Skip to content
← Back to explorer

HFEPX Hub

CS.AI + Rubric Rating Papers

Updated from current HFEPX corpus (Mar 8, 2026). 15 papers are grouped in this hub page.

Read Full Context

Updated from current HFEPX corpus (Mar 8, 2026). 15 papers are grouped in this hub page. Common evaluation modes: Automatic Metrics, Llm As Judge. Most common rater population: Domain Experts. Common annotation unit: Multi Dim Rubric. Frequent quality control: Inter Annotator Agreement Reported. Frequently cited benchmark: Healthbench. 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 Mar 2, 2026.

Papers: 15 Last published: Mar 2, 2026 Global RSS Tag RSS
Cs.AIRubric Rating

Researcher Quick Triage

This hub is best used for protocol triage and replication planning from abstract-level evidence. Quality band: Developing .

All Sampled Papers (15) Replication-Ready Only (2)

High-Signal Coverage

100.0%

15 / 15 sampled papers are not low-signal flagged.

Replication-Ready Set

2

Benchmark + metric + eval mode explicitly present.

Judge/Human Comparability

2

Papers containing both `human_eval` and `llm_as_judge`.

  • 2 papers are replication-ready (benchmark + metric + explicit evaluation mode).
  • 2 papers support judge-vs-human agreement analysis.
  • 2 papers report explicit quality controls (calibration/adjudication/IAA).

Primary action: Use this page for scouting only; collect additional papers before attempting replication-critical comparisons.

Currently showing only replication-ready papers in ranking and matrix sections (2 papers).

Why This Matters For Eval Research

  • 100% of papers report explicit human-feedback signals, led by rubric ratings.
  • automatic metrics appears in 40% of papers in this hub.
  • Healthbench is a recurring benchmark anchor for cross-paper comparisons in this page.

Protocol Takeaways

  • 2 sampled papers report both human evaluation and LLM-as-judge, supporting direct agreement checks.
  • Most common quality-control signal is inter-annotator agreement reporting (13.3% of papers).
  • Rater context is mostly domain experts, and annotation is commonly multi-dimensional rubrics; use this to scope replication staffing.

Benchmark Interpretation

  • Healthbench appears in 13.3% of hub papers (2/15); use this cohort for benchmark-matched comparisons.
  • CAPArena appears in 6.7% of hub papers (1/15); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • agreement is reported in 26.7% of hub papers (4/15); compare with a secondary metric before ranking methods.
  • accuracy is reported in 20% of hub papers (3/15); compare with a secondary metric before ranking methods.
Researcher Checklist (Expanded)

Researcher Checklist

  • Strong: Papers with explicit human feedback

    Coverage is strong (100% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (13.3% vs 30% target).

  • Moderate: Papers naming benchmarks/datasets

    Coverage is usable but incomplete (26.7% vs 35% target).

  • Strong: Papers naming evaluation metrics

    Coverage is strong (53.3% vs 35% target).

  • Strong: Papers with known rater population

    Coverage is strong (66.7% vs 35% target).

  • Strong: Papers with known annotation unit

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

Strengths

  • Strong human-feedback signal (100% of papers).
  • Contains both human-eval and LLM-as-judge protocols for head-to-head methodology comparison.
  • Agentic evaluation appears in 26.7% of papers.

Known Gaps

  • Only 13.3% of papers report quality controls; prioritize calibration/adjudication evidence.

Suggested Next Analyses

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

Recommended Queries

Judge vs Human Agreement Benchmark Slice: Healthbench Metric Slice: agreement IAA-Reported Evaluations Recent High-Signal Papers

Start with These 3

Use these when you need one protocol anchor, one benchmark anchor, and one recent comparison point before reading the wider hub.

Start Here (Best First 6)

Ranked for protocol completeness (human signal, benchmark + metric anchors, quality controls, and judge/human overlap).

Protocol Matrix (Top 12)

Use this to quickly compare protocol ingredients instead of scanning long prose.

Paper HF Signal Eval Modes Benchmarks Metrics QC
PoSh: Using Scene Graphs To Guide LLMs-as-a-Judge For Detailed Image Descriptions

Oct 21, 2025

 Yes
Rubric Rating
Human Eval , Llm As Judge CAPArena Spearman Not Reported
PanCanBench: A Comprehensive Benchmark for Evaluating Large Language Models in Pancreatic Oncology

Mar 2, 2026

 Yes
Rubric Rating , Expert Verification
Llm As Judge , Automatic Metrics Pancanbench , Healthbench Accuracy Not Reported

Protocol Diff (Top Papers)

Fast side-by-side comparison for the highest-ranked papers in this hub.

Signal PoSh: Using Scene Graphs To Guide LLMs-as-a-Judge F… PanCanBench: A Comprehensive Benchmark for Evaluati…
Human Feedback Rubric RatingRubric Rating, Expert Verification
Evaluation Modes Human Eval, Llm As JudgeLlm As Judge, Automatic Metrics
Benchmarks CAPArenaPancanbench, Healthbench
Metrics SpearmanAccuracy
Quality Controls Not reportedNot reported
Rater Population Domain ExpertsDomain Experts
Annotation Unit Multi Dim RubricMulti Dim Rubric
Suggested Reading Order (Extended)

This section is intentionally expanded only when needed; use “Start Here” above for a faster pass.

Suggested Reading Order

  1. A Scalable Framework for Evaluating Health Language Models

    Start here for detailed protocol reporting and quality-control evidence. Signals: automatic metrics + rubric ratings. Focus: accuracy. Abstract: In this work, we introduce Adaptive Precise Boolean rubrics: an.

  2. PanCanBench: A Comprehensive Benchmark for Evaluating Large Language Models in Pancreatic Oncology

    High citation traction makes this a strong baseline for protocol comparison. Signals: LLM-as-judge + rubric ratings. Focus: Pancanbench / accuracy. Abstract: Moreover, high rubric-based scores do not ensure.

  3. Optimizing In-Context Demonstrations for LLM-based Automated Grading

    High citation traction makes this a strong baseline for protocol comparison. Signals: rubric ratings. Abstract: Standard retrieval methods typically select examples based on semantic similarity, which often fails.

  4. Confusion-Aware Rubric Optimization for LLM-based Automated Grading

    High citation traction makes this a strong baseline for protocol comparison. Signals: automatic metrics + rubric ratings. Focus: accuracy. Abstract: To address these limitations, we introduce Confusion-Aware Rubric.

  5. PoSh: Using Scene Graphs To Guide LLMs-as-a-Judge For Detailed Image Descriptions

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: human evaluation + rubric ratings. Focus: CAPArena / spearman. Abstract: In this work, we introduce PoSh, a.

  6. HEART: A Unified Benchmark for Assessing Humans and LLMs in Emotional Support Dialogue

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: human evaluation + pairwise preferences. Focus: agreement. Abstract: For each dialogue history, we pair human and model.

  7. APEX-Agents

    Adds automatic metrics with rubric ratings for broader protocol coverage within this hub. Signals: automatic metrics + rubric ratings. Focus: pass@1. Abstract: We open source the APEX-Agents benchmark.

  8. MENLO: From Preferences to Proficiency -- Evaluating and Modeling Native-like Quality Across 47 Languages

    Adds automatic metrics with pairwise preferences for broader protocol coverage within this hub. Signals: automatic metrics + pairwise preferences. Focus: agreement. Abstract: Using MENLO, we create a dataset.

Known Limitations

Known Limitations

  • Only 13.3% of papers report quality controls; prioritize calibration/adjudication evidence.
  • 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)

Research Utility Snapshot

Human Feedback Mix

  • Rubric Rating (15)
  • Pairwise Preference (5)
  • Expert Verification (4)
  • Demonstrations (1)

Evaluation Modes

  • Automatic Metrics (6)
  • Llm As Judge (3)
  • Human Eval (2)

Top Benchmarks

  • Healthbench (2)
  • CAPArena (1)
  • MLE Bench (1)
  • Pancanbench (1)

Top Metrics

  • Agreement (4)
  • Accuracy (3)
  • Cost (1)
  • Pass@1 (1)

Rater Population Mix

  • Domain Experts (9)
  • Mixed (1)

Quality Controls

  • Inter Annotator Agreement Reported (2)
Coverage diagnostics (sample-based): human-feedback 100.0% · benchmarks 26.7% · metrics 46.7% · quality controls 13.3%.

Top Papers

Related Hubs

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

Post a Job Get a Quote