Skip to content
← Back to explorer

HFEPX Hub

Automatic Metrics Papers (Last 30 Days)

Updated from current HFEPX corpus (Apr 19, 2026). 394 papers are grouped in this hub page.

Read Full Context

Updated from current HFEPX corpus (Apr 19, 2026). 394 papers are grouped in this hub page. Common evaluation modes: Automatic Metrics, Human Eval. Most common rater population: Domain Experts. Common annotation unit: Ranking. Frequent quality control: Calibration. Frequently cited benchmark: GSM8K. Common metric signal: accuracy. 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 8, 2026.

Papers: 394 Last published: Apr 8, 2026 Global RSS Tag RSS
Automatic MetricsLast 30d

Researcher Quick Triage

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

Analysis blocks below are computed from the currently loaded sample (60 of 394 total papers in this hub).

High-Signal Coverage

100.0%

60 / 60 sampled papers are not low-signal flagged.

Replication-Ready Set

22

Benchmark + metric + eval mode explicitly present.

Judge/Human Comparability

1

Papers containing both `human_eval` and `llm_as_judge`.

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

Primary action: Start with the top 2 papers in “Start Here”, then validate assumptions in the protocol matrix.

Currently showing only replication-ready papers in ranking and matrix sections (22 papers).

Need evaluators for this research workflow?

Post a Job →

Why This Matters For Eval Research

  • 13.7% of papers report explicit human-feedback signals, led by pairwise preferences.
  • automatic metrics appears in 100% of papers in this hub.
  • GSM8K is a recurring benchmark anchor for cross-paper comparisons in this page.

Protocol Takeaways

  • Most common quality-control signal is rater calibration (4.1% of papers).
  • Rater context is mostly domain experts, and annotation is commonly ranking annotation; use this to scope replication staffing.
  • Compare papers that report both human_eval and llm_as_judge to quantify judge-human agreement drift.

Benchmark Interpretation

  • GSM8K appears in 0.8% of hub papers (3/394); use this cohort for benchmark-matched comparisons.
  • BFCL appears in 0.5% of hub papers (2/394); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 18.3% of hub papers (72/394); compare with a secondary metric before ranking methods.
  • cost is reported in 5.6% of hub papers (22/394); compare with a secondary metric before ranking methods.
Researcher Checklist (Expanded)

Researcher Checklist

  • Gap: Papers with explicit human feedback

    Coverage is a replication risk (13.7% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (8.4% vs 30% target).

  • Gap: Papers naming benchmarks/datasets

    Coverage is a replication risk (8.4% vs 35% target).

  • Moderate: Papers naming evaluation metrics

    Coverage is usable but incomplete (30.7% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (12.7% vs 35% target).

  • Gap: Papers with known annotation unit

    Coverage is a replication risk (17.8% vs 35% target).

Strengths

  • Contains both human-eval and LLM-as-judge protocols for head-to-head methodology comparison.

Known Gaps

  • Only 8.4% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (12.7% coverage).
  • Annotation unit is under-specified (17.8% coverage).

Suggested Next Analyses

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

Recommended Queries

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
Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization

Apr 8, 2026

Yes Human Eval , Automatic Metrics Rewardbench Accuracy , Helpfulness Not Reported
PubMed Reasoner: Dynamic Reasoning-based Retrieval for Evidence-Grounded Biomedical Question Answering

Mar 28, 2026

Yes Llm As Judge , Automatic Metrics MMLU Accuracy , Relevance Not Reported
TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories

Apr 8, 2026

Yes Automatic Metrics Tracesafe Bench Accuracy Not Reported
Beyond Paper-to-Paper: Structured Profiling and Rubric Scoring for Paper-Reviewer Matching

Apr 7, 2026

Yes Automatic Metrics Scirepeval Recall Not Reported
Xpertbench: Expert Level Tasks with Rubrics-Based Evaluation

Mar 27, 2026

Yes Automatic Metrics Xpertbench Success rate Not Reported
When AI Meets Early Childhood Education: Large Language Models as Assessment Teammates in Chinese Preschools

Mar 25, 2026

Yes Automatic Metrics Interaction2eval Agreement Not Reported
Paper Reconstruction Evaluation: Evaluating Presentation and Hallucination in AI-written Papers

Apr 1, 2026

Yes Automatic Metrics Paperwrite Bench Not Reported Not Reported
Rethinking Atomic Decomposition for LLM Judges: A Prompt-Controlled Study of Reference-Grounded QA Evaluation

Mar 30, 2026

Yes Automatic Metrics TruthfulQA Accuracy Not Reported
Stabilizing Rubric Integration Training via Decoupled Advantage Normalization

Mar 27, 2026

Yes Automatic Metrics Olympiadbench Accuracy Not Reported
Do Phone-Use Agents Respect Your Privacy?

Apr 1, 2026

Yes Automatic Metrics APPS , Myphonebench Task success Not Reported
ClimateCheck 2026: Scientific Fact-Checking and Disinformation Narrative Classification of Climate-related Claims

Mar 27, 2026

Yes Automatic Metrics Codabench Recall , Recall@k Not Reported
Stabilizing Iterative Self-Training with Verified Reasoning via Symbolic Recursive Self-Alignment

Mar 23, 2026

Yes Automatic Metrics GSM8K Accuracy Not Reported

Protocol Diff (Top Papers)

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

Signal Personalized RewardBench: Evaluating Reward Models… PubMed Reasoner: Dynamic Reasoning-based Retrieval… TraceSafe: A Systematic Assessment of LLM Guardrail…
Human Feedback Pairwise Preference, Rubric RatingExpert VerificationRed Team
Evaluation Modes Human Eval, Automatic MetricsLlm As Judge, Automatic MetricsAutomatic Metrics
Benchmarks RewardbenchMMLUTracesafe Bench
Metrics Accuracy, HelpfulnessAccuracy, RelevanceAccuracy
Quality Controls Not reportedNot reportedNot reported
Rater Population UnknownDomain ExpertsUnknown
Annotation Unit PairwiseUnknownTrajectory
Suggested Reading Order (Extended)

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

Suggested Reading Order

  1. More Human, More Efficient: Aligning Annotations with Quantized SLMs

    Start here for detailed protocol reporting and quality-control evidence. Signals: automatic metrics + rubric ratings. Focus: agreement. Abstract: As Large Language Model (LLM) capabilities advance, the demand for.

  2. 21c58ea0-b4be-4618-b71f-46a42d18f126

    High citation traction makes this a strong baseline for protocol comparison.

  3. 81330dad-24dc-4f72-82bc-37f6815aff67

    High citation traction makes this a strong baseline for protocol comparison.

  4. 4af9f797-f384-4a38-ba18-f4d4528e5ce5

    High citation traction makes this a strong baseline for protocol comparison.

  5. Improving Clinical Diagnosis with Counterfactual Multi-Agent Reasoning

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: human evaluation + expert verification. Focus: accuracy. Abstract: Human evaluation further indicates that our framework produces more.

  6. Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: human evaluation + pairwise preferences. Focus: Rewardbench / accuracy. Abstract: While benchmarks for general response quality are.

  7. PubMed Reasoner: Dynamic Reasoning-based Retrieval for Evidence-Grounded Biomedical Question Answering

    Include an LLM-as-judge paper to test judge design and agreement assumptions. Signals: LLM-as-judge + expert verification. Focus: MMLU / accuracy. Abstract: Moreover, LLM-as-judge evaluations prefer our responses across:.

  8. Blinded Radiologist and LLM-Based Evaluation of LLM-Generated Japanese Translations of Chest CT Reports: Comparative Study

    Include an LLM-as-judge paper to test judge design and agreement assumptions. Signals: LLM-as-judge + pairwise preferences. Focus: accuracy. Abstract: Objective: To evaluate the educational suitability of LLM-generated Japanese.

Known Limitations

Known Limitations

  • Only 8.4% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (12.7% coverage).
  • Narrative synthesis is grounded in metadata and abstracts only; full-paper implementation details are not parsed.
Research Utility Snapshot (Detailed)

Research Utility Snapshot

Human Feedback Mix

  • Pairwise Preference (25)
  • Expert Verification (15)
  • Rubric Rating (11)
  • Critique Edit (5)

Evaluation Modes

  • Automatic Metrics (394)
  • Human Eval (10)
  • Llm As Judge (10)
  • Simulation Env (8)

Top Benchmarks

  • GSM8K (3)
  • BFCL (2)
  • HotpotQA (2)
  • AlpacaEval (1)

Top Metrics

  • Accuracy (72)
  • Cost (22)
  • Agreement (12)
  • Latency (10)

Rater Population Mix

  • Domain Experts (49)
  • Mixed (1)

Quality Controls

  • Calibration (16)
  • Inter Annotator Agreement Reported (16)
  • Adjudication (3)
  • Gold Questions (2)
Coverage diagnostics (sample-based): human-feedback 80.0% · benchmarks 36.7% · metrics 100.0% · quality controls 16.7%.

Top Papers

Related Hubs

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.