Skip to content
← Back to explorer

HFEPX Hub

Demonstrations Or Rlaif Or Synthetic Feedback Papers

Updated from current HFEPX corpus (Apr 12, 2026). 76 papers are grouped in this hub page.

Read Full Context

Updated from current HFEPX corpus (Apr 12, 2026). 76 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: HotpotQA. Common metric signal: cost. 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 Mar 22, 2026.

Papers: 76 Last published: Mar 22, 2026 Global RSS Tag RSS
DemonstrationsRlaif Or Synthetic Feedback

Researcher Quick Triage

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

Analysis blocks below are computed from the currently loaded sample (60 of 76 total papers in this hub).

High-Signal Coverage

100.0%

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

Replication-Ready Set

1

Benchmark + metric + eval mode explicitly present.

Judge/Human Comparability

1

Papers containing both `human_eval` and `llm_as_judge`.

  • 1 papers are replication-ready (benchmark + metric + explicit evaluation mode).
  • 1 papers support judge-vs-human agreement analysis.
  • 2 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 demonstration data.
  • automatic metrics appears in 18.4% of papers in this hub.
  • HotpotQA is a recurring benchmark anchor for cross-paper comparisons in this page.

Protocol Takeaways

  • 1 sampled papers report both human evaluation and LLM-as-judge, supporting direct agreement checks.
  • Most common quality-control signal is rater calibration (1.3% of papers).
  • Rater context is mostly domain experts, and annotation is commonly trajectory-level annotation; use this to scope replication staffing.

Benchmark Interpretation

  • HotpotQA appears in 2.6% of hub papers (2/76); use this cohort for benchmark-matched comparisons.
  • Windowsagentarena appears in 2.6% of hub papers (2/76); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • cost is reported in 6.6% of hub papers (5/76); compare with a secondary metric before ranking methods.
  • accuracy is reported in 5.3% of hub papers (4/76); 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 (2.6% vs 30% target).

  • Gap: Papers naming benchmarks/datasets

    Coverage is a replication risk (14.5% vs 35% target).

  • Moderate: Papers naming evaluation metrics

    Coverage is usable but incomplete (21.1% vs 35% target).

  • Moderate: Papers with known rater population

    Coverage is usable but incomplete (21.1% vs 35% target).

  • Gap: Papers with known annotation unit

    Coverage is a replication risk (19.7% vs 35% target).

Strengths

  • Strong human-feedback signal (100% of papers).
  • 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 (21.1% coverage).
  • Annotation unit is under-specified (19.7% coverage).

Suggested Next Analyses

  • Compare papers that report both human_eval and llm_as_judge to quantify judge-human agreement drift.
  • Stratify by benchmark (HotpotQA vs Windowsagentarena) before comparing methods.
  • Track metric sensitivity by reporting both cost and accuracy.
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
AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling

Mar 22, 2026

Yes Human Eval , Llm As Judge WebArena , ToolBench Precision , Pass@1 Not Reported
Same Words, Different Judgments: Modality Effects on Preference Alignment

Feb 26, 2026

Yes Automatic Metrics Not Reported Agreement Inter Annotator Agreement Reported
Meanings and Measurements: Multi-Agent Probabilistic Grounding for Vision-Language Navigation

Mar 19, 2026

Yes Simulation Env Mapg Bench Not Reported Not Reported
Dual-Modality Multi-Stage Adversarial Safety Training: Robustifying Multimodal Web Agents Against Cross-Modal Attacks

Mar 4, 2026

Yes Simulation Env MiniWoB++ Not Reported Not Reported
IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning

Sep 26, 2025

Yes Automatic Metrics Not Reported Accuracy , Cost Calibration
An Industrial-Scale Insurance LLM Achieving Verifiable Domain Mastery and Hallucination Control without Competence Trade-offs

Mar 15, 2026

Yes Automatic Metrics Not Reported Hallucination rate Not Reported
State-of-the-Art Arabic Language Modeling with Sparse MoE Fine-Tuning and Chain-of-Thought Distillation

Apr 7, 2026

Yes Automatic Metrics Not Reported Cost Not Reported
AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors

Feb 26, 2026

Yes Not Reported Auditbench Not Reported Not Reported
FewMMBench: A Benchmark for Multimodal Few-Shot Learning

Feb 25, 2026

Yes Not Reported Fewmmbench Not Reported Not Reported
Automatic In-Domain Exemplar Construction and LLM-Based Refinement of Multi-LLM Expansions for Query Expansion

Feb 9, 2026

Yes Not Reported TREC Not Reported Not Reported
A Framework for Closed-Loop Robotic Assembly, Alignment and Self-Recovery of Precision Optical Systems

Mar 23, 2026

Yes Not Reported Not Reported Precision Not Reported
Beyond the Illusion of Consensus: From Surface Heuristics to Knowledge-Grounded Evaluation in LLM-as-a-Judge

Mar 11, 2026

Yes Llm As Judge Not Reported Spearman Not Reported

Protocol Diff (Top Papers)

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

Signal AgentHER: Hindsight Experience Replay for LLM Agent… Same Words, Different Judgments: Modality Effects o… Meanings and Measurements: Multi-Agent Probabilisti…
Human Feedback DemonstrationsPairwise Preference, Rlaif Or Synthetic FeedbackDemonstrations
Evaluation Modes Human Eval, Llm As JudgeAutomatic MetricsSimulation Env
Benchmarks WebArena, ToolBenchNot reportedMapg Bench
Metrics Precision, Pass@1AgreementNot reported
Quality Controls Not reportedInter Annotator Agreement ReportedNot reported
Rater Population UnknownUnknownUnknown
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. State-of-the-Art Arabic Language Modeling with Sparse MoE Fine-Tuning and Chain-of-Thought Distillation

    Start here for detailed protocol reporting and quality-control evidence. Signals: automatic metrics + demonstration data. Focus: cost. Abstract: This paper introduces Arabic-DeepSeek-R1, an application-driven open-source Arabic LLM that.

  2. In-Context Learning in Speech Language Models: Analyzing the Role of Acoustic Features, Linguistic Structure, and Induction Heads

    Start here for detailed protocol reporting and quality-control evidence. Signals: demonstration data. Abstract: In-Context Learning (ICL) has been extensively studied in text-only Language Models, but remains largely unexplored.

  3. Epistemic Blinding: An Inference-Time Protocol for Auditing Prior Contamination in LLM-Assisted Analysis

    Start here for detailed protocol reporting and quality-control evidence. Signals: demonstration data. Abstract: This paper presents epistemic blinding in the context of an agentic system that uses large.

  4. AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: human evaluation + demonstration data. Focus: WebArena / precision. Abstract: AgentHER realises this idea through a four-stage.

  5. VolleyBots: A Testbed for Multi-Drone Volleyball Game Combining Motion Control and Strategic Play

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: automatic metrics + demonstration data. Focus: win rate. Abstract: Robot sports, characterized by well-defined objectives, explicit rules,.

  6. Beyond the Illusion of Consensus: From Surface Heuristics to Knowledge-Grounded Evaluation in LLM-as-a-Judge

    Include an LLM-as-judge paper to test judge design and agreement assumptions. Signals: LLM-as-judge + rubric ratings. Focus: spearman. Abstract: The paradigm of LLM-as-a-judge relies on a critical assumption,.

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

    Adds simulation environments with demonstration data for broader protocol coverage within this hub. Signals: simulation environments + demonstration data. Focus: Mapg-Bench. Abstract: Robots collaborating with humans must convert.

  8. SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning

    Adds simulation environments with demonstration data for broader protocol coverage within this hub. Signals: simulation environments + demonstration data. Abstract: Vision-language models (VLMs) have shown impressive capabilities across.

Known Limitations

Known Limitations

  • Only 2.6% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (21.1% 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

  • Demonstrations (69)
  • Rlaif Or Synthetic Feedback (7)
  • Pairwise Preference (5)
  • Critique Edit (3)

Evaluation Modes

  • Automatic Metrics (14)
  • Simulation Env (12)
  • Human Eval (2)
  • Llm As Judge (2)

Top Benchmarks

  • HotpotQA (2)
  • Windowsagentarena (2)
  • ALFWorld (1)
  • Auditbench (1)

Top Metrics

  • Cost (5)
  • Accuracy (4)
  • Agreement (2)
  • Latency (2)

Rater Population Mix

  • Domain Experts (14)
  • Mixed (2)

Quality Controls

  • Calibration (1)
  • Inter Annotator Agreement Reported (1)
Coverage diagnostics (sample-based): human-feedback 100.0% · benchmarks 18.3% · metrics 26.7% · 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.