Skip to content
← Back to explorer

HFEPX Hub

Automatic Metrics + Law Papers

Updated from current HFEPX corpus (Feb 27, 2026). 39 papers are grouped in this hub page. Common evaluation modes: Automatic Metrics, Human Eval. Most common rater population: Domain Experts. Common annotation unit: Pairwise. Frequent quality control: Adjudication. Frequently cited benchmark: MATH. 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 Feb 26, 2026.

Papers: 39 Last published: Feb 26, 2026 Global RSS Tag RSS
Automatic MetricsLaw

Research Narrative

Grounded narrative Model: deterministic-grounded Source: persisted

Updated from current HFEPX corpus (Feb 27, 2026). This page tracks 39 papers for Automatic Metrics + Law Papers. Dominant protocol signals include automatic metrics, human evaluation, simulation environments, with frequent benchmark focus on MATH, Retrieval and metric focus on accuracy, cost. Use the grounded sections below to prioritize reproducible protocol choices, benchmark-matched comparisons, and judge-vs-human evaluation checks.

Why This Matters For Eval Research

Protocol Takeaways

Benchmark Interpretation

  • MATH appears in 5.1% of hub papers (2/39); use this cohort for benchmark-matched comparisons.
  • Retrieval appears in 5.1% of hub papers (2/39); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 20.5% of hub papers (8/39); compare with a secondary metric before ranking methods.
  • cost is reported in 10.3% of hub papers (4/39); compare with a secondary metric before ranking methods.

Researcher Checklist

  • Close gap on Papers with explicit human feedback. Coverage is a replication risk (12.8% vs 45% target).
  • Close gap on Papers reporting quality controls. Coverage is a replication risk (5.1% vs 30% target).
  • Close gap on Papers naming benchmarks/datasets. Coverage is a replication risk (20.5% vs 35% target).
  • Maintain strength on Papers naming evaluation metrics. Coverage is strong (48.7% vs 35% target).
  • Close gap on Papers with known rater population. Coverage is a replication risk (17.9% vs 35% target).
  • Close gap on Papers with known annotation unit. Coverage is a replication risk (2.6% vs 35% target).

Papers with explicit human feedback

Coverage is a replication risk (12.8% vs 45% target).

Papers reporting quality controls

Coverage is a replication risk (5.1% vs 30% target).

Papers naming benchmarks/datasets

Coverage is a replication risk (20.5% vs 35% target).

Papers naming evaluation metrics

Coverage is strong (48.7% vs 35% target).

Papers with known rater population

Coverage is a replication risk (17.9% vs 35% target).

Papers with known annotation unit

Coverage is a replication risk (2.6% vs 35% target).

Suggested Reading Order

  1. 1. Frequency-Ordered Tokenization for Better Text Compression

    Start here for detailed protocol reporting, including rater and quality-control evidence.

  2. 2. Towards Faithful Industrial RAG: A Reinforced Co-adaptation Framework for Advertising QA

    Start here for detailed protocol reporting, including rater and quality-control evidence.

  3. 3. MrBERT: Modern Multilingual Encoders via Vocabulary, Domain, and Dimensional Adaptation

    Start here for detailed protocol reporting, including rater and quality-control evidence.

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

    Include a human-eval paper to anchor calibration against automated judge settings.

  5. 5. Scaling View Synthesis Transformers

    Adds automatic metrics for broader coverage within this hub.

  6. 6. Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient Reasoning

    Adds automatic metrics for broader coverage within this hub.

  7. 7. See and Fix the Flaws: Enabling VLMs and Diffusion Models to Comprehend Visual Artifacts via Agentic Data Synthesis

    Adds automatic metrics for broader coverage within this hub.

  8. 8. Airavat: An Agentic Framework for Internet Measurement

    Adds automatic metrics for broader coverage within this hub.

Known Limitations

  • Only 5.1% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (17.9% coverage).
  • Narrative synthesis is grounded in metadata and abstracts only; full-paper implementation details are not parsed.

Research Utility Links

human_eval vs automatic_metrics

both=1, left_only=0, right_only=38

1 papers use both Human Eval and Automatic Metrics.

automatic_metrics vs simulation_env

both=1, left_only=38, right_only=0

1 papers use both Automatic Metrics and Simulation Env.

human_eval vs simulation_env

both=0, left_only=1, right_only=1

0 papers use both Human Eval and Simulation Env.

Benchmark Brief

MATH

Coverage: 2 papers (5.1%)

2 papers (5.1%) mention MATH.

Examples: Prescriptive Scaling Reveals the Evolution of Language Model Capabilities , Orthogonalized Policy Optimization:Policy Optimization as Orthogonal Projection in Hilbert Space

Benchmark Brief

Retrieval

Coverage: 2 papers (5.1%)

2 papers (5.1%) mention Retrieval.

Examples: Towards Faithful Industrial RAG: A Reinforced Co-adaptation Framework for Advertising QA , Quecto-V1: Empirical Analysis of 8-bit Quantized Small Language Models for On-Device Legal Retrieval

Benchmark Brief

AdvBench

Coverage: 1 papers (2.6%)

1 papers (2.6%) mention AdvBench.

Examples: A Simple and Efficient Jailbreak Method Exploiting LLMs' Helpfulness

Metric Brief

accuracy

Coverage: 8 papers (20.5%)

8 papers (20.5%) mention accuracy.

Examples: Towards Faithful Industrial RAG: A Reinforced Co-adaptation Framework for Advertising QA , Agentic Adversarial QA for Improving Domain-Specific LLMs , Quecto-V1: Empirical Analysis of 8-bit Quantized Small Language Models for On-Device Legal Retrieval

Metric Brief

cost

Coverage: 4 papers (10.3%)

4 papers (10.3%) mention cost.

Examples: ReIn: Conversational Error Recovery with Reasoning Inception , Group Representational Position Encoding , From Raw Corpora to Domain Benchmarks: Automated Evaluation of LLM Domain Expertise

Metric Brief

f1

Coverage: 2 papers (5.1%)

2 papers (5.1%) mention f1.

Examples: Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient Reasoning , Vichara: Appellate Judgment Prediction and Explanation for the Indian Judicial System

Most Cited In This Hub

Fast path to methods with the strongest citation traction in this scope.

Papers: Frequency-Ordered Tokenization for Better Text Compression , Towards Faithful Industrial RAG: A Reinforced Co-adaptation Framework for Advertising QA , MrBERT: Modern Multilingual Encoders via Vocabulary, Domain, and Dimensional Adaptation

Most Recent

Fast path to latest protocol changes and newly published evaluation setups.

Papers: Frequency-Ordered Tokenization for Better Text Compression , Towards Faithful Industrial RAG: A Reinforced Co-adaptation Framework for Advertising QA , MrBERT: Modern Multilingual Encoders via Vocabulary, Domain, and Dimensional Adaptation

Best Protocol Detail

Papers with explicit rater/unit metadata and quality-control signals for reproducibility.

Papers: Frequency-Ordered Tokenization for Better Text Compression , Towards Faithful Industrial RAG: A Reinforced Co-adaptation Framework for Advertising QA , MrBERT: Modern Multilingual Encoders via Vocabulary, Domain, and Dimensional Adaptation

Top Papers

Related Hubs