RLMRec
RLMRec copied to clipboard
HKUDS
[WWW'2024] "RLMRec: Representation Learning with Large Language Models for Recommendation"
Hi 👋, Thanks for your great work! I try to run your code on my own dataset. For fairness comparison, can you upload the whole data processing code? I find...
Hello, I am very interested in the experiment of LLMs as recommers in your paper A.3. I would like to reproduce and try it. I wonder if you can provide...
我对你们的工作很感兴趣！我借用了你们的项目尝试了下现在流行的一些多模态表征融入的方法。我发现加入了这些方法之后，在验证集上的效果都比不加多模态表征的情况要好，但是在测试集上却大大不如验证集。我看了下github issue。如果都是3:1:1取的，难道在验证集和测试集的效果应该差不多吗？还是说测试集上没有多模态的表征但是验证集上有，所以才导致了这种情况？
Thank you for your work. I have a small question to ask regarding the generate_profile.py file in the generation subdirectory. Currently, it can only generate responses (i.e., summarizations and reasonings)...
Hi, I have a quick question about the data for the Yelp dataset. In the user_prompts.json file, each business has a description field (e.g., "Users who enjoy outdoor shopping centers...")....
Hello! This is really nice and interesting work loved that! However I am trying to regenerate the raw files you used for this study. After using all the filters and...
Hello, Thank you for your great work on this paper. I noticed that in your experiments you compared against KAR, originally proposed as a reranker model. Could you kindly let...
Regarding to the user profiles generation part, how do you randmly choose 3 recipes for each user? In the whole recipe pool or just the recipes in the training set...
Hello author, I have some questions about the dataset of the code. For example, the screening of Amazon Books filters out interactions with a score lower than 3 according to...
