Skip to content
← Back to explorer

HFEPX Archive Slice

HFEPX Quarterly Archive: 2025-Q2

Updated from current HFEPX corpus (Apr 12, 2026). 322 papers are grouped in this daily page.

Read Full Context

Updated from current HFEPX corpus (Apr 12, 2026). 322 papers are grouped in this daily 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 Jun 30, 2025.

Papers: 322 Last published: Jun 30, 2025 Global RSS

Researcher Quick Triage

Use this archive page for time-slice monitoring (what changed in evaluation methods, metrics, and protocol quality this period). Quality band: High .

Analysis blocks are computed from the loaded sample (60 of 322 papers).

High-Signal Coverage

100.0%

60 / 60 papers are not low-signal flagged.

Benchmark Anchors

16.7%

Papers with benchmark/dataset mentions in extraction output.

Metric Anchors

33.3%

Papers with reported metric mentions in extraction output.

  • 1 papers report explicit quality controls for this archive period.
  • Prioritize papers with both benchmark and metric anchors for reliable longitudinal comparisons.

Primary action: Use this slice for trend comparison: review top papers first, then validate shifts in the protocol matrix.

Get this digest every Friday →

Subscribe

Why This Time Slice Matters

  • 15.5% of papers report explicit human-feedback signals, led by pairwise preferences.
  • automatic metrics appears in 27.3% of papers in this hub.
  • DROP is a recurring benchmark anchor for cross-paper comparisons in this page.

Protocol Takeaways For This Period

  • Most common quality-control signal is rater calibration (1.9% 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.

Start Here (Highest-Signal Papers In This Slice)

Ranked by protocol completeness and evidence density for faster period-over-period review.

Protocol Matrix (Top 10)

Quickly compare method ingredients across this archive slice.

Paper Eval Modes Benchmarks Metrics Quality Controls
An Agentic System for Rare Disease Diagnosis with Traceable Reasoning

Jun 25, 2025

Automatic Metrics Not reported Recall, Agreement Adjudication
LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning

Jun 23, 2025

Automatic Metrics LMSYS Chatbot Arena, Writingbench Coherence Not reported
PersonalAI: A Systematic Comparison of Knowledge Graph Storage and Retrieval Approaches for Personalized LLM agents

Jun 20, 2025

Automatic Metrics HotpotQA, TriviaQA Accuracy Not reported
SPARE: Single-Pass Annotation with Reference-Guided Evaluation for Automatic Process Supervision and Reward Modelling

Jun 18, 2025

Automatic Metrics GSM8K, Processbench Accuracy, Precision Not reported
AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents

Jun 17, 2025

Automatic Metrics DROP Cost Not reported
$\texttt{SPECS}$: Faster Test-Time Scaling through Speculative Drafts

Jun 15, 2025

Automatic Metrics MATH 500, Olympiadbench Accuracy, Latency Not reported
Accelerating Diffusion Large Language Models with SlowFast Sampling: The Three Golden Principles

Jun 12, 2025

Automatic Metrics DROP Accuracy, Latency Not reported
DistillNote: Toward a Functional Evaluation Framework of LLM-Generated Clinical Note Summaries

Jun 20, 2025

Llm As Judge, Automatic Metrics Not reported Auroc Not reported
Unveiling Decision-Making in LLMs for Text Classification : Extraction of influential and interpretable concepts with Sparse Autoencoders

Jun 30, 2025

Automatic Metrics Not reported Precision Not reported
MindCube: Spatial Mental Modeling from Limited Views

Jun 26, 2025

Automatic Metrics, Simulation Env Not reported Accuracy Not reported
Researcher Workflow (Detailed)

Checklist

  • Gap: Papers with explicit human feedback

    Coverage is a replication risk (15.5% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (2.8% vs 30% target).

  • Gap: Papers naming benchmarks/datasets

    Coverage is a replication risk (6.2% vs 35% target).

  • Gap: Papers naming evaluation metrics

    Coverage is a replication risk (18% vs 35% target).

  • Gap: Papers with known rater population

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

  • Gap: Papers with known annotation unit

    Coverage is a replication risk (6.8% vs 35% target).

Strengths

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

Known Gaps

  • Only 2.8% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (8.4% coverage).
  • Annotation unit is under-specified (6.8% coverage).

Suggested Next Analyses

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

Recommended Queries

Known Limitations
  • Only 2.8% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (8.4% coverage).
  • Narrative synthesis is grounded in metadata and abstracts only; full-paper implementation details are not parsed.
Research Utility Snapshot (Detailed)

Evaluation Modes

  • Automatic Metrics (88)
  • Simulation Env (12)
  • Human Eval (4)
  • Llm As Judge (4)

Top Metrics

  • Accuracy (28)
  • Cost (12)
  • Recall (7)
  • Jailbreak success rate (5)

Top Benchmarks

  • DROP (2)
  • AdvBench (1)
  • AIME (1)
  • ALFWorld (1)

Quality Controls

  • Calibration (6)
  • Adjudication (2)
  • Inter Annotator Agreement Reported (1)

Papers In This Archive Slice

Recent Archive Slices

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.