CRS-Mentor

*** Model *** ** LANGUAGE MODELS: glm4-chat ** EMBEDDING MODELS: bce-embedding-base_v1 ** RERANK MODELS: bce-reranker-base_v1

*** Dataset ***

*** Aminer ***

** Dataset Address **: https://www.aminer.cn/aminernetwork

** Aminer.pyAminer.py Processing Aminer Dataset Code

** AMiner-Paper.txt The original dataset is 2,092,356 pieces of data

** aminer_data_mini.csv The processed streamlined dataset consists of 10,737 pieces of data

*** DBLP ***

** Original dataset address:https://dblp.uni-trier.de/xml/

** The address of the processed dataset: https://www.aminer.cn/citation

** dblp.py Processing DBLP dataset code (DBLP-Citation-network V14 dataset used in the experiment)

** dblp_v14.json The original dataset is 5,259,858 pieces of data

** dbpl_data_mini.csv The processed streamlined dataset consists of 11,618 pieces of data

*** Code ***

** code CSR-Mentor code