Skip to content
← Back to explorer

HFEPX Archive Slice

HFEPX Daily Archive: 2026-02-02

Updated from current HFEPX corpus (Apr 12, 2026). 26 papers are grouped in this daily page.

Read Full Context

Updated from current HFEPX corpus (Apr 12, 2026). 26 papers are grouped in this daily page. Common evaluation modes: Automatic Metrics, Simulation Env. Most common rater population: Domain Experts. Common annotation unit: Trajectory. Frequent quality control: Adjudication. Frequently cited benchmark: HellaSwag. Common metric signal: relevance. 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 2, 2026.

Papers: 26 Last published: Feb 2, 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%

26 / 26 papers are not low-signal flagged.

Benchmark Anchors

7.7%

Papers with benchmark/dataset mentions in extraction output.

Metric Anchors

34.6%

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

  • 7.7% of papers report explicit human-feedback signals, led by demonstration data.
  • automatic metrics appears in 34.6% of papers in this hub.
  • HellaSwag is a recurring benchmark anchor for cross-paper comparisons in this page.

Protocol Takeaways For This Period

  • Most common quality-control signal is adjudication (3.8% of papers).
  • Rater context is mostly domain experts, and annotation is commonly trajectory-level annotation; use this to scope replication staffing.
  • Stratify by benchmark (HellaSwag vs Vdr-Bench) before comparing methods.

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
Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Models

Feb 2, 2026

Automatic Metrics Vdr Bench Not reported Adjudication
COMI: Coarse-to-fine Context Compression via Marginal Information Gain

Feb 2, 2026

Automatic Metrics NQ, HotpotQA Exact match, Relevance Not reported
WAXAL: A Large-Scale Multilingual African Language Speech Corpus

Feb 2, 2026

Automatic Metrics Not reported Jailbreak success rate Not reported
From Sycophancy to Sensemaking: Premise Governance for Human-AI Decision Making

Feb 2, 2026

Automatic Metrics Not reported Cost Not reported
Proof-RM: A Scalable and Generalizable Reward Model for Math Proof

Feb 2, 2026

Automatic Metrics Not reported Accuracy Not reported
CryoLVM: Self-supervised Learning from Cryo-EM Density Maps with Large Vision Models

Feb 2, 2026

Automatic Metrics Not reported Throughput Not reported
AXE: Low-Cost Cross-Domain Web Structured Information Extraction

Feb 2, 2026

Automatic Metrics Not reported F1, Cost Not reported
Mechanistic Indicators of Steering Effectiveness in Large Language Models

Feb 2, 2026

Automatic Metrics Not reported Agreement Not reported
Restoring Exploration after Post-Training: Latent Exploration Decoding for Large Reasoning Models

Feb 2, 2026

Automatic Metrics Not reported Accuracy, Pass@1 Not reported
Out of the Memory Barrier: A Highly Memory Efficient Training System for LLMs with Million-Token Contexts

Feb 2, 2026

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

Checklist

  • Gap: Papers with explicit human feedback

    Coverage is a replication risk (7.7% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (3.8% vs 30% target).

  • Gap: Papers naming benchmarks/datasets

    Coverage is a replication risk (7.7% vs 35% target).

  • Gap: Papers naming evaluation metrics

    Coverage is a replication risk (19.2% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (7.7% vs 35% target).

  • Gap: Papers with known annotation unit

    Coverage is a replication risk (7.7% vs 35% target).

Strengths

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

Known Gaps

  • Only 3.8% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (7.7% coverage).
  • Annotation unit is under-specified (7.7% coverage).

Suggested Next Analyses

  • Stratify by benchmark (HellaSwag vs Vdr-Bench) before comparing methods.
  • Track metric sensitivity by reporting both relevance and accuracy.
  • Add inter-annotator agreement checks when reproducing these protocols.

Recommended Queries

Known Limitations
  • Only 3.8% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (7.7% 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 (9)
  • Simulation Env (1)

Top Metrics

  • Relevance (2)
  • Accuracy (1)
  • Agreement (1)
  • Latency (1)

Top Benchmarks

  • HellaSwag (1)
  • Vdr Bench (1)

Quality Controls

  • Adjudication (1)

Papers In This Archive Slice

Recent Archive Slices

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