ref-hallucination-arena
仓库创建 2025年7月8日最近提交 18 天前SkillHot 收录 20 天前
▸ 精选理由
字段级验证准确性,适合引用质量基准测试
▸ 风险提示
会调用外部数据库/API进行核验
这个 Skill 做什么
检验模型引用的文献是否真实并衡量参考文献的幻觉率
把模型给出的学术引用一条条查实,去 Crossref、PubMed、arXiv、DBLP 验证题名、作者、年份、DOI 等字段对不对,算出整体和按学科的“引用幻觉率”。常在你要评测或比对模型推荐论文准不准、检查参考文献质量时用。能解析 BibTeX 输出并支持 ReAct + web search 的工具辅助,能细到年份约束和学科分布,方便定位问题来源。
▸ 展开 SKILL.md 英文原文
Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination rate, per-field accuracy (title/author/year/DOI), discipline breakdown, and year constraint compliance. Supports tool-augmented (ReAct + web search) mode. Use when the user asks to evaluate, benchmark, or compare models on academic reference hallucination, literature recommendation quality, or citation accuracy.
748
Stars
61
Forks
18
仓库内 Skill
+40
7 日增星
安装 / 使用
给你的 Agent 一句话(通用)
帮我安装这个 skill:https://raw.githubusercontent.com/agentscope-ai/OpenJudge/main/skills/ref-hallucination-arena/SKILL.md或 curl 直取 SKILL.md
curl -fsSL "https://raw.githubusercontent.com/agentscope-ai/OpenJudge/main/skills/ref-hallucination-arena/SKILL.md"SKILL.MD 节选查看完整文件 ↗
# Reference Hallucination Arena Skill Evaluate how accurately LLMs recommend real academic references using the OpenJudge `RefArenaPipeline`: 1. **Load queries** — from JSON/JSONL dataset 2. **Collect responses** — BibTeX-formatted references from target models 3. **Extract references** — parse BibTeX entries from model output 4. **Verify references** — cross-check against Crossref / PubMed / arXiv / DBLP 5. **Score & rank** — compute verification rate, per-field accuracy, discipline breakdown 6. **Generate report** — Markdown report + visualization charts ## Prerequisites ```bash # Install OpenJudge pip install py-openjudge # Extra dependency for ref_hallucination_arena (chart generati
via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有