Research map / Large language models / Agents, code and math
GUIDER: Uncertainty Guided Dynamic Re-ranking for Large Language Models Based Recommender Systems
Cai Xu, Xujing Wang, Ziyu Guan, Wei Zhao, Meng Yan
Read the paperCheck your idea against 137,217 papers
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 |
|---|---|---|---|
| add four-quadrant dynamic uncertainty strategy to the base LLM ranker (ablation) | Qwen2.5-7B · Amazon-Grocery | NDCG@20: 0.3608 -> 0.5899 | Improved |
| add data uncertainty (DU) signal (ablation) | GUIDER · Amazon-Grocery | NDCG@20: 0.4729 -> 0.5899 | Improved |
| add model uncertainty (MU) signal (ablation) | GUIDER · Amazon-Grocery | NDCG@20: 0.4932 -> 0.5899 | Improved |
| use GUIDER instead of LLM4Rerank | LLM4Rerank · ML-10M | Recall@20: 0.7389 -> 0.8149 | Improved |
| use GUIDER instead of LLM4Rerank | LLM4Rerank · Amazon-Grocery | NDCG@20: 0.5904 -> 0.5899 | Mixed |
| use Qwen2.5 backbone instead of Mistral for GUIDER (ablation) | GUIDER · ML-10M | NDCG@10: 0.5912 -> 0.6199 | Improved |
| use GUIDER single-pass instead of LLM4Rerank for inference | LLM4Rerank · Time per sample | time (ms): 12339 -> 147.3 | Improved |
| increase user history length from 10 to 20 (ablation) | GUIDER · Amazon-Grocery | NDCG@10 | Improved |
| increase candidate set size (ablation) | GUIDER · Amazon-Grocery | NDCG@10 | Hurt |
Closest papers by meaning
- LLM4RSR: Large Language Models as Data Correctors for Robust Sequential Recommendation (AAAI 2025 · similarity 0.91)
- Language Ranker: A Lightweight Ranking framework for LLM Decoding (NeurIPS 2025 · similarity 0.89)
- LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation (NeurIPS 2024 · similarity 0.89)
- Can LLMs Outshine Conventional Recommenders? A Comparative Evaluation (NeurIPS 2025 · similarity 0.88)
- Re2LLM: Reflective Reinforcement Large Language Model for Session-based Recommendation (AAAI 2025 · similarity 0.87)
- Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations (ICML 2024 · similarity 0.87)
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.
