Skip to content
← Back to explorer

HFEPX Hub

CS.CL + Expert Verification Papers

Updated from current HFEPX corpus (Feb 27, 2026). 20 papers are grouped in this hub page. Common evaluation modes: Automatic Metrics, Simulation Env. Most common rater population: Domain Experts. Common annotation unit: Multi Dim Rubric. Frequent quality control: Gold Questions. Frequently cited benchmark: Retrieval. 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 26, 2026.

Papers: 20 Last published: Feb 26, 2026 Global RSS Tag RSS
Cs.CLExpert Verification

Research Narrative

Grounded narrative Model: deterministic-grounded Source: preview

Updated from current HFEPX corpus (Feb 27, 2026). This page tracks 20 papers for CS.CL + Expert Verification Papers. Dominant protocol signals include automatic metrics, simulation environments, human evaluation, with frequent benchmark focus on Retrieval, BIRD and metric focus on accuracy, cost. Use the grounded sections below to prioritize reproducible protocol choices, benchmark-matched comparisons, and judge-vs-human evaluation checks.

Why This Matters For Eval Research

Protocol Takeaways

Benchmark Interpretation

  • Retrieval appears in 10% of hub papers (2/20); use this cohort for benchmark-matched comparisons.
  • BIRD appears in 5% of hub papers (1/20); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 35% of hub papers (7/20); compare with a secondary metric before ranking methods.
  • cost is reported in 15% of hub papers (3/20); compare with a secondary metric before ranking methods.

Researcher Checklist

  • Maintain strength on Papers with explicit human feedback. Coverage is strong (100% vs 45% target).
  • Tighten coverage on Papers reporting quality controls. Coverage is usable but incomplete (20% vs 30% target).
  • Tighten coverage on Papers naming benchmarks/datasets. Coverage is usable but incomplete (25% vs 35% target).
  • Maintain strength on Papers naming evaluation metrics. Coverage is strong (75% vs 35% target).
  • Maintain strength on Papers with known rater population. Coverage is strong (100% vs 35% target).
  • Tighten coverage on Papers with known annotation unit. Coverage is usable but incomplete (30% vs 35% target).

Papers with explicit human feedback

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

Papers reporting quality controls

Coverage is usable but incomplete (20% vs 30% target).

Papers naming benchmarks/datasets

Coverage is usable but incomplete (25% vs 35% target).

Papers naming evaluation metrics

Coverage is strong (75% vs 35% target).

Papers with known rater population

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

Papers with known annotation unit

Coverage is usable but incomplete (30% vs 35% target).

Suggested Reading Order

  1. 1. An artificial intelligence framework for end-to-end rare disease phenotyping from clinical notes using large language models

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

  2. 2. TherapyProbe: Generating Design Knowledge for Relational Safety in Mental Health Chatbots Through Adversarial Simulation

    High citation traction makes this a useful baseline for method and protocol context.

  3. 3. MEDSYN: Benchmarking Multi-EviDence SYNthesis in Complex Clinical Cases for Multimodal Large Language Models

    High citation traction makes this a useful baseline for method and protocol context.

  4. 4. An Expert Schema for Evaluating Large Language Model Errors in Scholarly Question-Answering Systems

    High citation traction makes this a useful baseline for method and protocol context.

  5. 5. Multi-Agent Comedy Club: Investigating Community Discussion Effects on LLM Humor Generation

    Include a human-eval paper to anchor calibration against automated judge settings.

  6. 6. DistillNote: Toward a Functional Evaluation Framework of LLM-Generated Clinical Note Summaries

    Include an LLM-as-judge paper to assess judge design and agreement assumptions.

  7. 7. Hyper-KGGen: A Skill-Driven Knowledge Extractor for High-Quality Knowledge Hypergraph Generation

    Adds automatic metrics with expert verification for broader coverage within this hub.

  8. 8. CUICurate: A GraphRAG-based Framework for Automated Clinical Concept Curation for NLP applications

    Adds automatic metrics with expert verification for broader coverage within this hub.

Known Limitations

  • LLM-as-judge appears without enough inter-annotator agreement reporting.
  • Narrative synthesis is grounded in metadata and abstracts only; full-paper implementation details are not parsed.
  • Cross-page comparisons should be benchmark- and metric-matched to avoid protocol confounding.

Research Utility Links

human_eval vs llm_as_judge

both=0, left_only=1, right_only=1

0 papers use both Human Eval and Llm As Judge.

human_eval vs automatic_metrics

both=0, left_only=1, right_only=16

0 papers use both Human Eval and Automatic Metrics.

llm_as_judge vs automatic_metrics

both=0, left_only=1, right_only=16

0 papers use both Llm As Judge and Automatic Metrics.

Benchmark Brief

Retrieval

Coverage: 2 papers (10%)

2 papers (10%) mention Retrieval.

Examples: CUICurate: A GraphRAG-based Framework for Automated Clinical Concept Curation for NLP applications , MedPlan: A Two-Stage RAG-Based System for Personalized Medical Plan Generation

Benchmark Brief

BIRD

Coverage: 1 papers (5%)

1 papers (5%) mention BIRD.

Examples: CricBench: A Multilingual Benchmark for Evaluating LLMs in Cricket Analytics

Benchmark Brief

Cricbench

Coverage: 1 papers (5%)

1 papers (5%) mention Cricbench.

Examples: CricBench: A Multilingual Benchmark for Evaluating LLMs in Cricket Analytics

Metric Brief

accuracy

Coverage: 7 papers (35%)

7 papers (35%) mention accuracy.

Examples: MEDSYN: Benchmarking Multi-EviDence SYNthesis in Complex Clinical Cases for Multimodal Large Language Models , What Makes a Good Doctor Response? An Analysis on a Romanian Telemedicine Platform , HLE-Verified: A Systematic Verification and Structured Revision of Humanity's Last Exam

Metric Brief

cost

Coverage: 3 papers (15%)

3 papers (15%) mention cost.

Examples: Multi-Objective Alignment of Language Models for Personalized Psychotherapy , From Raw Corpora to Domain Benchmarks: Automated Evaluation of LLM Domain Expertise , A Scalable Framework for Evaluating Health Language Models

Metric Brief

precision

Coverage: 3 papers (15%)

3 papers (15%) mention precision.

Examples: An Expert Schema for Evaluating Large Language Model Errors in Scholarly Question-Answering Systems , An artificial intelligence framework for end-to-end rare disease phenotyping from clinical notes using large language models , CUICurate: A GraphRAG-based Framework for Automated Clinical Concept Curation for NLP applications

Most Cited In This Hub

Fast path to methods with the strongest citation traction in this scope.

Papers: TherapyProbe: Generating Design Knowledge for Relational Safety in Mental Health Chatbots Through Adversarial Simulation , MEDSYN: Benchmarking Multi-EviDence SYNthesis in Complex Clinical Cases for Multimodal Large Language Models , An Expert Schema for Evaluating Large Language Model Errors in Scholarly Question-Answering Systems

Most Recent

Fast path to latest protocol changes and newly published evaluation setups.

Papers: TherapyProbe: Generating Design Knowledge for Relational Safety in Mental Health Chatbots Through Adversarial Simulation , MEDSYN: Benchmarking Multi-EviDence SYNthesis in Complex Clinical Cases for Multimodal Large Language Models , An Expert Schema for Evaluating Large Language Model Errors in Scholarly Question-Answering Systems

Best Protocol Detail

Papers with explicit rater/unit metadata and quality-control signals for reproducibility.

Papers: An artificial intelligence framework for end-to-end rare disease phenotyping from clinical notes using large language models

Top Papers

Related Hubs