Skip to content
← Back to explorer

HFEPX Metric Hub

Agreement + Automatic Metrics Metric Papers (Last 90 Days)

Updated from current HFEPX corpus (Apr 12, 2026). 22 papers are grouped in this metric page.

Read Full Context

Updated from current HFEPX corpus (Apr 12, 2026). 22 papers are grouped in this metric page. Common evaluation modes: Automatic Metrics, Llm As Judge. Most common rater population: Domain Experts. Common annotation unit: Pairwise. Frequent quality control: Inter Annotator Agreement Reported. Frequently cited benchmark: ContentBench. Common metric signal: agreement. Use this page to compare protocol setup, judge behavior, and labeling design decisions before running new eval experiments. Newest paper in this set is from Apr 1, 2026.

Papers: 22 Last published: Apr 1, 2026 Global RSS

Researcher Quick Triage

Use this page to compare metric behavior across protocols and benchmarks before selecting your reporting stack. Quality band: Medium .

Metric Coverage

100.0%

22 sampled papers include metric names.

Benchmark Anchoring

13.6%

Papers with explicit dataset/benchmark anchors for fair comparison.

Quality Controls

45.5%

10 papers report calibration/adjudication/IAA controls.

  • 22 papers are not low-signal flagged in this sample.
  • Use the protocol matrix below to avoid comparing metrics across incompatible eval setups.

Primary action: Treat this as directional signal only; metric reporting is present but benchmark anchoring is still thin.

Why This Matters (Expanded)

Why This Matters For Eval Research

  • 63.6% of papers report explicit human-feedback signals, led by pairwise preferences.
  • automatic metrics appears in 100% of papers in this hub.
  • ContentBench is a recurring benchmark anchor for cross-paper comparisons in this page.
Metric Notes (Expanded)

Metric-Driven Protocol Takeaways

  • 1 sampled papers report both human evaluation and LLM-as-judge, supporting direct agreement checks.
  • Most common quality-control signal is inter-annotator agreement reporting (31.8% of papers).
  • Rater context is mostly domain experts, and annotation is commonly pairwise annotation; use this to scope replication staffing.

Metric Interpretation

  • agreement is reported in 100% of hub papers (22/22); compare with a secondary metric before ranking methods.
  • accuracy is reported in 45.5% of hub papers (10/22); compare with a secondary metric before ranking methods.

Benchmark Context

  • ContentBench appears in 4.5% of hub papers (1/22); use this cohort for benchmark-matched comparisons.
  • GSM8K appears in 4.5% of hub papers (1/22); use this cohort for benchmark-matched comparisons.

Start Here (Metric-Reliable First 6)

Ranked for metric reporting completeness and comparability.

Metric Protocol Matrix (Top 10)

Compare metric, benchmark, and evaluation context side by side.

Paper Metrics Benchmarks Eval Modes Quality Controls
More Human, More Efficient: Aligning Annotations with Quantized SLMs

Apr 1, 2026

Agreement Not reported Automatic Metrics Inter Annotator Agreement Reported, Adjudication
When AI Meets Early Childhood Education: Large Language Models as Assessment Teammates in Chinese Preschools

Mar 25, 2026

Agreement, Cost Interaction2eval Automatic Metrics Not reported
A Multi-Stage Validation Framework for Trustworthy Large-scale Clinical Information Extraction using Large Language Models

Apr 7, 2026

F1, Agreement Not reported Automatic Metrics Calibration, Adjudication
From Consensus to Split Decisions: ABC-Stratified Sentiment in Holocaust Oral Histories

Mar 30, 2026

Kappa, Agreement Not reported Automatic Metrics Inter Annotator Agreement Reported
ReasonScaffold: A Scaffolded Reasoning-based Annotation Protocol for Human-AI Co-Annotation

Mar 22, 2026

Accuracy, Agreement Not reported Automatic Metrics Inter Annotator Agreement Reported
Modeling Expert AI Diagnostic Alignment via Immutable Inference Snapshots

Feb 26, 2026

Agreement Not reported Automatic Metrics Adjudication
Yor-Sarc: A gold-standard dataset for sarcasm detection in a low-resource African language

Feb 21, 2026

Agreement Not reported Automatic Metrics Inter Annotator Agreement Reported, Adjudication
Same Words, Different Judgments: Modality Effects on Preference Alignment

Feb 26, 2026

Agreement Not reported Automatic Metrics Inter Annotator Agreement Reported
Can Large Language Models Replace Human Coders? Introducing ContentBench

Feb 23, 2026

Agreement, Cost ContentBench Automatic Metrics Not reported
Don't Overthink It: Inter-Rollout Action Agreement as a Free Adaptive-Compute Signal for LLM Agents

Apr 9, 2026

Accuracy GSM8K Automatic Metrics Not reported
Researcher Workflow (Detailed)

Checklist

  • Strong: Papers with explicit human feedback

    Coverage is strong (63.6% vs 45% target).

  • Strong: Papers reporting quality controls

    Coverage is strong (45.5% vs 30% target).

  • Gap: Papers naming benchmarks/datasets

    Coverage is a replication risk (13.6% vs 35% target).

  • Strong: Papers naming evaluation metrics

    Coverage is strong (100% vs 35% target).

  • Strong: Papers with known rater population

    Coverage is strong (40.9% vs 35% target).

  • Strong: Papers with known annotation unit

    Coverage is strong (45.5% vs 35% target).

Strengths

  • Strong human-feedback signal (63.6% of papers).
  • Quality-control evidence appears in 45.5% of papers.
  • Contains both human-eval and LLM-as-judge protocols for head-to-head methodology comparison.

Known Gaps

  • Benchmark coverage is thin (13.6% of papers mention benchmarks/datasets).

Suggested Next Analyses

  • Compare papers that report both human_eval and llm_as_judge to quantify judge-human agreement drift.
  • Stratify by benchmark (ContentBench vs GSM8K) before comparing methods.
  • Track metric sensitivity by reporting both agreement and accuracy.

Recommended Queries

Known Limitations
  • Benchmark coverage is thin (13.6% of papers mention benchmarks/datasets).
  • Narrative synthesis is grounded in metadata and abstracts only; full-paper implementation details are not parsed.
  • Cross-page comparisons should be benchmark- and metric-matched to avoid protocol confounding.
Research Utility Snapshot (Detailed)

Top Metrics

  • Agreement (22)
  • Accuracy (10)
  • Cost (4)
  • F1 (3)

Evaluation Modes

  • Automatic Metrics (22)
  • Llm As Judge (3)
  • Human Eval (2)
  • Simulation Env (1)

Top Benchmarks

  • ContentBench (1)
  • GSM8K (1)
  • Interaction2eval (1)

Agentic Mix

  • Long Horizon (3)
  • Web Browsing (2)
  • Multi Agent (1)

Top Papers Reporting This Metric

Related Metric Hubs

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