Yuxin Jiang 姜宇心

Lion. [EMNLP 2023] Lion: Adversarial Distillation of Proprietary Large Language Models

PromCSE. [EMNLP 2022] Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning

FollowBench. [ACL 2024] FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models

SST-2-sentiment-analysis. Use BiLSTM_attention, BERT, ALBERT, RoBERTa, XLNet model to classify the SST-2 data set based on pytorch

Chinese-sentence-pair-modeling. Use deep models including BiLSTM, ABCNN, ESIM, RE2, BERT, etc. and evaluate on 5 Chinese NLP datasets: LCQMC, BQ Corpus, ChineseSTS, OCNLI, CMNLI

Movielens1M-movie-recommendation-system. 使用MovieLens数据集实现了基于Auto Encoder(AE), Variational Auto Encoder(VAE), BERT的深度学习电影推荐系统

LTE. [ACL 2024] Learning to Edit: Aligning LLMs with Knowledge Editing

improved_DeepLOB. This repo contains my reimplementation and improvement of DeepLOB model.

GOLF_for_IDRR. [ACL 2023] Global and Local Hierarchy-aware Contrastive Framework for Hierarchical Implicit Discourse Relation Recognition

BMC. [ICLR 2025] Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization

WebR. [ACL 2025] Instruction-Tuning Data Synthesis from Scratch via Web Reconstruction

deep-learning-tutorial. a deep learning tutorial containing FNN, CNN, RNN, XAI, VAE, GAN, etc.

MSBD-5003-project. parallel implementation of hierarchical clustering algorithm based on pyspark

Debate-alpaca-lora. Instruct-tune LLaMA on debate data; Light-weight DebateGPT

argument-impact-classification. Further research on the paper "The Role of Pragmatic and Discourse Context in Determining Argument Impact"

MSBD_5001_kaggle. Containing the data and codes for MSBD_5001_kaggle_competition

XAI_in_NLP. XAI_in_NLP

COMP_5222_Project. This is the repository of COMP 5222 group project, our group number is 13.

algorithms-python. 使用python编写的部分算法题目整理

YJiangcm.

YJiangcm.github.io. Personal Github Page of Yuxin Jiang

RLVRR. From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation