Awesome-LLM-for-RecSys

Why we included this project

Researchers and engineers working on recommender systems will find this index a fast way to see how large language models are being used across the field. The papers are grouped by where the LLM enters the pipeline, from feature engineering to scoring, so you can jump straight to the stage you care about. Each entry records the LLM backbone and tuning strategy, which makes it easy to compare work that keeps models frozen against approaches that use full fine-tuning or LoRA. The companion survey, published in ACM TOIS, offers a taxonomy that helps newcomers get oriented before reading individual papers. It is a research resource rather than production software, but for anyone scoping an LLM-enhanced recommendation project, it is a solid way to survey prior work and spot techniques worth trying.