper studies multi-domain support-dialogue evaluation without relying on large language models as final judges.
  • We use a direct LLM judge as a baseline that reads raw dialogue text and predicts whether the target response is harmful, productive, or neutral.

Researcher Actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Automatic metrics) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended Queries

Research Summary

Contribution Summary

  • As conversational AI therapists are increasingly used in psychological support settings, reliable offline evaluation of therapeutic response quality remains an open problem.
  • To address this issue, we propose Dynamic Emotional Signature Graphs (DESG), a model-agnostic evaluator that represents dialogue windows with decoupled clinical states and scores them using asymmetric clinical geometry.
  • We evaluate DESG on a constructed diagnostic stress-test benchmark of 3{,}000 dialogue windows from EmpatheticDialogues, ESConv, and CRADLE-Dialogue, covering peer support, counseling dialogue, and crisis-oriented interaction.

Why It Matters For Eval

  • As conversational AI therapists are increasingly used in psychological support settings, reliable offline evaluation of therapeutic response quality remains an open problem.
  • We evaluate DESG on a constructed diagnostic stress-test benchmark of 3{,}000 dialogue windows from EmpatheticDialogues, ESConv, and CRADLE-Dialogue, covering peer support, counseling dialogue, and crisis-oriented interaction.

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Pass: Quality control reporting appears

    Detected: Adjudication

  • Gap: Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Pass: Metric reporting is present

    Detected: f1, f1 macro, bertscore

Related Papers

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

Get Started

Join the #1 Platform for AI Training Talent

Where top AI builders and expert AI Trainers connect to build the future of AI.
Self-Service
Post a Job
Post your project and get a shortlist of qualified AI Trainers and Data Labelers. Hire and manage your team in the tools you already use.
Managed Service
For Large Projects
Done-for-You
We recruit, onboard, and manage a dedicated team inside your tools. End-to-end operations for large or complex projects.
For Freelancers
Join as an AI Trainer
Find AI training and data labeling projects across platforms, all in one place. One profile, one application process, more opportunities.