Skip to content
← Back to explorer

HFEPX Hub

CS.LG Papers (Last 30 Days)

Updated from current HFEPX corpus (Apr 12, 2026). 632 papers are grouped in this hub page.

Read Full Context

Updated from current HFEPX corpus (Apr 12, 2026). 632 papers are grouped in this hub page. Common evaluation modes: Automatic Metrics, Simulation Env. Most common rater population: Domain Experts. Common annotation unit: Trajectory. 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 Apr 8, 2026.

Papers: 632 Last published: Apr 8, 2026 Global RSS
Cs.LGLast 30d

Researcher Quick Triage

This hub is best used for protocol triage and replication planning from abstract-level evidence. Quality band: High .

Analysis blocks below are computed from the currently loaded sample (60 of 632 total papers in this hub).

High-Signal Coverage

100.0%

60 / 60 sampled papers are not low-signal flagged.

Replication-Ready Set

15

Benchmark + metric + eval mode explicitly present.

Judge/Human Comparability

0

Papers containing both `human_eval` and `llm_as_judge`.

  • 15 papers are replication-ready (benchmark + metric + explicit evaluation mode).
  • 0 papers support judge-vs-human agreement analysis.
  • 2 papers report explicit quality controls (calibration/adjudication/IAA).

Primary action: Start with the top 2 papers in “Start Here”, then validate assumptions in the protocol matrix.

Currently showing only replication-ready papers in ranking and matrix sections (15 papers).

Need evaluators for this research workflow?

Post a Job →

Why This Matters For Eval Research

  • 4.7% of papers report explicit human-feedback signals, led by pairwise preferences.
  • automatic metrics appears in 19% of papers in this hub.
  • DROP is a recurring benchmark anchor for cross-paper comparisons in this page.

Protocol Takeaways

  • Most common quality-control signal is rater calibration (1.7% of papers).
  • Rater context is mostly domain experts, and annotation is commonly trajectory-level annotation; use this to scope replication staffing.
  • Compare papers that report both human_eval and llm_as_judge to quantify judge-human agreement drift.

Benchmark Interpretation

  • DROP appears in 0.6% of hub papers (4/632); use this cohort for benchmark-matched comparisons.
  • MMLU appears in 0.6% of hub papers (4/632); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 12.2% of hub papers (77/632); compare with a secondary metric before ranking methods.
  • cost is reported in 7% of hub papers (44/632); compare with a secondary metric before ranking methods.
Researcher Checklist (Expanded)

Researcher Checklist

  • Gap: Papers with explicit human feedback

    Coverage is a replication risk (4.7% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (2.1% vs 30% target).

  • Gap: Papers naming benchmarks/datasets

    Coverage is a replication risk (6.6% vs 35% target).

  • Moderate: Papers naming evaluation metrics

    Coverage is usable but incomplete (27.2% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (3.8% vs 35% target).

  • Gap: Papers with known annotation unit

    Coverage is a replication risk (7.3% vs 35% target).

Strengths

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

Known Gaps

  • Only 2.1% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (3.8% coverage).
  • Annotation unit is under-specified (7.3% 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 MMLU) before comparing methods.
  • Track metric sensitivity by reporting both accuracy and cost.
Recommended Queries (Expanded)

Recommended Queries

Start with These 3

Use these when you need one protocol anchor, one benchmark anchor, and one recent comparison point before reading the wider hub.

Start Here (Best First 6)

Ranked for protocol completeness (human signal, benchmark + metric anchors, quality controls, and judge/human overlap).

Protocol Matrix (Top 12)

Use this to quickly compare protocol ingredients instead of scanning long prose.

Paper HF Signal Eval Modes Benchmarks Metrics QC
Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization

Apr 8, 2026

Yes Human Eval , Automatic Metrics Rewardbench Accuracy , Helpfulness Not Reported
TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories

Apr 8, 2026

Yes Automatic Metrics Tracesafe Bench Accuracy Not Reported
Paper Reconstruction Evaluation: Evaluating Presentation and Hallucination in AI-written Papers

Apr 1, 2026

Yes Automatic Metrics Paperwrite Bench Cost Not Reported
FairMed-XGB: A Bayesian-Optimised Multi-Metric Framework with Explainability for Demographic Equity in Critical Healthcare Data

Mar 16, 2026

Yes Automatic Metrics DROP Accuracy , Auroc Not Reported
Modeling and Benchmarking Spoken Dialogue Rewards with Modality and Colloquialness

Mar 16, 2026

Yes Automatic Metrics Esdr Bench Accuracy Not Reported
Do Phone-Use Agents Respect Your Privacy?

Apr 1, 2026

Yes Automatic Metrics APPS , Myphonebench Task success Not Reported
DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment

Mar 23, 2026

Yes Automatic Metrics MT Bench , AlpacaEval Accuracy Not Reported
CausalRM: Causal-Theoretic Reward Modeling for RLHF from Observational User Feedbacks

Mar 19, 2026

Yes Automatic Metrics Harmbench Cost Not Reported
Entropy trajectory shape predicts LLM reasoning reliability: A diagnostic study of uncertainty dynamics in chain-of-thought

Mar 19, 2026

No
Not Reported
Automatic Metrics GSM8K Accuracy , Calibration error Calibration
ReDAct: Uncertainty-Aware Deferral for LLM Agents

Apr 8, 2026

No
Not Reported
Simulation Env ALFWorld Cost , Token cost Not Reported
LUDOBENCH: Evaluating LLM Behavioural Decision-Making Through Spot-Based Board Game Scenarios in Ludo

Apr 7, 2026

No
Not Reported
Simulation Env Ludobench Dice Not Reported
S0 Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models

Apr 1, 2026

No
Not Reported
Automatic Metrics MATH 500 , GSM8K Pass@1 , Cost Not Reported

Protocol Diff (Top Papers)

Fast side-by-side comparison for the highest-ranked papers in this hub.

Signal Personalized RewardBench: Evaluating Reward Models… TraceSafe: A Systematic Assessment of LLM Guardrail… Paper Reconstruction Evaluation: Evaluating Present…
Human Feedback Pairwise Preference, Rubric RatingRed TeamRubric Rating
Evaluation Modes Human Eval, Automatic MetricsAutomatic MetricsAutomatic Metrics
Benchmarks RewardbenchTracesafe BenchPaperwrite Bench
Metrics Accuracy, HelpfulnessAccuracyCost
Quality Controls Not reportedNot reportedNot reported
Rater Population UnknownUnknownUnknown
Annotation Unit PairwiseTrajectoryMulti Dim Rubric
Suggested Reading Order (Extended)

This section is intentionally expanded only when needed; use “Start Here” above for a faster pass.

Suggested Reading Order

  1. 5927ed59-8617-4149-ba2f-3333487e639a

    Start here for detailed protocol reporting and quality-control evidence.

  2. 7fcb077d-1be0-48ff-b520-29cb03330422

    Start here for detailed protocol reporting and quality-control evidence.

  3. e9250a0d-77c6-4937-9bde-62fba067e8ac

    Start here for detailed protocol reporting and quality-control evidence.

  4. Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: human evaluation + pairwise preferences. Focus: Rewardbench / accuracy. Abstract: While benchmarks for general response quality are.

  5. Meanings and Measurements: Multi-Agent Probabilistic Grounding for Vision-Language Navigation

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: simulation environments + demonstration data. Focus: Mapg-Bench. Abstract: Robots collaborating with humans must convert natural language goals.

  6. RuleForge: Automated Generation and Validation for Web Vulnerability Detection at Scale

    Include an LLM-as-judge paper to test judge design and agreement assumptions. Signals: LLM-as-judge + expert verification. Focus: auroc. Abstract: This paper focuses on RuleForge's architecture and operational deployment.

  7. Text-to-Stage: Spatial Layouts from Long-form Narratives

    Include an LLM-as-judge paper to test judge design and agreement assumptions. Signals: LLM-as-judge + pairwise preferences. Abstract: Experiments on a text-only corpus of classical English literature demonstrate improvements.

  8. TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories

    Adds automatic metrics with red-team protocols for broader protocol coverage within this hub. Signals: automatic metrics + red-team protocols. Focus: Tracesafe-Bench / accuracy. Abstract: As large language models.

Known Limitations

Known Limitations

  • Only 2.1% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (3.8% coverage).
  • Narrative synthesis is grounded in metadata and abstracts only; full-paper implementation details are not parsed.
Research Utility Snapshot (Detailed)

Research Utility Snapshot

Human Feedback Mix

  • Pairwise Preference (15)
  • Expert Verification (6)
  • Red Team (4)
  • Rubric Rating (4)

Evaluation Modes

  • Automatic Metrics (120)
  • Simulation Env (11)
  • Llm As Judge (5)
  • Human Eval (1)

Top Benchmarks

  • DROP (4)
  • MMLU (4)
  • GSM8K (3)
  • AIME (2)

Top Metrics

  • Accuracy (77)
  • Cost (44)
  • F1 (14)
  • Precision (14)

Rater Population Mix

  • Domain Experts (24)

Quality Controls

  • Calibration (11)
  • Gold Questions (1)
  • Inter Annotator Agreement Reported (1)
Coverage diagnostics (sample-based): human-feedback 50.0% · benchmarks 30.0% · metrics 50.0% · quality controls 3.3%.

Top Papers

Related Hubs

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.