- name
SKILL.md
Le fichier du skill reste dans le dépôt de l'éditeur.
Collez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add agentscope-ai/OpenJudge --skill 02-ref-hallucination-arena -a cursor -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add agentscope-ai/OpenJudge --skill 02-ref-hallucination-arena -a claude-code -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add agentscope-ai/OpenJudge --skill 02-ref-hallucination-arena -a codex -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add agentscope-ai/OpenJudge --skill 02-ref-hallucination-arena -a grok -yEnvoyez le message copié dans un chat Grok Bot. Le Bot récupère ce SKILL.md sur GitHub et l'ajoute aux skills que partagent tous vos Bots.
Install this skill: https://github.com/agentscope-ai/OpenJudge/tree/HEAD/skills/arena-eval/02-ref-hallucination-arenaDe l'éditeur
Evaluate how accurately LLMs recommend real academic references using the
OpenJudge RefArenaPipeline:
# Install OpenJudge
pip install py-openjudge
# Extra dependency for ref_hallucination_arena (chart generation)
pip install matplotlib
# Run evaluation with config file
python -m cookbooks.ref_hallucination_arena --config config.yaml --save
# Resume from checkpoint (default behavior)
python -m cookbooks.ref_hallucination_arena --config config.yaml --save
# Start fresh, ignore checkpoint
python -m cookbooks.ref_hallucination_arena --config config.yaml --fresh --save
# Override output directory
python -m cookbooks.ref_hallucination_arena --config config.yaml \
--output_dir ./my_results --save
import asyncio
from cookbooks.ref_hallucination_arena.pipeline import RefArenaPipeline
async def main():
pipeline = RefArenaPipeline.from_config("config.yaml")
result = await pipeline.evaluate()
for rank, (model, score) in enumerate(result.rankings, 1):
print(f"{rank}. {model}: {score:.1%}")
asyncio.run(main())
task:
description: "Evaluate LLM reference recommendation capabilities"
dataset:
path: "./data/queries.json"
target_endpoints:
model_a:
base_url: "https://api.openai.com/v1"
api_key: "${OPENAI_API_KEY}"
model: "gpt-4"
system_prompt: "You are an academic literature recommendation expert. Recommend {num_refs} real papers in BibTeX format. Only recommend papers you are confident actually exist."
model_b:
base_url: "https://dashscope.aliyuncs.com/compatible-mode/v1"
api_key: "${DASHSCOPE_API_KEY}"
model: "qwen3-max"
system_prompt: "You are an academic literature recommendation expert. Recommend {num_refs} real papers in BibTeX format. Only recommend papers you are confident actually exist."
Each query in the JSON/JSONL dataset:
{
"query": "Please recommend papers on Transformer architectures for NLP.",
"discipline": "computer_science",
"num_refs": 5,
"language": "en",
"year_constraint": {"min_year": 2020}
}
Official dataset: OpenJudge/ref-hallucination-arena
Overall accuracy (verification rate):
Per-field accuracy:
title_accuracy — % of titles matching real papersauthor_accuracy — % of correct author listsyear_accuracy — % of correct publication yearsdoi_accuracy — % of valid DOIsVerification status:
VERIFIED — title + author + year all exactly match a real paperSUSPECT — partial match (e.g. title matches but authors differ)NOT_FOUND — no match in any databaseERROR — API timeout or network failureRanking order: overall accuracy → year compliance rate → avg confidence → completeness
evaluation_results/ref_hallucination_arena/
├── evaluation_report.md # Detailed Markdown report
├── evaluation_results.json # Rankings, per-field accuracy, scores
├── verification_chart.png # Per-field accuracy bar chart
├── discipline_chart.png # Per-discipline accuracy chart
├── queries.json # Loaded evaluation queries
├── responses.json # Raw model responses
├── extracted_refs.json # Extracted BibTeX references
├── verification_results.json # Per-reference verification details
└── checkpoint.json # Pipeline checkpoint for resume
>
---name: 02-ref-hallucination-arenadescription: >---# skills/arena-eval/02-ref-hallucination-arena/SKILL.mdFAQ
Téléchargez skills/arena-eval/02-ref-hallucination-arena/SKILL.md auprès de l'éditeur, ou copiez le chemin et ouvrez le dépôt. PlugMCP répertorie le skill et n'héberge pas le fichier.
L'éditeur le maintient sur https://github.com/agentscope-ai/OpenJudge.
Claude, Cursor, Codex et Grok Build peuvent lire un SKILL.md que vous ajoutez depuis le dépôt de l'éditeur. Grok Bot l'installe lorsque vous envoyez dans un chat le lien du dossier GitHub du skill.