Skip to content
← Back to explorer

Moving Beyond Medical Exams: A Clinician-Annotated Fairness Dataset of Real-World Tasks and Ambiguity in Mental Healthcare

Max Lamparth, Declan Grabb, Amy Franks, Scott Gershan, Kaitlyn N. Kunstman, Aaron Lulla, Monika Drummond Roots, Manu Sharma, Aryan Shrivastava, Nina Vasan, Colleen Waickman · Feb 22, 2025 · Citations: 0

Automatic Metrics Expert Verification Medicine Pairwise Preference
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

Feb 17, 2026, 6:57 AM

Stale

Extraction refreshed

Apr 13, 2026, 6:26 AM

Fresh

Extraction source

Persisted extraction

Confidence 0.70

Abstract

Current medical language model (LM) benchmarks often over-simplify the complexities of day-to-day clinical practice tasks and instead rely on evaluating LMs on multiple-choice board exam questions. In psychiatry especially, these challenges are worsened by fairness and bias issues, since models can be swayed by patient demographics even when those factors should not influence clinical decisions. Thus, we present an expert-created and annotated dataset spanning five critical domains of decision-making in mental healthcare: treatment, diagnosis, documentation, monitoring, and triage. This U.S.-centric dataset - created without any LM assistance - is designed to capture the nuanced clinical reasoning and daily ambiguities mental health practitioners encounter, reflecting the inherent complexities of care delivery that are missing from existing datasets. Almost all base questions with five answer options each have had the decision-irrelevant demographic patient information removed and replaced with variables, e.g., for age or ethnicity, and are available for male, female, or non-binary-coded patients. This design enables systematic evaluations of model performance and bias by studying how demographic factors affect decision-making. For question categories dealing with ambiguity and multiple valid answer options, we create a preference dataset with uncertainties from the expert annotations. We outline a series of intended use cases and demonstrate the usability of our dataset by evaluating sixteen off-the-shelf and six (mental) health fine-tuned LMs on category-specific task accuracy, on the fairness impact of patient demographic information on decision-making, and how consistently free-form responses deviate from human-annotated samples.

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

65/100 • 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

Pairwise Preference, Expert Verification

Confidence: Moderate Source: Persisted extraction evidenced

Directly usable for protocol triage.

Evidence snippet: Current medical language model (LM) benchmarks often over-simplify the complexities of day-to-day clinical practice tasks and instead rely on evaluating LMs on multiple-choice board exam questions.

Evaluation Modes

strong

Automatic Metrics

Confidence: Moderate Source: Persisted extraction evidenced

Includes extracted eval setup.

Evidence snippet: Current medical language model (LM) benchmarks often over-simplify the complexities of day-to-day clinical practice tasks and instead rely on evaluating LMs on multiple-choice board exam questions.

Quality Controls

missing

Not reported

Confidence: Low Source: Persisted extraction missing

No explicit QC controls found.

Evidence snippet: Current medical language model (LM) benchmarks often over-simplify the complexities of day-to-day clinical practice tasks and instead rely on evaluating LMs on multiple-choice board exam questions.

Benchmarks / Datasets

missing

Not extracted

Confidence: Low Source: Persisted extraction missing

No benchmark anchors detected.

Evidence snippet: Current medical language model (LM) benchmarks often over-simplify the complexities of day-to-day clinical practice tasks and instead rely on evaluating LMs on multiple-choice board exam questions.

Reported Metrics

strong

Accuracy

Confidence: Moderate Source: Persisted extraction evidenced

Useful for evaluation criteria comparison.

Evidence snippet: We outline a series of intended use cases and demonstrate the usability of our dataset by evaluating sixteen off-the-shelf and six (mental) health fine-tuned LMs on category-specific task accuracy, on the fairness impact of patient demographic information on decision-making, and how consistently free-form responses deviate from human-annotated samples.

Rater Population

strong

Domain Experts

Confidence: Moderate Source: Persisted extraction evidenced

Helpful for staffing comparability.

Evidence snippet: Thus, we present an expert-created and annotated dataset spanning five critical domains of decision-making in mental healthcare: treatment, diagnosis, documentation, monitoring, and triage.

Human Data Lens

  • Uses human feedback: Yes
  • Feedback types: Pairwise Preference, Expert Verification
  • Rater population: Domain Experts
  • Unit of annotation: Freeform
  • Expertise required: Medicine
  • Extraction source: Persisted extraction

Evaluation Lens

  • Evaluation modes: Automatic Metrics
  • 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

accuracy

Research Brief

Deterministic synthesis

Current medical language model (LM) benchmarks often over-simplify the complexities of day-to-day clinical practice tasks and instead rely on evaluating LMs on multiple-choice board exam questions. HFEPX signals include Pairwise Preference, Expert Verification, Automatic Metrics with confidence 0.70. Updated from current HFEPX corpus.

Generated Apr 13, 2026, 6:26 AM · Grounded in abstract + metadata only

Key Takeaways

  • Current medical language model (LM) benchmarks often over-simplify the complexities of day-to-day clinical practice tasks and instead rely on evaluating LMs on multiple-choice…
  • Thus, we present an expert-created and annotated dataset spanning five critical domains of decision-making in mental healthcare: treatment, diagnosis, documentation, monitoring,…

Researcher Actions

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

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

  • Current medical language model (LM) benchmarks often over-simplify the complexities of day-to-day clinical practice tasks and instead rely on evaluating LMs on multiple-choice board exam questions.
  • Thus, we present an expert-created and annotated dataset spanning five critical domains of decision-making in mental healthcare: treatment, diagnosis, documentation, monitoring, and triage.
  • We outline a series of intended use cases and demonstrate the usability of our dataset by evaluating sixteen off-the-shelf and six (mental) health fine-tuned LMs on category-specific task accuracy, on the fairness impact of patient…

Why It Matters For Eval

  • Current medical language model (LM) benchmarks often over-simplify the complexities of day-to-day clinical practice tasks and instead rely on evaluating LMs on multiple-choice board exam questions.
  • We outline a series of intended use cases and demonstrate the usability of our dataset by evaluating sixteen off-the-shelf and six (mental) health fine-tuned LMs on category-specific task accuracy, on the fairness impact of patient…

Researcher Checklist

  • Pass: Human feedback protocol is explicit

    Detected: Pairwise Preference, Expert Verification

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • 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: accuracy

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