Can LLMs Capture Expert Uncertainty? A Comparative Analysis of Value Alignment in Ethnographic Qualitative Research

Arina Kostina, Marios Dikaiakos, Alejandro Porcel, Tassos Stassopoulos · Mar 5, 2026 · Citations: 0

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

Mar 5, 2026, 7:38 AM

Fresh

Extraction refreshed

Mar 7, 2026, 2:53 AM

Fresh

Extraction source

Persisted extraction

Confidence 0.45

Abstract

Qualitative analysis of open-ended interviews plays a central role in ethnographic and economic research by uncovering individuals' values, motivations, and culturally embedded financial behaviors. While large language models (LLMs) offer promising support for automating and enriching such interpretive work, their ability to produce nuanced, reliable interpretations under inherent task ambiguity remains unclear. In our work we evaluate LLMs on the task of identifying the top three human values expressed in long-form interviews based on the Schwartz Theory of Basic Values framework. We compare their outputs to expert annotations, analyzing both performance and uncertainty patterns relative to the experts. Results show that LLMs approach the human ceiling on set-based metrics (F1, Jaccard) but struggle to recover exact value rankings, as reflected in lower RBO scores. While the average Schwartz value distributions of most models closely match those of human analysts, their uncertainty structures across the Schwartz values diverge from expert uncertainty patterns. Among the evaluated models, Qwen performs closest to expert-level agreement and exhibits the strongest alignment with expert Schwartz value distributions. LLM ensemble methods yield consistent gains across metrics, with Majority Vote and Borda Count performing best. Notably, systematic overemphasis on certain Schwartz values, like Security, suggests both the potential of LLMs to provide complementary perspectives and the need to further investigate model-induced value biases. Overall, our findings highlight both the promise and the limitations of LLMs as collaborators in inherently ambiguous qualitative value analysis.

Low-signal caution for protocol decisions

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

Extraction flags indicate low-signal or possible false-positive protocol mapping.
Extraction confidence is 0.45 (below strong-reference threshold).

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

HFEPX Relevance Assessment

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

Extraction flags indicate low-signal or possible false-positive protocol mapping.

Trust level

Low

Eval-Fit Score

15/100 • Low

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

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

HFEPX Fit

Adjacent candidate

Extraction confidence: Low

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

missing

None explicit

Confidence: Low Source: Persisted extraction missing

No explicit feedback protocol extracted.

Evidence snippet: Qualitative analysis of open-ended interviews plays a central role in ethnographic and economic research by uncovering individuals' values, motivations, and culturally embedded financial behaviors.

Evaluation Modes

partial

Automatic Metrics

Confidence: Low Source: Persisted extraction evidenced

Includes extracted eval setup.

Quality Controls

partial

Adjudication

Confidence: Low Source: Persisted extraction evidenced

Calibration/adjudication style controls detected.

Benchmarks / Datasets

missing

Not extracted

Confidence: Low Source: Persisted extraction missing

No benchmark anchors detected.

Reported Metrics

partial

F1, Agreement

Confidence: Low Source: Persisted extraction evidenced

Useful for evaluation criteria comparison.

Evidence snippet: Among the evaluated models, Qwen performs closest to expert-level agreement and exhibits the strongest alignment with expert Schwartz value distributions.

Rater Population

partial

Domain Experts

Confidence: Low Source: Persisted extraction evidenced

Helpful for staffing comparability.

Evidence snippet: We compare their outputs to expert annotations, analyzing both performance and uncertainty patterns relative to the experts.

Human Data Lens

Uses human feedback: No
Feedback types: None
Rater population: Domain Experts
Unit of annotation: Ranking
Expertise required: General
Extraction source: Persisted extraction

Evaluation Lens

Evaluation modes: Automatic Metrics
Agentic eval: None
Quality controls: Adjudication
Confidence: 0.45
Flags: low_signal, possible_false_positive

Protocol And Measurement Signals

Benchmarks / Datasets

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

Reported Metrics

f1agreement

Research Brief

Deterministic synthesis

In our work we evaluate LLMs on the task of identifying the top three human values expressed in long-form interviews based on the Schwartz Theory of Basic Values framework. HFEPX signals include Automatic Metrics with confidence 0.45. Updated from current HFEPX corpus.

Generated Mar 7, 2026, 2:53 AM · Grounded in abstract + metadata only

Key Takeaways

In our work we evaluate LLMs on the task of identifying the top three human values expressed in long-form interviews based on the Schwartz Theory of Basic Values framework.
Results show that LLMs approach the human ceiling on set-based metrics (F1, Jaccard) but struggle to recover exact value rankings, as reflected in lower RBO scores.

Researcher Actions

Treat this as method context, then pivot to protocol-specific HFEPX hubs.
Identify benchmark choices from full text before operationalizing conclusions.
Validate metric comparability (f1, agreement).

Caveats

Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
Low-signal flag detected: protocol relevance may be indirect.

Recommended Queries

human-eval protocol design pairwise preference data quality adjudication reporting patterns

Research Summary

Contribution Summary

In our work we evaluate LLMs on the task of identifying the top three human values expressed in long-form interviews based on the Schwartz Theory of Basic Values framework.
Results show that LLMs approach the human ceiling on set-based metrics (F1, Jaccard) but struggle to recover exact value rankings, as reflected in lower RBO scores.
While the average Schwartz value distributions of most models closely match those of human analysts, their uncertainty structures across the Schwartz values diverge from expert uncertainty patterns.

Why It Matters For Eval

In our work we evaluate LLMs on the task of identifying the top three human values expressed in long-form interviews based on the Schwartz Theory of Basic Values framework.
Results show that LLMs approach the human ceiling on set-based metrics (F1, Jaccard) but struggle to recover exact value rankings, as reflected in lower RBO scores.

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, agreement

Category-Adjacent Papers (Broader Context)

These papers are nearby in arXiv category and useful for broader context, but not necessarily protocol-matched to this paper.

ThaiSafetyBench: Assessing Language Model Safety in Thai Cultural Contexts
Benchmark-aligned Protocol Overlap

Citations: 0 Relevance: 3.30
- Shared arXiv category (cs.CL)
- Shared metric mentions
AILS-NTUA at SemEval-2026 Task 10: Agentic LLMs for Psycholinguistic Marker Extraction and Conspiracy Endorsement Detection
Benchmark-aligned Protocol Overlap

Citations: 0 Relevance: 2.85
- Shared arXiv category (cs.CL)
- Shared metric mentions
Autoscoring Anticlimax: A Meta-analytic Understanding of AI's Short-answer Shortcomings and Wording Weaknesses
QC-aligned Protocol Overlap

Citations: 0 Relevance: 2.50
- Shared arXiv category (cs.CL)
- Shared terminology (agreement, llms)
VRM: Teaching Reward Models to Understand Authentic Human Preferences
Category Neighbor Protocol Overlap

Citations: 0 Relevance: 2.50
- Shared arXiv category (cs.CL)
- Shared terminology (llms, capture)
When Weak LLMs Speak with Confidence, Preference Alignment Gets Stronger
Category Neighbor Protocol Overlap

Citations: 0 Relevance: 2.50
- Shared arXiv category (cs.CL)
- Shared terminology (llms, alignment)
Alignment Backfire: Language-Dependent Reversal of Safety Interventions Across 16 Languages in LLM Multi-Agent Systems
Category Neighbor Protocol Overlap

Citations: 0 Relevance: 2.05
- Shared arXiv category (cs.CL)
- Shared terminology (alignment)
Beyond the Context Window: A Cost-Performance Analysis of Fact-Based Memory vs. Long-Context LLMs for Persistent Agents
Category Neighbor Protocol Overlap

Citations: 0 Relevance: 2.05
- Shared arXiv category (cs.CL)
- Shared terminology (llms)
Functionality-Oriented LLM Merging on the Fisher--Rao Manifold
Category Neighbor Protocol Overlap

Citations: 0 Relevance: 2.05
- Shared arXiv category (cs.CL)
- Shared terminology (llms)

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

Post a Job Get a Quote