Skip to content
← Back to explorer

HFEPX Archive Slice

HFEPX Daily Archive: 2026-02-15

Updated from current HFEPX corpus (Apr 12, 2026). 42 papers are grouped in this daily page.

Read Full Context

Updated from current HFEPX corpus (Apr 12, 2026). 42 papers are grouped in this daily page. Common evaluation modes: Automatic Metrics, Llm As Judge. Most common rater population: Domain Experts. Common annotation unit: Trajectory. Frequent quality control: Adjudication. Frequently cited benchmark: Ad-Bench. 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 15, 2026.

Papers: 42 Last published: Feb 15, 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%

42 / 42 papers are not low-signal flagged.

Benchmark Anchors

21.4%

Papers with benchmark/dataset mentions in extraction output.

Metric Anchors

47.6%

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

  • 19% of papers report explicit human-feedback signals, led by pairwise preferences.
  • automatic metrics appears in 45.2% of papers in this hub.
  • Ad-Bench is a recurring benchmark anchor for cross-paper comparisons in this page.

Protocol Takeaways For This Period

  • Most common quality-control signal is adjudication (2.4% of papers).
  • Rater context is mostly domain experts, and annotation is commonly trajectory-level annotation; 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
HLE-Verified: A Systematic Verification and Structured Revision of Humanity's Last Exam

Feb 15, 2026

Automatic Metrics HLE Accuracy Adjudication
AD-Bench: A Real-World, Trajectory-Aware Advertising Analytics Benchmark for LLM Agents

Feb 15, 2026

Simulation Env Ad Bench Pass@1, Pass@3 Not reported
MAGE: All-[MASK] Block Already Knows Where to Look in Diffusion LLM

Feb 15, 2026

Automatic Metrics LongBench, Needle In A Haystack Accuracy, Cost Not reported
The Sufficiency-Conciseness Trade-off in LLM Self-Explanation from an Information Bottleneck Perspective

Feb 15, 2026

Automatic Metrics ARC Challenge Accuracy, Conciseness Not reported
Neuromem: A Granular Decomposition of the Streaming Lifecycle in External Memory for LLMs

Feb 15, 2026

Automatic Metrics Insertion And Retrieval, Longmemeval Accuracy, F1 Not reported
LM-Lexicon: Improving Definition Modeling via Harmonizing Semantic Experts

Feb 15, 2026

Automatic Metrics Not reported Bleu Not reported
We can still parse using syntactic rules

Feb 15, 2026

Automatic Metrics Not reported Accuracy Not reported
REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents

Feb 15, 2026

Automatic Metrics Not reported Recall, Cost Not reported
Reasoning Language Models for complex assessments tasks: Evaluating parental cooperation from child protection case reports

Feb 15, 2026

Automatic Metrics Not reported Accuracy Not reported
Knowing When Not to Answer: Abstention-Aware Scientific Reasoning

Feb 15, 2026

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

Checklist

  • Gap: Papers with explicit human feedback

    Coverage is a replication risk (19% 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 (9.5% vs 35% target).

  • Gap: Papers naming evaluation metrics

    Coverage is a replication risk (16.7% vs 35% target).

  • Gap: Papers with known rater population

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

  • Moderate: Papers with known annotation unit

    Coverage is usable but incomplete (23.8% 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 (23.8% coverage).

Suggested Next Analyses

  • Pair this hub with a human_eval-heavy hub to validate judge-model calibration.
  • Stratify by benchmark (Ad-Bench vs ARC-Challenge) before comparing methods.
  • Track metric sensitivity by reporting both accuracy and bleu.
  • 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 (19)
  • Llm As Judge (2)
  • Simulation Env (2)

Top Metrics

  • Accuracy (4)
  • Bleu (2)
  • Conciseness (1)
  • Cost (1)

Top Benchmarks

  • Ad Bench (1)
  • ARC Challenge (1)
  • HLE (1)
  • OSWorld (1)

Quality Controls

  • Adjudication (1)
  • Calibration (1)

Papers In This Archive Slice

Recent Archive Slices

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