Skip to content
← Back to explorer

HFEPX Archive Slice

HFEPX Daily Archive: 2026-02-20

Updated from current HFEPX corpus (Apr 12, 2026). 38 papers are grouped in this daily page.

Read Full Context

Updated from current HFEPX corpus (Apr 12, 2026). 38 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: Gold Questions. 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 Feb 20, 2026.

Papers: 38 Last published: Feb 20, 2026 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%

38 / 38 papers are not low-signal flagged.

Benchmark Anchors

15.8%

Papers with benchmark/dataset mentions in extraction output.

Metric Anchors

57.9%

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

  • 13.2% of papers report explicit human-feedback signals, led by pairwise preferences.
  • automatic metrics appears in 52.6% of papers in this hub.
  • long-horizon tasks appears in 2.6% of papers, indicating agentic evaluation demand.

Protocol Takeaways For This Period

  • Most common quality-control signal is gold-question checks (2.6% 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
Validating Political Position Predictions of Arguments

Feb 20, 2026

Human Eval Not reported Agreement Gold Questions, Inter Annotator Agreement Reported
SPQ: An Ensemble Technique for Large Language Model Compression

Feb 20, 2026

Automatic Metrics GSM8K, TruthfulQA Accuracy, Perplexity Not reported
Agentic Adversarial QA for Improving Domain-Specific LLMs

Feb 20, 2026

Automatic Metrics Legalbench Accuracy, Recall Not reported
Decomposing Retrieval Failures in RAG for Long-Document Financial Question Answering

Feb 20, 2026

Automatic Metrics Financebench Recall, Coherence Not reported
FENCE: A Financial and Multimodal Jailbreak Detection Dataset

Feb 20, 2026

Automatic Metrics Not reported Accuracy Not reported
Gradient Regularization Prevents Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards

Feb 20, 2026

Llm As Judge, Automatic Metrics Not reported Accuracy, Win rate Not reported
CUICurate: A GraphRAG-based Framework for Automated Clinical Concept Curation for NLP applications

Feb 20, 2026

Automatic Metrics Not reported Precision, Recall Not reported
PolyFrame at MWE-2026 AdMIRe 2: When Words Are Not Enough: Multimodal Idiom Disambiguation

Feb 20, 2026

Automatic Metrics Not reported Ndcg Not reported
Luna-2: Scalable Single-Token Evaluation with Small Language Models

Feb 20, 2026

Llm As Judge, Automatic Metrics Not reported Accuracy, Latency Not reported
VIRAASAT: Traversing Novel Paths for Indian Cultural Reasoning

Feb 20, 2026

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

Checklist

  • Gap: Papers with explicit human feedback

    Coverage is a replication risk (13.2% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (2.6% vs 30% target).

  • Gap: Papers naming benchmarks/datasets

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

  • Gap: Papers naming evaluation metrics

    Coverage is a replication risk (18.4% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (13.2% vs 35% target).

  • Gap: Papers with known annotation unit

    Coverage is a replication risk (10.5% vs 35% target).

Strengths

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

Known Gaps

  • Only 2.6% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (13.2% coverage).
  • Annotation unit is under-specified (10.5% coverage).

Suggested Next Analyses

  • Compare papers that report both human_eval and llm_as_judge to quantify judge-human agreement drift.
  • Track metric sensitivity by reporting both accuracy and agreement.

Recommended Queries

Known Limitations
  • Only 2.6% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (13.2% 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)
  • Human Eval (2)
  • Llm As Judge (2)
  • Simulation Env (2)

Top Metrics

  • Accuracy (4)
  • Agreement (2)
  • F1 (2)
  • Precision (2)

Top Benchmarks

Quality Controls

  • Gold Questions (1)
  • Inter Annotator Agreement Reported (1)

Papers In This Archive Slice

Recent Archive Slices

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