Beyond Sequences: Distilling Structured Decision Memory for LLM Recommendation
To bridge this gap, we propose MARI (Memory-Augmented Recommendation with Interpretability), which grounds predictions in explicit, structured decision evidence.
Key points
- Despite the adoption of large language models (LLMs) in recommendation systems, prevailing approaches mostly model single-type behaviors (e.g., views or purchases).
- MARI maintains a Decision Memory Bank (DMB) that archives users' past rationales as Structured Decision Memories (SDMs): concise records of goals, constraints, and trade-offs.
- Extensive experiments show MARI significantly outperforms state-of-the-art baselines on standard next-item prediction and a newly introduced Difficult Choice Prediction task, incurring low latency overhead by decoupling memory construction from online inference.
- Qualitative analyses reveal actionable, human-readable insights into user decision-making, marking a concrete step toward reasoning-aware recommendation systems.
Sources (1)
- [1]Beyond Sequences: Distilling Structured Decision Memory for LLM RecommendationarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 08:40 AM
To bridge this gap, we propose MARI (Memory-Augmented Recommendation with Interpretability), which grounds predictions in explicit, structured decision evidence.
Despite the adoption of large language models (LLMs) in recommendation systems, prevailing approaches mostly model single-type behaviors (e.g., views or purchases).
Extractive summary: sentences quoted from the sources.