Skip to content
← Back to explorer

HFEPX Archive Slice

HFEPX Fortnight Archive: 2025-F26

Updated from current HFEPX corpus (Apr 12, 2026). 69 papers are grouped in this daily page.

Read Full Context

Updated from current HFEPX corpus (Apr 12, 2026). 69 papers are grouped in this daily page. Common evaluation modes: Automatic Metrics, Llm As Judge. Most common rater population: Domain Experts. Common annotation unit: Ranking. 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 Dec 28, 2025.

Papers: 69 Last published: Dec 28, 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 69 papers).

High-Signal Coverage

100.0%

60 / 60 papers are not low-signal flagged.

Benchmark Anchors

10.0%

Papers with benchmark/dataset mentions in extraction output.

Metric Anchors

30.0%

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

  • 7.2% of papers report explicit human-feedback signals, led by expert verification.
  • automatic metrics appears in 29% 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 (1.4% of papers).
  • Rater context is mostly domain experts, and annotation is commonly ranking 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
CricBench: A Multilingual Benchmark for Evaluating LLMs in Cricket Analytics

Dec 26, 2025

Automatic Metrics DROP, BIRD Accuracy Gold Questions
Towards Efficient Agents: A Co-Design of Inference Architecture and System

Dec 20, 2025

Automatic Metrics BrowseComp Accuracy, Latency Not reported
Generative Adversarial Reasoner: Enhancing LLM Reasoning with Adversarial Reinforcement Learning

Dec 18, 2025

Automatic Metrics Not reported Exact match Not reported
Refusal Steering: Fine-grained Control over LLM Refusal Behaviour for Sensitive Topics

Dec 18, 2025

Llm As Judge Jailbreakbench Not reported Not reported
Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills

Dec 18, 2025

Automatic Metrics Not reported Cost Not reported
Diversity or Precision? A Deep Dive into Next Token Prediction

Dec 28, 2025

Automatic Metrics Not reported Precision Not reported
Beg to Differ: Understanding Reasoning-Answer Misalignment Across Languages

Dec 27, 2025

Automatic Metrics Not reported Accuracy Not reported
Hallucination Detection and Evaluation of Large Language Model

Dec 27, 2025

Automatic Metrics Not reported Accuracy Not reported
Large Language Models Approach Expert Pedagogical Quality in Math Tutoring but Differ in Instructional and Linguistic Profiles

Dec 23, 2025

Automatic Metrics Not reported Accuracy Not reported
DIAL: Direct Iterative Adversarial Learning for Realistic Multi-Turn Dialogue Simulation

Dec 23, 2025

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

Checklist

  • Gap: Papers with explicit human feedback

    Coverage is a replication risk (7.2% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (2.9% vs 30% target).

  • Gap: Papers naming benchmarks/datasets

    Coverage is a replication risk (8.7% vs 35% target).

  • Moderate: Papers naming evaluation metrics

    Coverage is usable but incomplete (21.7% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (7.2% vs 35% target).

  • Gap: Papers with known annotation unit

    Coverage is a replication risk (7.2% vs 35% target).

Strengths

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

Known Gaps

  • Only 2.9% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (7.2% coverage).
  • Annotation unit is under-specified (7.2% 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 BIRD) 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 2.9% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (7.2% 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 (20)
  • Llm As Judge (2)
  • Human Eval (1)
  • Simulation Env (1)

Top Metrics

  • Accuracy (11)
  • Cost (6)
  • Precision (2)
  • Bertscore (1)

Top Benchmarks

  • DROP (2)
  • BIRD (1)
  • BrowseComp (1)
  • Cricbench (1)

Quality Controls

  • Calibration (1)
  • Gold Questions (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.