Skip to content
← Back to explorer

HFEPX Hub

CS.AI + Human Eval Papers

Updated from current HFEPX corpus (Apr 12, 2026). 46 papers are grouped in this hub page.

Read Full Context

Updated from current HFEPX corpus (Apr 12, 2026). 46 papers are grouped in this hub page. Common evaluation modes: Human Eval, Automatic Metrics. Most common rater population: Domain Experts. Common annotation unit: Multi Dim Rubric. Frequent quality control: Inter Annotator Agreement Reported. Frequently cited benchmark: AIME. 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 22, 2026.

Papers: 46 Last published: Mar 22, 2026 Global RSS Tag RSS
Cs.AIHuman Eval

Researcher Quick Triage

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

High-Signal Coverage

100.0%

46 / 46 sampled papers are not low-signal flagged.

Replication-Ready Set

3

Benchmark + metric + eval mode explicitly present.

Judge/Human Comparability

6

Papers containing both `human_eval` and `llm_as_judge`.

  • 3 papers are replication-ready (benchmark + metric + explicit evaluation mode).
  • 6 papers support judge-vs-human agreement analysis.
  • 5 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.

Need evaluators for this research workflow?

Post a Job →

Why This Matters For Eval Research

  • 60.7% of papers report explicit human-feedback signals, led by pairwise preferences.
  • human evaluation appears in 60.9% of papers in this hub.
  • AIME is a recurring benchmark anchor for cross-paper comparisons in this page.

Protocol Takeaways

  • 3 sampled papers report both human evaluation and LLM-as-judge, supporting direct agreement checks.
  • Most common quality-control signal is inter-annotator agreement reporting (8.7% of papers).
  • Rater context is mostly domain experts, and annotation is commonly multi-dimensional rubrics; use this to scope replication staffing.

Benchmark Interpretation

  • AIME appears in 3.6% of hub papers (1/46); use this cohort for benchmark-matched comparisons.
  • Biggenbench appears in 3.6% of hub papers (1/46); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • agreement is reported in 25% of hub papers (7/46); compare with a secondary metric before ranking methods.
  • accuracy is reported in 14.3% of hub papers (4/46); compare with a secondary metric before ranking methods.
Researcher Checklist (Expanded)

Researcher Checklist

  • Strong: Papers with explicit human feedback

    Coverage is strong (60.7% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (17.9% vs 30% target).

  • Strong: Papers naming benchmarks/datasets

    Coverage is strong (35.7% vs 35% target).

  • Strong: Papers naming evaluation metrics

    Coverage is strong (64.3% vs 35% target).

  • Moderate: Papers with known rater population

    Coverage is usable but incomplete (32.1% vs 35% target).

  • Moderate: Papers with known annotation unit

    Coverage is usable but incomplete (32.1% vs 35% target).

Strengths

  • Strong human-feedback signal (60.7% of papers).
  • Most papers provide measurable evaluation context (35.7% benchmarks, 64.3% metrics).
  • Contains both human-eval and LLM-as-judge protocols for head-to-head methodology comparison.

Known Gaps

  • Only 17.9% 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 (AIME vs Biggenbench) before comparing methods.
  • Track metric sensitivity by reporting both agreement and accuracy.
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
AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling

Mar 22, 2026

Yes Human Eval , Llm As Judge WebArena , ToolBench Precision , Pass@1 Not Reported
PoSh: Using Scene Graphs To Guide LLMs-as-a-Judge For Detailed Image Descriptions

Oct 21, 2025

Yes Human Eval , Llm As Judge CAPArena Spearman Not Reported
Is this Idea Novel? An Automated Benchmark for Judgment of Research Ideas

Mar 11, 2026

Yes Human Eval Rinobench Not Reported Gold Questions
LLM Essay Scoring Under Holistic and Analytic Rubrics: Prompt Effects and Bias

Mar 31, 2026

Yes Human Eval Not Reported Kappa , Agreement Inter Annotator Agreement Reported , Adjudication
LMUnit: Fine-grained Evaluation with Natural Language Unit Tests

Dec 17, 2024

Yes Human Eval Biggenbench , Rewardbench Agreement Inter Annotator Agreement Reported
Validating Political Position Predictions of Arguments

Feb 20, 2026

Yes Human Eval Not Reported Agreement Gold Questions , Inter Annotator Agreement Reported
HEART: A Unified Benchmark for Assessing Humans and LLMs in Emotional Support Dialogue

Jan 9, 2026

Yes Human Eval , Llm As Judge Not Reported Agreement Not Reported
A Decade-Scale Benchmark Evaluating LLMs' Clinical Practice Guidelines Detection and Adherence in Multi-turn Conversations

Mar 26, 2026

Yes Human Eval Cpgbench Not Reported Not Reported
IntelliAsk: Learning to Ask High-Quality Research Questions via RLVR

Jan 23, 2026

Yes Human Eval Writingbench Not Reported Not Reported
Think$^{2}$: Grounded Metacognitive Reasoning in Large Language Models

Feb 21, 2026

Yes Human Eval GSM8K , AIME Not Reported Not Reported
RebuttalAgent: Strategic Persuasion in Academic Rebuttal via Theory of Mind

Jan 22, 2026

Yes Human Eval Rebuttalbench Not Reported Not Reported
Evaluating Austrian A-Level German Essays with Large Language Models for Automated Essay Scoring

Mar 6, 2026

Yes Human Eval Not Reported Agreement Not Reported

Protocol Diff (Top Papers)

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

Signal AgentHER: Hindsight Experience Replay for LLM Agent… PoSh: Using Scene Graphs To Guide LLMs-as-a-Judge F… Is this Idea Novel? An Automated Benchmark for Judg…
Human Feedback DemonstrationsRubric RatingRubric Rating
Evaluation Modes Human Eval, Llm As JudgeHuman Eval, Llm As JudgeHuman Eval
Benchmarks WebArena, ToolBenchCAPArenaRinobench
Metrics Precision, Pass@1SpearmanNot reported
Quality Controls Not reportedNot reportedGold Questions
Rater Population UnknownDomain ExpertsDomain Experts
Annotation Unit TrajectoryMulti 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. Is this Idea Novel? An Automated Benchmark for Judgment of Research Ideas

    Start here for detailed protocol reporting and quality-control evidence. Signals: human evaluation + rubric ratings. Focus: Rinobench. Abstract: Yet, evaluation of these approaches remains largely inconsistent and is.

  2. Strengthening Human-Centric Chain-of-Thought Reasoning Integrity in LLMs via a Structured Prompt Framework

    High citation traction makes this a strong baseline for protocol comparison. Signals: human evaluation. Focus: accuracy. Abstract: However, its reliability in security-sensitive analytical tasks remains insufficiently examined, particularly.

  3. LLM Essay Scoring Under Holistic and Analytic Rubrics: Prompt Effects and Bias

    High citation traction makes this a strong baseline for protocol comparison. Signals: human evaluation + rubric ratings. Focus: kappa. Abstract: In particular, we observe large and stable negative.

  4. Voxtral TTS

    High citation traction makes this a strong baseline for protocol comparison. Signals: human evaluation. Focus: win rate. Abstract: In human evaluations conducted by native speakers, Voxtral TTS is.

  5. AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: human evaluation + demonstration data. Focus: WebArena / precision. Abstract: AgentHER realises this idea through a four-stage.

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

    Include an LLM-as-judge paper to test judge design and agreement assumptions. Signals: human evaluation + rubric ratings. Focus: CAPArena / spearman. Abstract: In this work, we introduce PoSh,.

  7. LMUnit: Fine-grained Evaluation with Natural Language Unit Tests

    Adds human evaluation with pairwise preferences for broader protocol coverage within this hub. Signals: human evaluation + pairwise preferences. Focus: Biggenbench / agreement. Abstract: As language models become.

  8. Validating Political Position Predictions of Arguments

    Adds human evaluation with pairwise preferences for broader protocol coverage within this hub. Signals: human evaluation + pairwise preferences. Focus: agreement. Abstract: Real-world knowledge representation often requires capturing.

Known Limitations

Known Limitations

  • Only 17.9% 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

  • Pairwise Preference (10)
  • Rubric Rating (6)
  • Critique Edit (2)
  • Expert Verification (2)

Evaluation Modes

  • Human Eval (28)
  • Automatic Metrics (7)
  • Llm As Judge (6)
  • Simulation Env (2)

Top Benchmarks

  • AIME (1)
  • Biggenbench (1)
  • CAPArena (1)
  • Correctbench (1)

Top Metrics

  • Agreement (7)
  • Accuracy (4)
  • Cost (2)
  • F1 (2)

Rater Population Mix

  • Domain Experts (8)
  • Mixed (1)

Quality Controls

  • Inter Annotator Agreement Reported (4)
  • Gold Questions (2)
  • Adjudication (1)
Coverage diagnostics (sample-based): human-feedback 37.0% · benchmarks 26.1% · metrics 54.3% · quality controls 10.9%.

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.