Skip to content
← Back to explorer

HFEPX Hub

CS.AI Papers (Last 30 Days)

Updated from current HFEPX corpus (Apr 27, 2026). 961 papers are grouped in this hub page.

Read Full Context

Updated from current HFEPX corpus (Apr 27, 2026). 961 papers are grouped in this hub page. Common evaluation modes: Automatic Metrics, Simulation Env. Most common rater population: Domain Experts. Common annotation unit: Trajectory. Frequent quality control: Calibration. Frequently cited benchmark: DROP. 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 31, 2026.

Papers: 961 Last published: Mar 31, 2026 Global RSS
Cs.AILast 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 961 total papers in this hub).

High-Signal Coverage

100.0%

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

Replication-Ready Set

16

Benchmark + metric + eval mode explicitly present.

Judge/Human Comparability

0

Papers containing both `human_eval` and `llm_as_judge`.

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

  • 5.2% of papers report explicit human-feedback signals, led by pairwise preferences.
  • automatic metrics appears in 16.2% of papers in this hub.
  • DROP is a recurring benchmark anchor for cross-paper comparisons in this page.

Protocol Takeaways

  • Most common quality-control signal is rater calibration (1.2% of papers).
  • Rater context is mostly domain experts, and annotation is commonly trajectory-level 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

  • DROP appears in 1.2% of hub papers (12/961); use this cohort for benchmark-matched comparisons.
  • MMLU appears in 0.9% of hub papers (9/961); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 14.7% of hub papers (141/961); compare with a secondary metric before ranking methods.
  • cost is reported in 6.3% of hub papers (61/961); compare with a secondary metric before ranking methods.
Researcher Checklist (Expanded)

Researcher Checklist

  • Gap: Papers with explicit human feedback

    Coverage is a replication risk (5.2% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (1.8% vs 30% target).

  • Gap: Papers naming benchmarks/datasets

    Coverage is a replication risk (11.1% vs 35% target).

  • Moderate: Papers naming evaluation metrics

    Coverage is usable but incomplete (33% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (4% vs 35% target).

  • Gap: Papers with known annotation unit

    Coverage is a replication risk (7% vs 35% target).

Strengths

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

Known Gaps

  • Only 1.8% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (4% coverage).
  • Annotation unit is under-specified (7% coverage).

Suggested Next Analyses

  • Compare papers that report both human_eval and llm_as_judge to quantify judge-human agreement drift.
  • Stratify by benchmark (DROP vs MMLU) 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
TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories

Apr 8, 2026

Yes Automatic Metrics Tracesafe Bench Accuracy 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
Do Phone-Use Agents Respect Your Privacy?

Apr 1, 2026

Yes Automatic Metrics APPS , Myphonebench Task success Not Reported
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
A Multi-Stage Validation Framework for Trustworthy Large-scale Clinical Information Extraction using Large Language Models

Apr 7, 2026

Yes Automatic Metrics Not Reported F1 , Agreement Calibration , Adjudication
Self-Preference Bias in Rubric-Based Evaluation of Large Language Models

Apr 8, 2026

Yes Llm As Judge IFEval , Healthbench Not Reported Not Reported
MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome

Mar 30, 2026

Yes Not Reported Miroeval Not Reported Not Reported
Blinded Radiologist and LLM-Based Evaluation of LLM-Generated Japanese Translations of Chest CT Reports: Comparative Study

Apr 2, 2026

Yes Llm As Judge , Automatic Metrics Not Reported Accuracy Not Reported
HyperMem: Hypergraph Memory for Long-Term Conversations

Apr 9, 2026

Yes Llm As Judge , Automatic Metrics Not Reported Accuracy , Coherence Not Reported
RuleForge: Automated Generation and Validation for Web Vulnerability Detection at Scale

Apr 2, 2026

Yes Llm As Judge , Automatic Metrics Not Reported Auroc Not Reported
Signals: Trajectory Sampling and Triage for Agentic Interactions

Apr 1, 2026

Yes Automatic Metrics Not Reported Not Reported Not Reported
LUDOBENCH: Evaluating LLM Behavioural Decision-Making Through Spot-Based Board Game Scenarios in Ludo

Apr 7, 2026

No
Not Reported
Simulation Env Ludobench Dice Not Reported

Protocol Diff (Top Papers)

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

Signal TraceSafe: A Systematic Assessment of LLM Guardrail… Paper Reconstruction Evaluation: Evaluating Present… Do Phone-Use Agents Respect Your Privacy?
Human Feedback Red TeamRubric RatingPairwise Preference
Evaluation Modes Automatic MetricsAutomatic MetricsAutomatic Metrics
Benchmarks Tracesafe BenchPaperwrite BenchAPPS, Myphonebench
Metrics AccuracyNot reportedTask success
Quality Controls Not reportedNot reportedNot reported
Rater Population UnknownUnknownUnknown
Annotation Unit TrajectoryMulti Dim RubricUnknown
Suggested Reading Order (Extended)

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

Suggested Reading Order

  1. Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond

    Start here for detailed protocol reporting and quality-control evidence. Signals: simulation environments. Abstract: As AI systems move from generating text to accomplishing goals through sustained interaction, the ability.

  2. daf19bd3-58e4-4d1f-9200-6fb6dfa2b503

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

  3. 70f5eac0-0472-4963-be2b-dfbf6f9c11c6

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

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

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: human evaluation + rubric ratings. Focus: kappa. Abstract: In particular, we observe large and stable negative directional.

  5. TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: automatic metrics + red-team protocols. Focus: Tracesafe-Bench / accuracy. Abstract: As large language models (LLMs) evolve from.

  6. 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.

  7. Self-Preference Bias in Rubric-Based Evaluation of Large Language Models

    Include an LLM-as-judge paper to test judge design and agreement assumptions. Signals: LLM-as-judge + pairwise preferences. Focus: IFEval. Abstract: LLM-as-a-judge has become the de facto approach for evaluating.

  8. HyperMem: Hypergraph Memory for Long-Term Conversations

    Adds LLM-as-judge with pairwise preferences for broader protocol coverage within this hub. Signals: LLM-as-judge + pairwise preferences. Focus: accuracy. Abstract: However, existing approaches as Retrieval-Augmented Generation (RAG) and.

Known Limitations

Known Limitations

  • Only 1.8% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (4% 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 (23)
  • Expert Verification (9)
  • Rubric Rating (7)
  • Demonstrations (6)

Evaluation Modes

  • Automatic Metrics (156)
  • Simulation Env (17)
  • Llm As Judge (14)
  • Human Eval (5)

Top Benchmarks

  • DROP (12)
  • MMLU (9)
  • GSM8K (6)
  • GPQA (4)

Top Metrics

  • Accuracy (141)
  • Cost (61)
  • F1 (31)
  • Agreement (25)

Rater Population Mix

  • Domain Experts (36)
  • Mixed (2)

Quality Controls

  • Calibration (12)
  • Inter Annotator Agreement Reported (4)
  • Adjudication (2)
  • Gold Questions (2)
Coverage diagnostics (sample-based): human-feedback 46.7% · benchmarks 30.0% · metrics 80.0% · quality controls 10.0%.

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.