hallucinations - GitHub 开源项目专题

1

vectara/hallucination-leaderboard

Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents

Python ⭐ 3.3k ⑂ 107 Apache-2.0 · 2026-05-12推送

generative-ai llm

2026-05-12

最近推送

2

lechmazur/confabulations

Hallucinations (Confabulations) Document-Based Benchmark for RAG. Includes human-verified questions and answers.

HTML ⭐ 249 ⑂ 9 · 2025-08-08推送

benchmark claude

2025-08-08

最近推送

3

LLAMATOR-Core/llamator

Red Teaming python-framework for testing chatbots and GenAI systems.

Python ⭐ 215 ⑂ 21 NOASSERTION · 2026-05-21推送

agent ai

2026-05-21

最近推送

4

IAAR-Shanghai/UHGEval

[ACL 2024] User-friendly evaluation framework: Eval Suite & Benchmarks: UHGEval, HaluEval, HalluQA, etc.

Python ⭐ 182 ⑂ 13 Apache-2.0 · 2025-06-07推送

benchmark chatgpt

2025-06-07

最近推送

5

rungalileo/hallucination-index

Initiative to evaluate and rank the most popular LLMs across common task types based on their propensity to hallucinate.

⭐ 116 ⑂ 8 · 2025-07-29推送

large-language-models llm

2025-07-29

最近推送