中文纠错数据集汇总

CTC2021-中文文本纠错大赛的SOTA方案及在线演示

IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

DSPy: The framework for programming—not prompting—foundation models

Latex双栏中文模板，修改自ACL会议模板

Visualize the intermediate output of Mistral 7B

[CVPR 2024] Shadows Don’t Lie and Lines Can’t Bend! Generative Models don’t know Projective Geometry...for now

Paper list of misinformation research using (multi-modal) large language models, i.e., (M)LLMs.

[ACL'24] Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning

Tools for merging pretrained large language models.

中文大模型能力评测榜单：目前已囊括128个大模型，覆盖chatgpt、gpt-4o、谷歌gemini、百度文心一言、阿里通义千问、百川、讯飞星火、商汤senseChat、minimax等商用模型， 以及qwen2.5、llama3.1、glm4、书生internLM2.5、openbuddy、AquilaChat等开源大模型。不仅提供能力评分排行榜，也提供所有模型的原始输出结果！

[NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other models

[NeurIPS 2024] Needle In A Multimodal Haystack (MM-NIAH): A comprehensive benchmark designed to systematically evaluate the capability of existing MLLMs to comprehend long multimodal documents.

MuCGEC中文纠错数据集及文本纠错SOTA模型开源；Code & Data for our NAACL 2022 Paper "MuCGEC: a Multi-Reference Multi-Source Evaluation Dataset for Chinese Grammatical Error Correction"

Train transformer language models with reinforcement learning.

pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，Qwen2.5等模型应用在纠错场景，开箱即用。

Code for training of T5-based Grammatical Error Correction models with cLang-8.

FuseAI Project

LLM-Merging: Building LLMs Efficiently through Merging

Unofficial PyTorch implementation of "GECToR -- Grammatical Error Correction: Tag, Not Rewrite"

A Code System for Grammar Error Correction Method. Code Repo for ACL 24 Main "Detection-Correction Structure via General Language Model for Grammatical Error Correction"

2019-SOTA简繁中文拼写检查工具：FASPell Chinese Spell Checker (Chinese Spell Check / 中文拼写检错 / 中文拼写纠错 / 中文拼写检查)

Official implementation of the papers "GECToR – Grammatical Error Correction: Tag, Not Rewrite" (BEA-20) and "Text Simplification by Tagging" (BEA-21)

MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.

Pillars of Grammatical Error Correction: Comprehensive Inspection Of Contemporary Approaches In The Era of Large Language Models

Official Implementation of "Multi-Head RAG: Solving Multi-Aspect Problems with LLMs"

Data and code for Kang et al., NAACL 2018's paper titled "A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications"