rucaibox / llmrank Goto Github PK
View Code? Open in Web Editor NEW[ECIR'24] Implementation of "Large Language Models are Zero-Shot Rankers for Recommender Systems"
License: MIT License
[ECIR'24] Implementation of "Large Language Models are Zero-Shot Rankers for Recommender Systems"
License: MIT License
据我了解,这个表格中的zero-shot部分,随机抽取200个用户,作为test set,每个用户1个正样本+19个负采样;
我的问题是,baseline中的full这些模型的指标
另外在3.2节中提到:"The top-3 best items retrieved by each candidate generation model will be merged into a candidate set containing a total of 21 items." 我想问一下:
3. 每种检索方式检索的3个中,如果有重复是怎么处理的?
感谢回复!
test result: OrderedDict([('recall@1', 0.04), ('recall@5', 0.235), ('recall@10', 0.46), ('recall@20', 1.0), ('recall@50', 1.0), ('ndcg@1', 0.04), ('ndcg@5', 0.1323), ('ndcg@10', 0.2035), ('ndcg@20', 0.3383), ('ndcg@50', 0.3383)])
您好,以上是我按照给出的sasrec预训练模型和代码中的数据得到的结果,远低于论文结果,请问是怎么回事,是yaml文件中某个地方的设置问题吗,现在是在random数据集中进行的,请问是什么原因?
在使用asyncio异步调用api时显示Error communicating with OpenAI,而当使用串行调用api时,即async_dispatch设为False,可以正常返回结果。
hello, I try to search some user with items from m1-1m.random in file m1-1m.inter, but I cannot find the corresponding one?does this file include random negative pairs?
Lines 22 to 23 in 2d2384f
您好,这里我有些困惑,有些不确定。
filed可能指的是user 和 item;
field 2 token_id,token_id 是什么?
user_token 2 id 和 item_token 2 id 这里的id是什么?
这里可能涉及内部id和外部id,item id、token 和真实item的自然语言名字,这三个如何转换?
感谢您的工作,期望得到您的回复。
您好,我从代码中看到你们实现boostrap策略是通过同一个样本复制三次然后shuffle计算结果的,那么你们的方法在推理的阶段是如何使用呢?比如有三个候选项目,三次大模型给出三个排序结果,如何将这个shuffle三次的输出结果综合得到最后的输出结果呢?这块我看论文中没有明显提出来,还是说这不是你们论文的讨论范围,也就是你们只是做评测,然后这个过程和推理过程是有差别的呢?
希望能得到您的回答,谢谢!
使用python dataset/unisrec_auxiliary_files_process.py生成 *.feat1CLS时,提示:
huggingface_hub.utils._validators.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/mnt/zhangjunjie/bert-base-uncased'.
此处是否有需要下载的预训练模型
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.