Skip to content
← Back to explorer

HFEPX Hub

Automatic Metrics + Law (Last 120 Days)

Updated from current HFEPX corpus (Mar 10, 2026). 10 papers are grouped in this hub page.

Read Full Context

Updated from current HFEPX corpus (Mar 10, 2026). 10 papers are grouped in this hub page. Common evaluation modes: Automatic Metrics, Human Eval. Most common rater population: Domain Experts. Common annotation unit: Multi Dim Rubric. Frequent quality control: Adjudication. Frequently cited benchmark: HLE. 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 Mar 9, 2026.

Papers: 10 Last published: Mar 9, 2026 Global RSS Tag RSS
Automatic MetricsLawLast 120d

Researcher Quick Triage

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

All Sampled Papers (10) Replication-Ready Only (2)

High-Signal Coverage

100.0%

10 / 10 sampled papers are not low-signal flagged.

Replication-Ready Set

2

Benchmark + metric + eval mode explicitly present.

Judge/Human Comparability

0

Papers containing both `human_eval` and `llm_as_judge`.

  • 2 papers are replication-ready (benchmark + metric + explicit evaluation mode).
  • 0 papers support judge-vs-human agreement analysis.
  • 1 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).

Need evaluators for this research workflow?

Post a Job →

Why This Matters For Eval Research

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

Protocol Takeaways

  • Most common quality-control signal is adjudication (10% of papers).
  • Rater context is mostly domain experts, and annotation is commonly multi-dimensional rubrics; use this to scope replication staffing.
  • Pair this hub with llm_as_judge pages to benchmark automated-vs-human evaluation tradeoffs.

Benchmark Interpretation

  • HLE appears in 10% of hub papers (1/10); use this cohort for benchmark-matched comparisons.
  • MATH appears in 10% of hub papers (1/10); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 40% of hub papers (4/10); compare with a secondary metric before ranking methods.
  • coherence is reported in 10% of hub papers (1/10); compare with a secondary metric before ranking methods.
Researcher Checklist (Expanded)

Researcher Checklist

  • Moderate: Papers with explicit human feedback

    Coverage is usable but incomplete (40% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (10% vs 30% target).

  • Moderate: Papers naming benchmarks/datasets

    Coverage is usable but incomplete (30% vs 35% target).

  • Strong: Papers naming evaluation metrics

    Coverage is strong (90% vs 35% target).

  • Strong: Papers with known rater population

    Coverage is strong (40% vs 35% target).

  • Moderate: Papers with known annotation unit

    Coverage is usable but incomplete (30% vs 35% target).

Strengths

  • Agentic evaluation appears in 80% of papers.

Known Gaps

  • Only 10% of papers report quality controls; prioritize calibration/adjudication evidence.

Suggested Next Analyses

  • Pair this hub with llm_as_judge pages to benchmark automated-vs-human evaluation tradeoffs.
  • Stratify by benchmark (HLE vs MATH) before comparing methods.
  • Track metric sensitivity by reporting both accuracy and coherence.
  • Add inter-annotator agreement checks when reproducing these protocols.
Recommended Queries (Expanded)

Recommended Queries

Human Eval Protocols Benchmark Slice: HLE Metric Slice: accuracy 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
HLE-Verified: A Systematic Verification and Structured Revision of Humanity's Last Exam

Feb 15, 2026

 Yes
Expert Verification , Critique Edit
Automatic Metrics HLE Accuracy Adjudication
\$OneMillion-Bench: How Far are Language Agents from Human Experts?

Mar 9, 2026

 Yes
Rubric Rating
Automatic Metrics Onemillion Bench Accuracy , Coherence Not Reported

Protocol Diff (Top Papers)

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

Signal HLE-Verified: A Systematic Verification and Structu… \$OneMillion-Bench: How Far are Language Agents fro…
Human Feedback Expert Verification, Critique EditRubric Rating
Evaluation Modes Automatic MetricsAutomatic Metrics
Benchmarks HLEOnemillion Bench
Metrics AccuracyAccuracy, Coherence
Quality Controls AdjudicationNot reported
Rater Population Domain ExpertsDomain Experts
Annotation Unit UnknownMulti 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. \$OneMillion-Bench: How Far are Language Agents from Human Experts?

    Start here for detailed protocol reporting and quality-control evidence. Signals: automatic metrics + rubric ratings. Focus: Onemillion-Bench / accuracy. Abstract: We adopt a rubric-based evaluation protocol scoring factual.

  2. MAWARITH: A Dataset and Benchmark for Legal Inheritance Reasoning with LLMs

    Start here for detailed protocol reporting and quality-control evidence. Signals: automatic metrics. Focus: accuracy. Abstract: Islamic inheritance law ('ilm al-mawarith) is challenging for large language models because solving.

  3. TableMind++: An Uncertainty-Aware Programmatic Agent for Tool-Augmented Table Reasoning

    Start here for detailed protocol reporting and quality-control evidence. Signals: automatic metrics. Focus: precision. Abstract: Table reasoning requires models to jointly perform semantic understanding and precise numerical operations.

  4. Vichara: Appellate Judgment Prediction and Explanation for the Indian Judicial System

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: human evaluation. Focus: f1. Abstract: Human evaluation of the generated explanations across Clarity, Linking, and Usefulness metrics.

  5. HLE-Verified: A Systematic Verification and Structured Revision of Humanity's Last Exam

    Include an LLM-as-judge paper to test judge design and agreement assumptions. Signals: automatic metrics + expert verification. Focus: HLE / accuracy. Abstract: Overall, HLE-Verified improves HLE-style evaluations by.

  6. 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.

  7. Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills

    Adds automatic metrics with pairwise preferences for broader protocol coverage within this hub. Signals: automatic metrics + pairwise preferences. Focus: cost. Abstract: On the agent side, A1 (tool-execution-signaled).

  8. Orthogonalized Policy Optimization:Policy Optimization as Orthogonal Projection in Hilbert Space

    Adds automatic metrics for broader protocol coverage within this hub. Signals: automatic metrics. Focus: MATH. Abstract: We propose Orthogonalized Policy Optimization (OPO), a principled framework for large language.

Known Limitations

Known Limitations

  • Only 10% 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

  • Expert Verification (2)
  • Rubric Rating (2)
  • Critique Edit (1)
  • Pairwise Preference (1)

Evaluation Modes

  • Automatic Metrics (10)
  • Human Eval (1)

Top Benchmarks

  • HLE (1)
  • MATH (1)
  • Onemillion Bench (1)

Top Metrics

  • Accuracy (4)
  • Coherence (1)
  • Cost (1)
  • Error rate (1)

Rater Population Mix

  • Domain Experts (4)

Quality Controls

  • Adjudication (1)
Coverage diagnostics (sample-based): human-feedback 40.0% · benchmarks 30.0% · metrics 90.0% · quality controls 10.0%.

Top Papers

  • \$OneMillion-Bench: How Far are Language Agents from Human Experts?

    Qianyu Yang, Yang Liu, Jiaqi Li, Jun Bai, Hao Chen · Mar 9, 2026 · Citations: 0

    Rubric Rating Automatic Metrics Tool Use

    To this end, we introduce \OneMillion-Bench \OneMillion-Bench, a benchmark of 400 expert-curated tasks spanning Law, Finance, Industry, Healthcare, and Natural Science, built to evaluate agents across economically consequential scenarios.

  • HLE-Verified: A Systematic Verification and Structured Revision of Humanity's Last Exam

    Weiqi Zhai, Zhihai Wang, Jinghang Wang, Boyu Yang, Xiaogang Li · Feb 15, 2026 · Citations: 0

    Expert VerificationCritique Edit Automatic Metrics

    Humanity's Last Exam (HLE) has become a widely used benchmark for evaluating frontier large language models on challenging, multi-domain questions.

Related Hubs

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

Post a Job Get a Quote