Skip to content
← Back to explorer

HFEPX Archive Slice

HFEPX Weekly Archive: 2025-W35

Updated from current HFEPX corpus (Apr 17, 2026). 21 papers are grouped in this daily page.

Read Full Context

Updated from current HFEPX corpus (Apr 17, 2026). 21 papers are grouped in this daily page. Common evaluation modes: Automatic Metrics, Llm As Judge. Most common rater population: Domain Experts. Frequent quality control: Calibration. Frequently cited benchmark: BrowseComp. 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 Aug 31, 2025.

Papers: 21 Last published: Aug 31, 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 .

High-Signal Coverage

100.0%

21 / 21 papers are not low-signal flagged.

Benchmark Anchors

23.8%

Papers with benchmark/dataset mentions in extraction output.

Metric Anchors

57.1%

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 as early signal only; benchmark/metric anchoring is limited for rigorous period-over-period claims.

Get this digest every Friday →

Subscribe

Why This Time Slice Matters

  • 9.5% of papers report explicit human-feedback signals, led by demonstration data.
  • automatic metrics appears in 61.9% of papers in this hub.
  • BrowseComp 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 (4.8% of papers).
  • Rater context is mostly domain experts, and annotation is commonly mixed annotation units; use this to scope replication staffing.
  • Pair this hub with a human_eval-heavy hub to validate judge-model calibration.

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
Dyslexify: A Mechanistic Defense Against Typographic Attacks in CLIP

Aug 28, 2025

Automatic Metrics DROP Accuracy Not reported
AgentCoMa: A Compositional Benchmark Mixing Commonsense and Mathematical Reasoning in Real-World Scenarios

Aug 27, 2025

Automatic Metrics MATH Accuracy Not reported
Diffusion Language Models Know the Answer Before Decoding

Aug 27, 2025

Automatic Metrics MMLU, GSM8K Cost Not reported
Hybrid Deep Searcher: Scalable Parallel and Sequential Search Reasoning

Aug 26, 2025

Automatic Metrics Reasoning Query0retrieval F1 Not reported
Agri-Query: A Case Study on RAG vs. Long-Context LLMs for Cross-Lingual Technical Question Answering

Aug 25, 2025

Llm As Judge, Automatic Metrics Needle In A Haystack Accuracy Not reported
LaTeXTrans: Structured LaTeX Translation with Multi-Agent Coordination

Aug 26, 2025

Automatic Metrics Not reported Accuracy Not reported
L-MARS: Legal Multi-Agent Workflow with Orchestrated Reasoning and Agentic Search

Aug 31, 2025

Automatic Metrics Not reported Accuracy Not reported
On the Theoretical Limitations of Embedding-Based Retrieval

Aug 28, 2025

Automatic Metrics Not reported Relevance Not reported
AVIATOR: Towards AI-Agentic Vulnerability Injection Workflow for High-Fidelity, Large-Scale Code Security Dataset

Aug 28, 2025

Automatic Metrics Not reported Accuracy, F1 Not reported
From Guidelines to Guarantees: A Graph-Based Evaluation Harness for Domain-Specific Evaluation of LLMs

Aug 28, 2025

Automatic Metrics Not reported Accuracy Not reported
Researcher Workflow (Detailed)

Checklist

  • Gap: Papers with explicit human feedback

    Coverage is a replication risk (9.5% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (4.8% vs 30% target).

  • Gap: Papers naming benchmarks/datasets

    Coverage is a replication risk (19% vs 35% target).

  • Moderate: Papers naming evaluation metrics

    Coverage is usable but incomplete (33.3% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (14.3% vs 35% target).

  • Gap: Papers with known annotation unit

    Coverage is a replication risk (0% vs 35% target).

Strengths

  • This hub still surfaces a concentrated paper set for protocol triage and replication planning.

Known Gaps

  • Only 4.8% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (14.3% coverage).
  • Annotation unit is under-specified (0% coverage).

Suggested Next Analyses

  • Pair this hub with a human_eval-heavy hub to validate judge-model calibration.
  • Stratify by benchmark (BrowseComp vs DROP) before comparing methods.
  • Track metric sensitivity by reporting both accuracy and calibration error.
  • Add inter-annotator agreement checks when reproducing these protocols.

Recommended Queries

Known Limitations
  • Only 4.8% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (14.3% 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 (13)
  • Llm As Judge (1)
  • Simulation Env (1)

Top Metrics

  • Accuracy (5)
  • Calibration error (1)
  • Cost (1)
  • F1 (1)

Top Benchmarks

  • BrowseComp (1)
  • DROP (1)
  • MMLU (1)
  • Needle In A Haystack (1)

Quality Controls

  • Calibration (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.