This is the repository for the paper 'Enhancing Uncertainty Modeling with Semantic Graph for Hallucination Detection' (AAAI2025)

Unified Automated Evaluation for Hallucination Detection and Fact Verification

Collection of scripts and notebooks for OpenAI's latest GPT OSS models

Code for paper Towards Mitigating LLM Hallucination via Self Reflection

This is the code for the paper "Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation".

Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"

CEduMEval : A Chinese educational multi-task evaluation benchmark

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models

GAOKAO-Bench is an evaluation framework that utilizes GAOKAO questions as a dataset to evaluate large language models.

👮‍♂️The sensitive word tool for java.(敏感词/违禁词/违法词/脏词。基于 DFA 算法实现的高性能 java 敏感词过滤工具框架。内置支持单词标签分类分级。请勿发布涉及政治、广告、营销、翻墙、违反国家法律法规等内容。高性能敏感词检测过滤组件，附带繁体简体互换，支持全角半角互换，汉字转拼音，模糊搜索等功能。)

Streamlit app for chatting with Meta Llama 3.2 using Ollama and LangChain

a curated list of the role of small models in the LLM era

The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and…

GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI.

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

A pytorch adversarial library for attack and defense methods on images and graphs

Model interpretability and understanding for PyTorch

A Python package to assess and improve fairness of machine learning models.

This repository introduces different Explainable AI approaches and demonstrates how they can be implemented with PyTorch and torchvision. Used approaches are Class Activation Mappings, LIMA and SHa…

A game theoretic approach to explain the output of any machine learning model.

The project page of paper: Trusted Multi-View Classification [ICLR'2021 paper]

Reliable Conflictive Multi-view Learning

Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety. [ACL 2024]

Python-based Comprehensive Network Packet Analysis Library