Skip to content
← Back to explorer

HFEPX Hub

General + Red Team (Last 90 Days)

Updated from current HFEPX corpus (Apr 19, 2026). 25 papers are grouped in this hub page.

Read Full Context

Updated from current HFEPX corpus (Apr 19, 2026). 25 papers are grouped in this hub page. Common evaluation modes: Automatic Metrics, Llm As Judge. Most common rater population: Domain Experts. Common annotation unit: Multi Dim Rubric. Frequently cited benchmark: Reliablebench. 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: 25 Last published: Apr 8, 2026 Global RSS Tag RSS
GeneralRed TeamLast 90d

Researcher Quick Triage

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

High-Signal Coverage

100.0%

25 / 25 sampled papers are not low-signal flagged.

Replication-Ready Set

2

Benchmark + metric + eval mode explicitly present.

Judge/Human Comparability

0

Papers containing both `human_eval` and `llm_as_judge`.

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

Primary action: Use this page for scouting only; collect additional papers before attempting replication-critical comparisons.

Need evaluators for this research workflow?

Post a Job →

Why This Matters For Eval Research

  • 100% of papers report explicit human-feedback signals, led by red-team protocols.
  • automatic metrics appears in 40% of papers in this hub.
  • Reliablebench is a recurring benchmark anchor for cross-paper comparisons in this page.

Protocol Takeaways

  • Quality-control reporting is sparse in this slice; prioritize papers with explicit calibration or adjudication steps.
  • Rater context is mostly domain experts, and annotation is commonly multi-dimensional rubrics; use this to scope replication staffing.
  • Pair this hub with a human_eval-heavy hub to validate judge-model calibration.

Benchmark Interpretation

  • Reliablebench appears in 4% of hub papers (1/25); use this cohort for benchmark-matched comparisons.
  • Semeval appears in 4% of hub papers (1/25); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 12% of hub papers (3/25); compare with a secondary metric before ranking methods.
  • helpfulness is reported in 8% of hub papers (2/25); compare with a secondary metric before ranking methods.
Researcher Checklist (Expanded)

Researcher Checklist

  • Strong: Papers with explicit human feedback

    Coverage is strong (100% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (0% vs 30% target).

  • Gap: Papers naming benchmarks/datasets

    Coverage is a replication risk (12% vs 35% target).

  • Strong: Papers naming evaluation metrics

    Coverage is strong (48% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (12% vs 35% target).

  • Gap: Papers with known annotation unit

    Coverage is a replication risk (8% vs 35% target).

Strengths

  • Strong human-feedback signal (100% of papers).

Known Gaps

  • Only 0% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (12% coverage).
  • Annotation unit is under-specified (8% coverage).

Suggested Next Analyses

  • Pair this hub with a human_eval-heavy hub to validate judge-model calibration.
  • Stratify by benchmark (Reliablebench vs Semeval) before comparing methods.
  • Track metric sensitivity by reporting both accuracy and helpfulness.
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
TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories

Apr 8, 2026

Yes Automatic Metrics Tracesafe Bench Accuracy Not Reported
SemEval-2026 Task 6: CLARITY -- Unmasking Political Question Evasions

Mar 14, 2026

Yes Automatic Metrics Semeval F1 , F1 macro Not Reported
A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness

Feb 4, 2026

Yes Llm As Judge Reliablebench Not Reported Not Reported
Prompt Attack Detection with LLM-as-a-Judge and Mixture-of-Models

Mar 26, 2026

Yes Llm As Judge Not Reported Not Reported Not Reported
Red-Teaming Vision-Language-Action Models via Quality Diversity Prompt Generation for Robust Robot Policies

Mar 12, 2026

Yes Simulation Env Not Reported Task success Not Reported
WebWeaver: Breaking Topology Confidentiality in LLM Multi-Agent Systems with Stealthy Context-Based Inference

Mar 11, 2026

Yes Automatic Metrics Not Reported Accuracy Not Reported
MUSE: A Run-Centric Platform for Multimodal Unified Safety Evaluation of Large Language Models

Mar 3, 2026

Yes Automatic Metrics Not Reported Success rate , Jailbreak success rate Not Reported
Exposing Long-Tail Safety Failures in Large Language Models through Efficient Diverse Response Sampling

Mar 15, 2026

Yes Automatic Metrics Not Reported Not Reported Not Reported
IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs

Mar 11, 2026

Yes Automatic Metrics Not Reported Helpfulness Not Reported
Can Safety Emerge from Weak Supervision? A Systematic Analysis of Small Language Models

Mar 7, 2026

Yes Automatic Metrics Not Reported Helpfulness Not Reported
MANATEE: Inference-Time Lightweight Diffusion Based Safety Defense for LLMs

Feb 21, 2026

Yes Automatic Metrics Not Reported Success rate , Jailbreak success rate Not Reported
FENCE: A Financial and Multimodal Jailbreak Detection Dataset

Feb 20, 2026

Yes Automatic Metrics Not Reported Accuracy Not Reported

Protocol Diff (Top Papers)

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

Signal TraceSafe: A Systematic Assessment of LLM Guardrail… SemEval-2026 Task 6: CLARITY -- Unmasking Political… A Coin Flip for Safety: LLM Judges Fail to Reliably…
Human Feedback Red TeamRed TeamRed Team
Evaluation Modes Automatic MetricsAutomatic MetricsLlm As Judge
Benchmarks Tracesafe BenchSemevalReliablebench
Metrics AccuracyF1, F1 macroNot reported
Quality Controls Not reportedNot reportedNot reported
Rater Population UnknownDomain ExpertsUnknown
Annotation Unit TrajectoryUnknownUnknown
Suggested Reading Order (Extended)

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

Suggested Reading Order

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

    Start here for detailed protocol reporting and quality-control evidence. Signals: automatic metrics + red-team protocols. Focus: Tracesafe-Bench / accuracy. Abstract: As large language models (LLMs) evolve from static.

  2. Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning

    Start here for detailed protocol reporting and quality-control evidence. Signals: red-team protocols. Abstract: Fine-tuning APIs offered by major AI providers create new attack surfaces where adversaries can bypass.

  3. Prompt Attack Detection with LLM-as-a-Judge and Mixture-of-Models

    Start here for detailed protocol reporting and quality-control evidence. Signals: LLM-as-judge + red-team protocols. Focus: latency. Abstract: In production, guardrails must mitigate these attacks under strict low-latency constraints,.

  4. A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: LLM-as-judge + red-team protocols. Focus: Reliablebench. Abstract: Automated \enquote{LLM-as-a-Judge} frameworks have become the de facto standard for.

  5. SemEval-2026 Task 6: CLARITY -- Unmasking Political Question Evasions

    Adds automatic metrics with red-team protocols for broader protocol coverage within this hub. Signals: automatic metrics + red-team protocols. Focus: Semeval / f1. Abstract: Political speakers often avoid.

  6. Red-Teaming Vision-Language-Action Models via Quality Diversity Prompt Generation for Robust Robot Policies

    Adds simulation environments with red-team protocols for broader protocol coverage within this hub. Signals: simulation environments + red-team protocols. Focus: task success. Abstract: Furthermore, results from a user.

  7. WebWeaver: Breaking Topology Confidentiality in LLM Multi-Agent Systems with Stealthy Context-Based Inference

    Adds automatic metrics with red-team protocols for broader protocol coverage within this hub. Signals: automatic metrics + red-team protocols. Focus: accuracy. Abstract: Communication topology is a critical factor.

  8. MUSE: A Run-Centric Platform for Multimodal Unified Safety Evaluation of Large Language Models

    Adds automatic metrics with red-team protocols for broader protocol coverage within this hub. Signals: automatic metrics + red-team protocols. Focus: success rate. Abstract: We present MUSE (Multimodal Unified.

Known Limitations

Known Limitations

  • Only 0% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (12% 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

  • Red Team (25)
  • Pairwise Preference (2)
  • Rubric Rating (1)

Evaluation Modes

  • Automatic Metrics (10)
  • Llm As Judge (2)
  • Simulation Env (1)

Top Benchmarks

  • Reliablebench (1)
  • Semeval (1)
  • Tracesafe Bench (1)

Top Metrics

  • Accuracy (3)
  • Helpfulness (2)
  • Jailbreak success rate (2)
  • Success rate (2)

Rater Population Mix

  • Domain Experts (3)

Quality Controls

Coverage diagnostics (sample-based): human-feedback 100.0% · benchmarks 12.0% · metrics 44.0% · quality controls 0.0%.

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.