Skip to content
← Back to explorer

HFEPX Hub

Math Papers (Last 30 Days)

Updated from current HFEPX corpus (Apr 17, 2026). 23 papers are grouped in this hub page.

Read Full Context

Updated from current HFEPX corpus (Apr 17, 2026). 23 papers are grouped in this hub page. Common evaluation modes: Automatic Metrics, Human Eval. Most common rater population: Domain Experts. Common annotation unit: Trajectory. Frequent quality control: Calibration. Frequently cited benchmark: GSM8K. 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 2, 2026.

Papers: 23 Last published: Apr 2, 2026 Global RSS Tag RSS
MathLast 30d

Researcher Quick Triage

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

High-Signal Coverage

100.0%

23 / 23 sampled papers are not low-signal flagged.

Replication-Ready Set

6

Benchmark + metric + eval mode explicitly present.

Judge/Human Comparability

0

Papers containing both `human_eval` and `llm_as_judge`.

  • 6 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.

Need evaluators for this research workflow?

Post a Job →

Why This Matters For Eval Research

  • 47.8% of papers report explicit human-feedback signals, led by critique/edit feedback.
  • automatic metrics appears in 69.6% of papers in this hub.
  • GSM8K is a recurring benchmark anchor for cross-paper comparisons in this page.

Protocol Takeaways

  • Most common quality-control signal is rater calibration (4.3% 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

  • GSM8K appears in 21.7% of hub papers (5/23); use this cohort for benchmark-matched comparisons.
  • AlpacaEval appears in 4.3% of hub papers (1/23); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 52.2% of hub papers (12/23); compare with a secondary metric before ranking methods.
  • cost is reported in 21.7% of hub papers (5/23); compare with a secondary metric before ranking methods.
Researcher Checklist (Expanded)

Researcher Checklist

  • Strong: Papers with explicit human feedback

    Coverage is strong (47.8% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (8.7% vs 30% target).

  • Moderate: Papers naming benchmarks/datasets

    Coverage is usable but incomplete (34.8% vs 35% target).

  • Strong: Papers naming evaluation metrics

    Coverage is strong (69.6% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (17.4% vs 35% target).

  • Moderate: Papers with known annotation unit

    Coverage is usable but incomplete (34.8% vs 35% target).

Strengths

  • Strong human-feedback signal (47.8% of papers).
  • Contains both human-eval and LLM-as-judge protocols for head-to-head methodology comparison.
  • Agentic evaluation appears in 52.2% of papers.

Known Gaps

  • Only 8.7% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (17.4% coverage).
  • LLM-as-judge appears without enough inter-annotator agreement reporting.

Suggested Next Analyses

  • Compare papers that report both human_eval and llm_as_judge to quantify judge-human agreement drift.
  • Stratify by benchmark (GSM8K vs AlpacaEval) before comparing methods.
  • Track metric sensitivity by reporting both accuracy and cost.
  • Add inter-annotator agreement checks when reproducing these protocols.
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
Stabilizing Iterative Self-Training with Verified Reasoning via Symbolic Recursive Self-Alignment

Mar 23, 2026

Yes Automatic Metrics GSM8K Accuracy Not Reported
PAVE: Premise-Aware Validation and Editing for Retrieval-Augmented LLMs

Mar 21, 2026

Yes Automatic Metrics Post Retrieval Accuracy 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
RASPRef: Retrieval-Augmented Self-Supervised Prompt Refinement for Large Reasoning Models

Mar 27, 2026

Yes Not Reported GSM8K Not Reported Not Reported
TARo: Token-level Adaptive Routing for LLM Test-time Alignment

Mar 19, 2026

Yes Not Reported AlpacaEval Not Reported Not Reported
RuleForge: Automated Generation and Validation for Web Vulnerability Detection at Scale

Apr 2, 2026

Yes Llm As Judge , Automatic Metrics Not Reported Auroc Not Reported
QED-Nano: Teaching a Tiny Model to Prove Hard Theorems

Apr 6, 2026

Yes Automatic Metrics Not Reported Inference cost Not Reported
Towards Reward Modeling for AI Tutors in Math Mistake Remediation

Mar 25, 2026

Yes Automatic Metrics Not Reported Accuracy , Coherence Not Reported
Generating and Evaluating Sustainable Procurement Criteria for the Swiss Public Sector using In-Context Prompting with Large Language Models

Mar 23, 2026

Yes Not Reported Not Reported Not Reported Gold Questions
Don't Overthink It: Inter-Rollout Action Agreement as a Free Adaptive-Compute Signal for LLM Agents

Apr 9, 2026

No
Not Reported
Automatic Metrics GSM8K Accuracy 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 , Inference cost Not Reported
Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learning

Apr 1, 2026

No
Not Reported
Automatic Metrics HLE Accuracy , Token cost Not Reported

Protocol Diff (Top Papers)

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

Signal Stabilizing Iterative Self-Training with Verified R… PAVE: Premise-Aware Validation and Editing for Retr… Entropy trajectory shape predicts LLM reasoning rel…
Human Feedback Pairwise PreferenceCritique EditNot reported
Evaluation Modes Automatic MetricsAutomatic MetricsAutomatic Metrics
Benchmarks GSM8KPost RetrievalGSM8K
Metrics AccuracyAccuracyAccuracy, Calibration error
Quality Controls Not reportedNot reportedCalibration
Rater Population UnknownUnknownUnknown
Annotation Unit UnknownUnknownScalar
Suggested Reading Order (Extended)

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

Suggested Reading Order

  1. Don't Overthink It: Inter-Rollout Action Agreement as a Free Adaptive-Compute Signal for LLM Agents

    Start here for detailed protocol reporting and quality-control evidence. Signals: automatic metrics. Focus: GSM8K / accuracy. Abstract: Inference-time compute scaling has emerged as a powerful technique for improving.

  2. Cognitive Loop of Thought: Reversible Hierarchical Markov Chain for Efficient Mathematical Reasoning

    Start here for detailed protocol reporting and quality-control evidence. Signals: automatic metrics. Focus: accuracy. Abstract: Multi-step Chain-of-Thought (CoT) has significantly advanced the mathematical reasoning capabilities of LLMs by.

  3. How Long Reasoning Chains Influence LLMs' Judgment of Answer Factuality

    Start here for detailed protocol reporting and quality-control evidence. Signals: human evaluation. Focus: accuracy. Abstract: Large language models (LLMs) has been widely adopted as a scalable surrogate for.

  4. Learning to Predict Future-Aligned Research Proposals with Language Models

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: human evaluation. Focus: accuracy. Abstract: Large language models (LLMs) are increasingly used to assist ideation in research,.

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

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: LLM-as-judge + expert verification. Focus: auroc. Abstract: This paper focuses on RuleForge's architecture and operational deployment for.

  6. RASPRef: Retrieval-Augmented Self-Supervised Prompt Refinement for Large Reasoning Models

    Include an LLM-as-judge paper to test judge design and agreement assumptions. Signals: critique/edit feedback. Focus: GSM8K. Abstract: To address this limitation, we introduce Retrieval-Augmented Self-Supervised Prompt Refinement (RASPRef),.

  7. Entropy trajectory shape predicts LLM reasoning reliability: A diagnostic study of uncertainty dynamics in chain-of-thought

    Adds automatic metrics for broader protocol coverage within this hub. Signals: automatic metrics. Focus: GSM8K / accuracy. Abstract: Chain-of-thought (CoT) reasoning improves LLM accuracy, yet detecting failures cheaply.

  8. Stabilizing Iterative Self-Training with Verified Reasoning via Symbolic Recursive Self-Alignment

    Adds automatic metrics with pairwise preferences for broader protocol coverage within this hub. Signals: automatic metrics + pairwise preferences. Focus: GSM8K / accuracy. Abstract: We further demonstrate that.

Known Limitations

Known Limitations

  • Only 8.7% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (17.4% 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

  • Critique Edit (3)
  • Expert Verification (3)
  • Pairwise Preference (3)
  • Red Team (1)

Evaluation Modes

  • Automatic Metrics (16)
  • Human Eval (2)
  • Llm As Judge (1)
  • Simulation Env (1)

Top Benchmarks

  • GSM8K (5)
  • AlpacaEval (1)
  • HLE (1)
  • HumanEval+ (1)

Top Metrics

  • Accuracy (12)
  • Cost (5)
  • Coherence (2)
  • Inference cost (2)

Rater Population Mix

  • Domain Experts (4)

Quality Controls

  • Calibration (1)
  • Gold Questions (1)
Coverage diagnostics (sample-based): human-feedback 47.8% · benchmarks 34.8% · metrics 69.6% · quality controls 8.7%.

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.