Research map / Large language models / Instruction and fine-tuning
RecCocktail: A Generalizable and Efficient Framework for LLM-Based Recommendation
Min Hou, Chenxi Bai, Le Wu, Hao Liu, Kai Zhang, Weiwen Liu, Richang Hong, Ruiming Tang, Meng Wang
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| merge domain-general and domain-specific LoRA (entropy-guided) instead of domain-specific only (ablation) | RecCocktail (Qwen2-7B) · Beauty warm-start | NDCG@1: 0.4079 -> 0.4132 | Improved |
| merge in domain-specific LoRA with base spirit instead of general only (ablation) | RecCocktail (Qwen2-7B) · Beauty warm-start | NDCG@1: 0.3081 -> 0.4132 | Improved |
| merge in base spirit LoRA instead of specific only (ablation) | RecCocktail (Qwen2-7B) · Beauty cold-start | NDCG@1: 0.1603 -> 0.1825 | Improved |
| entropy-guided adaptive merging instead of simple weight average (ablation) | RecCocktail (Qwen2-7B) · MovieLens-1M cold-start | NDCG@1: 0.1636 -> 0.1818 | Improved |
| entropy-guided adaptive merging instead of simple weight average (ablation) | RecCocktail (Qwen2-7B) · Beauty warm-start | NDCG@1: 0.3722 -> 0.4132 | Improved |
| weight average merging instead of domain-specific LoRA only (ablation) | RecCocktail-WA · Sports warm-start | NDCG@1: 0.3735 -> 0.3410 | Hurt |
| merge LoRAs instead of second-round fine-tuning of base LoRA (ablation) | RecCocktail (Qwen2-7B) · MovieLens-1M few-shot 10% warm | NDCG@1: 0.0704 -> 0.5353 | Improved |
| use RecCocktail instead of TALLRec in few-shot | RecCocktail (Qwen2-7B) · MovieLens-1M few-shot 10% warm | NDCG@1: 0.3957 -> 0.5353 | Improved |
| swap backbone to Llama-3.1-8B and merge (ablation) | RecCocktail (Llama-3.1-8B) · Sports cold-start | NDCG@1: 0.1538 -> 0.1587 | Improved |
| use more unlabeled test samples (50 vs 100 vs 200) for entropy merging (ablation) | RecCocktail · Beauty/Toys/Sports | NDCG@1 | No clear effect |
Closest papers by meaning
- Can LLMs Outshine Conventional Recommenders? A Comparative Evaluation (NeurIPS 2025 · similarity 0.92)
- SLMRec: Distilling Large Language Models into Small for Sequential Recommendation (ICLR 2025 · similarity 0.90)
- LLMRG: Improving Recommendations through Large Language Model Reasoning Graphs (AAAI 2024 · similarity 0.90)
- CoRA: Collaborative Information Perception by Large Language Model’s Weights for Recommendation (AAAI 2025 · similarity 0.90)
- Improving LLMs for Recommendation with Out-Of-Vocabulary Tokens (ICML 2025 · similarity 0.90)
- LLM4RSR: Large Language Models as Data Correctors for Robust Sequential Recommendation (AAAI 2025 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
