Skip to content
← Back to explorer

HFEPX Archive Slice

HFEPX Weekly Archive: 2025-W15

Updated from current HFEPX corpus (Apr 12, 2026). 20 papers are grouped in this daily page.

Read Full Context

Updated from current HFEPX corpus (Apr 12, 2026). 20 papers are grouped in this daily page. Common evaluation modes: Automatic Metrics, Human Eval. Most common rater population: Domain Experts. Common annotation unit: Ranking. Frequent quality control: Calibration. Frequently cited benchmark: MCPToolBench. 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 Apr 13, 2025.

Papers: 20 Last published: Apr 13, 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%

20 / 20 papers are not low-signal flagged.

Benchmark Anchors

5.0%

Papers with benchmark/dataset mentions in extraction output.

Metric Anchors

35.0%

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

  • 10% of papers report explicit human-feedback signals, led by critique/edit feedback.
  • automatic metrics appears in 30% of papers in this hub.
  • MCPToolBench 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 (5% of papers).
  • Rater context is mostly domain experts, and annotation is commonly ranking annotation; use this to scope replication staffing.
  • Pair this hub with llm_as_judge pages to benchmark automated-vs-human evaluation tradeoffs.

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
SkillFlow: Scalable and Efficient Agent Skill Retrieval System

Apr 8, 2025

Automatic Metrics Skillsbench, Terminal Bench Precision, Recall Not reported
Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models

Apr 7, 2025

Automatic Metrics Not reported Coherence Not reported
Adaptive Insurance Reserving with CVaR-Constrained Reinforcement Learning under Macroeconomic Regimes

Apr 13, 2025

Simulation Env Not reported Not reported Calibration
BioChemInsight: An Online Platform for Automated Extraction of Chemical Structures and Activity Data from Patents

Apr 12, 2025

Automatic Metrics Not reported Accuracy Not reported
Estimating Item Difficulty Using Large Language Models and Tree-Based Machine Learning Algorithms

Apr 9, 2025

Automatic Metrics Not reported Accuracy Not reported
Don't Let It Hallucinate: Premise Verification via Retrieval-Augmented Logical Reasoning

Apr 8, 2025

Automatic Metrics Not reported Accuracy Not reported
Causal Retrieval with Semantic Consideration

Apr 7, 2025

Automatic Metrics Not reported Accuracy Not reported
Generating Fine Details of Entity Interactions

Apr 11, 2025

Human Eval Not reported Not reported Not reported
Pretraining Language Models for Diachronic Linguistic Change Discovery

Apr 7, 2025

Not reported Not reported Precision Not reported
AgentA/B: Automated and Scalable Web A/BTesting with Interactive LLM Agents

Apr 13, 2025

Not reported Not reported Not reported Not reported
Researcher Workflow (Detailed)

Checklist

  • Gap: Papers with explicit human feedback

    Coverage is a replication risk (10% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (5% vs 30% target).

  • Gap: Papers naming benchmarks/datasets

    Coverage is a replication risk (5% vs 35% target).

  • Gap: Papers naming evaluation metrics

    Coverage is a replication risk (20% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (5% vs 35% target).

  • Gap: Papers with known annotation unit

    Coverage is a replication risk (5% vs 35% target).

Strengths

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

Known Gaps

  • Only 5% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (5% coverage).
  • Annotation unit is under-specified (5% coverage).

Suggested Next Analyses

  • Pair this hub with llm_as_judge pages to benchmark automated-vs-human evaluation tradeoffs.
  • Track metric sensitivity by reporting both accuracy and coherence.
  • Add inter-annotator agreement checks when reproducing these protocols.

Recommended Queries

Known Limitations
  • Only 5% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (5% 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 (6)
  • Human Eval (1)
  • Simulation Env (1)

Top Metrics

  • Accuracy (1)
  • Coherence (1)
  • F1 (1)
  • Recall (1)

Top Benchmarks

  • MCPToolBench (1)

Quality Controls

  • Calibration (1)

Papers In This Archive Slice

Recent Archive Slices

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.