TJUNLP-Lab

Awesome-LLMs-Evaluation-Papers. The papers are organized according to our survey: Evaluating Large Language Models: A Comprehensive Survey.

M3KE. A Massive Multi-Level Multi-Subject Knowledge Evaluation benchmark

Awesome-LLM-Safety-Papers.

awesome-NLP-Machine-Learning. A list of paper & code on machine learning techniques for NLP research, including RL/Self-supervised Learning/VAE/GAN/Meta learning

Awesome-Multilingual-LLMs-Papers. Awesome-Multilingual-LLMs-Papers

ChatSOP. Python

FuxiTranyu. FuxiTranyu-8B is an open-source multilingual large language model trained from scratch with 606B tokens.

CMoralEval. A Moral Evaluation Benchmark for Chinese Large Language Models

MCTS-VCB. Python

CommonMT.

Shallow-Discourse-Annotation-for-Chinese-TED-Talks. Datasets for "Shallow Discourse Annotation for Chinese TED Talks" Accepted by LREC 2020

KaFSP. Python

APRT. Python

TGEA. Python

CogAlign. Source code of ACL-2021 CogAlign: Learning to Align Textual Neural Representations to Cognitive Language Processing Signals

Lexical-Unit-Decoding-LUD-. Lexical Unit Decoding (LUD)

Debate4Math. Python

CRiskEval. CRiskEval is a Chinese dataset meticulously designed for gauging the risk proclivities inherent in LLMs.

Discourse-Phenomena-in-Document-level-Neural-Machine-Translation. Datasets for "A Test Suite for Evaluating Discourse Phenomena in Document-level Neural Machine Translation" accepted by Proceedings of the Second International Workshop of Discourse Processing

Tab-CQA. Tab-CQA

PCKMT. Source codes of ACL 2022-Efficient Cluster-Based k-Nearest-Neighbor Machine Translation

llm_translate_robust. Source code of LREC-COLING 2024 Paper: Can Large Language Models Learn Translation Robustness from Noisy-Source In-context Demonstrations?

LFED. Source dataset of LREC-COLING 2024 paper: A Literary Fiction Evaluation Dataset for Large Language Models

FineMATH. FineMath is a fine-grained mathematical evaluation benchmark dataset for assessing Chinese LLMs. FineMath is created to cover the major key mathematical concepts taught in elementary school math, which are further divided into 17 categories of math word problems, enabling in-depth analysis of mathematical reasoning abilities of LLMs.

tjunlp-lab.github.io. NLP Research Group from Tianjin University

CogTaskonomy. Source code of ACL-2022 CogTaskonomy: Cognitively Inspired Task Taxonomy Is Beneficial to Transfer Learning in NLP

Chinese-WPLC. Python