Skip to content
← Back to explorer

HFEPX Benchmark Hub

MMLU Or LMSYS Chatbot Arena Or SWE-bench Benchmark Papers

Updated from current HFEPX corpus (Mar 31, 2026). 36 papers are grouped in this benchmark page.

Read Full Context

Updated from current HFEPX corpus (Mar 31, 2026). 36 papers are grouped in this benchmark page. Common evaluation modes: Automatic Metrics, Llm As Judge. Most common rater population: Domain Experts. Common annotation unit: Pairwise. Frequent quality control: Calibration. Frequently cited benchmark: LMSYS Chatbot Arena. 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 Feb 13, 2026.

Papers: 36 Last published: Feb 13, 2026 Global RSS

Researcher Quick Triage

Use this page for benchmark-matched method comparisons and eval protocol selection. Quality band: Medium .

High-Signal Coverage

100.0%

36 / 36 sampled papers are not low-signal flagged.

Replication-Ready Set

8

Papers with explicit benchmark + metric + eval mode fields.

Quality Controls

2.8%

1 papers report calibration/adjudication/IAA controls.

  • 19 papers explicitly name benchmark datasets in the sampled set.
  • 8 papers report at least one metric term in metadata extraction.
  • Start with the ranked shortlist below before reading all papers.

Primary action: Start with the top 2 benchmark-matched papers, then compare evaluation modes in the protocol matrix.

Why This Matters (Expanded)

Why This Matters For Eval Research

  • 73.7% of papers report explicit human-feedback signals, led by pairwise preferences.
  • automatic metrics appears in 25% of papers in this hub.
  • LMSYS Chatbot Arena is a recurring benchmark anchor for cross-paper comparisons in this page.
Protocol Notes (Expanded)

Protocol Takeaways

  • Most common quality-control signal is rater calibration (2.8% of papers).
  • Rater context is mostly domain experts, and annotation is commonly pairwise annotation; use this to scope replication staffing.
  • Pair this hub with a human_eval-heavy hub to validate judge-model calibration.

Benchmark Interpretation

  • LMSYS Chatbot Arena appears in 42.1% of hub papers (8/36); use this cohort for benchmark-matched comparisons.
  • MMLU appears in 36.8% of hub papers (7/36); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 26.3% of hub papers (5/36); compare with a secondary metric before ranking methods.
  • cost is reported in 21.1% of hub papers (4/36); compare with a secondary metric before ranking methods.

Start Here (Benchmark-Matched First 6)

Ranked by protocol completeness so you can quickly find papers suitable for comparison studies.

Protocol Matrix (Top 10)

Compare protocol ingredients quickly before deep-reading full papers.

Paper Eval Modes Human Feedback Metrics Quality Controls
SCOPE: Selective Conformal Optimized Pairwise LLM Judging

Feb 13, 2026

Automatic Metrics Pairwise Preference Error rate Calibration
PubMed Reasoner: Dynamic Reasoning-based Retrieval for Evidence-Grounded Biomedical Question Answering

Mar 28, 2026

Llm As Judge, Automatic Metrics Expert Verification Accuracy, Relevance Not reported
$V_1$: Unifying Generation and Self-Verification for Parallel Reasoners

Mar 4, 2026

Automatic Metrics Pairwise Preference Pass@1 Not reported
How Reliable is Language Model Micro-Benchmarking?

Oct 9, 2025

Automatic Metrics Pairwise Preference Accuracy, Cost Not reported
Learning When to Sample: Confidence-Aware Self-Consistency for Efficient LLM Chain-of-Thought Reasoning

Mar 9, 2026

Automatic Metrics Not reported Accuracy, Cost Not reported
SWE-Protégé: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering Agents

Feb 25, 2026

Automatic Metrics Not reported Pass@1, Latency Not reported
D-COT: Disciplined Chain-of-Thought Learning for Efficient Reasoning in Small Language Models

Feb 25, 2026

Automatic Metrics Not reported Accuracy Not reported
Confidence-Driven Multi-Scale Model Selection for Cost-Efficient Inference

Feb 25, 2026

Automatic Metrics Not reported Accuracy, Cost Not reported
Inducing Epistemological Humility in Large Language Models: A Targeted SFT Approach to Reducing Hallucination

Mar 18, 2026

Not reported Pairwise Preference Not reported Not reported
Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training

Mar 12, 2026

Not reported Pairwise Preference Not reported Not reported
Researcher Workflow (Detailed)

Checklist

  • Strong: Papers with explicit human feedback

    Coverage is strong (73.7% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (5.3% vs 30% target).

  • Strong: Papers naming benchmarks/datasets

    Coverage is strong (100% vs 35% target).

  • Strong: Papers naming evaluation metrics

    Coverage is strong (47.4% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (10.5% vs 35% target).

  • Strong: Papers with known annotation unit

    Coverage is strong (47.4% vs 35% target).

Strengths

  • Strong human-feedback signal (73.7% of papers).
  • Most papers provide measurable evaluation context (100% benchmarks, 47.4% metrics).
  • Agentic evaluation appears in 31.6% of papers.

Known Gaps

  • Only 5.3% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (10.5% coverage).
  • LLM-as-judge appears without enough inter-annotator agreement reporting.

Suggested Next Analyses

  • Pair this hub with a human_eval-heavy hub to validate judge-model calibration.
  • Stratify by benchmark (LMSYS Chatbot Arena vs MMLU) before comparing methods.
  • Track metric sensitivity by reporting both accuracy and cost.
  • Add inter-annotator agreement checks when reproducing these protocols.

Recommended Queries

Known Limitations
  • Only 5.3% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (10.5% 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)
  • Llm As Judge (2)

Human Feedback Mix

  • Pairwise Preference (12)
  • Expert Verification (1)
  • Rubric Rating (1)

Top Benchmarks

  • LMSYS Chatbot Arena (8)
  • MMLU (7)
  • SWE Bench (4)
  • Arena Hard (3)

Top Metrics

  • Accuracy (5)
  • Cost (4)
  • Pass@1 (3)
  • Error rate (1)

Top Papers On This Benchmark

Related Benchmark Hubs

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