Skip to content
← Back to explorer

HFEPX Archive Slice

HFEPX Weekly Archive: 2025-W43

Updated from current HFEPX corpus (Apr 12, 2026). 61 papers are grouped in this daily page.

Read Full Context

Updated from current HFEPX corpus (Apr 12, 2026). 61 papers are grouped in this daily page. Common evaluation modes: Automatic Metrics, Human Eval. Most common rater population: Domain Experts. Common annotation unit: Freeform. Frequent quality control: Calibration. Frequently cited benchmark: CAPArena. 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 Oct 26, 2025.

Papers: 61 Last published: Oct 26, 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 61 papers).

High-Signal Coverage

100.0%

60 / 60 papers are not low-signal flagged.

Benchmark Anchors

15.0%

Papers with benchmark/dataset mentions in extraction output.

Metric Anchors

38.3%

Papers with reported metric mentions in extraction output.

  • 2 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

  • 14.8% of papers report explicit human-feedback signals, led by pairwise preferences.
  • automatic metrics appears in 34.4% of papers in this hub.
  • CAPArena is a recurring benchmark anchor for cross-paper comparisons in this page.

Protocol Takeaways For This Period

  • 2 sampled papers report both human evaluation and LLM-as-judge, supporting direct agreement checks.
  • Most common quality-control signal is rater calibration (3.3% of papers).
  • Rater context is mostly domain experts, and annotation is commonly Freeform; use this to scope replication staffing.

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

Oct 21, 2025

Human Eval, Llm As Judge CAPArena Spearman Not reported
VisJudge-Bench: Aesthetics and Quality Assessment of Visualizations

Oct 25, 2025

Automatic Metrics Visjudge Bench, Visjudgebench Accuracy, Mae Not reported
RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA

Oct 23, 2025

Automatic Metrics HotpotQA Accuracy, F1 Not reported
LightMem: Lightweight and Efficient Memory-Augmented Generation

Oct 21, 2025

Automatic Metrics Longmemeval Accuracy Not reported
Automated Coding of Communication Data Using ChatGPT: Consistency Across Subgroups

Oct 23, 2025

Human Eval, Automatic Metrics Not reported Accuracy Not reported
Robust Preference Alignment via Directional Neighborhood Consensus

Oct 23, 2025

Automatic Metrics Not reported Helpfulness Not reported
Difficulty-Controllable Multiple-Choice Question Generation Using Large Language Models and Direct Preference Optimization

Oct 22, 2025

Automatic Metrics Not reported Accuracy Not reported
A Multi-faceted Analysis of Cognitive Abilities: Evaluating Prompt Methods with Large Language Models on the CONSORT Checklist

Oct 22, 2025

Automatic Metrics Not reported Calibration error Calibration
Batch Speculative Decoding Done Right

Oct 26, 2025

Not reported Specbench Throughput, Cost Not reported
Towards Scalable Oversight via Partitioned Human Supervision

Oct 26, 2025

Automatic Metrics Not reported Accuracy, Top 1 accuracy Not reported
Researcher Workflow (Detailed)

Checklist

  • Gap: Papers with explicit human feedback

    Coverage is a replication risk (14.8% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (3.3% vs 30% target).

  • Gap: Papers naming benchmarks/datasets

    Coverage is a replication risk (6.6% vs 35% target).

  • Moderate: Papers naming evaluation metrics

    Coverage is usable but incomplete (24.6% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (8.2% vs 35% target).

  • Gap: Papers with known annotation unit

    Coverage is a replication risk (9.8% vs 35% target).

Strengths

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

Known Gaps

  • Only 3.3% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (8.2% coverage).
  • Annotation unit is under-specified (9.8% coverage).

Suggested Next Analyses

  • Compare papers that report both human_eval and llm_as_judge to quantify judge-human agreement drift.
  • Stratify by benchmark (CAPArena vs HotpotQA) before comparing methods.
  • Track metric sensitivity by reporting both accuracy and cost.
  • Add inter-annotator agreement checks when reproducing these protocols.

Recommended Queries

Known Limitations
  • Only 3.3% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (8.2% 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 (21)
  • Human Eval (4)
  • Llm As Judge (4)
  • Simulation Env (2)

Top Metrics

  • Accuracy (7)
  • Cost (3)
  • F1 (2)
  • Latency (2)

Top Benchmarks

  • CAPArena (1)
  • HotpotQA (1)
  • HR Bench (1)
  • Longmemeval (1)

Quality Controls

  • Calibration (2)

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.