voidism/DoLa
Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"
Code for the EMNLP 2024 paper "Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps"
$ git clone https://github.com/voidism/Lookback-Lens.gitOfficial implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"
▲ +20 ★ this week
An open-source, tool-augmented conversational language model from Fudan University
Benchmarking long-form factuality in large language models. Original code for our paper "Long-form factuality in large language models".
聚宝盆(Cornucopia): 中文金融系列开源可商用大模型,并提供一套高效轻量化的垂直领域LLM训练框架(Pretraining、SFT、RLHF、Quantize等)
✨✨Woodpecker: Hallucination Correction for Multimodal Large Language Models
Dataset and evaluation code for measuring hallucinations in Chinese large language models
Data from GitHub · snapshot Nov 13, 2026