Leveraging Large Language Models for Sequential Recommendation (RecSys 2023)
Overview
This entry indexes the academic paper "Leveraging Large Language Models for Sequential Recommendation", presented at RecSys 2023.
| Field | Detail | |-------|--------| | Venue | RecSys 2023 | | Source | https://dl.acm.org/doi/abs/10.1145/3604915.3610639 | | Type | Academic paper | | Categories | Recommender Engines, Sequential Recommendation |
> Note: The forum post is largely a template entry. Specific experimental results and method details should be verified against the original PDF at the ACM link above.
Key points
- The paper explores applying large language models (LLMs) to sequential recommendation, a core topic in modern recommender systems research.
- Contextual motivation: traditional recommendation pipelines split retrieval, ranking, and generation into separate stages, which struggles to meet LLM-era demands for natural-language interaction, multi-hop reasoning, and up-to-date knowledge.
- The work is positioned at the intersection of recommendation and large-scale search/personalization systems, addressing how responsibilities between retrieval, ranking, generation, and tool use should be redistributed in the LLM era.
- Architecture: Cascade retrieve → rerank → generate remains mainstream, but agentic paradigms are making retrieval count and strategy themselves learnable.
- Data: High-quality instruction data and click/session logs are both critical; synthetic data must guard against knowledge leakage and distribution shift.
- Evaluation: The gap between offline metrics and online satisfaction is widening; LLM-as-judge should be cross-validated with human evaluation.
- Productization: Latency, cost, explainability, and safety are hard constraints for industrial deployment — academic benchmarks alone are insufficient.
- 360Brew: A Decoder-only Foundation Model for Personalized Ranking
- Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers
- Augmenting Netflix Search with In-Session Adapted Recommendations
- Bridging Language and Items for Retrieval and Recommendation
- Data-efficient Fine-tuning for LLM-based Recommendation, SIGIR 2024
- DiffKG: Knowledge Graph Diffusion Model for Recommendation, WSDM 2024
- Original paper: Leveraging Large Language Models for Sequential Recommendation, RecSys 2023. https://dl.acm.org/doi/abs/10.1145/3604915.3610639
Broader context from the entry
Research trends discussed
Engineering deployment checklist
| Item | Question | Suggestion | |------|----------|------------| | Data | Does training/indexing contain PII? How are versions managed? | Partitioned indexes, anonymization, rollback-capable embedding versions | | Latency | What is the p99 budget? How many retrieval steps? | Cascade + early stopping, caching hot queries, async reranking | | Quality | Do offline gains translate to online CTR/satisfaction? | Interleaving experiments, human audit samples, citation verification | | Safety | Does open retrieval introduce poisoning/bias? | Source whitelists, adversarial detection, output filtering | | Cost | Token and GPU cost per query? | Route to smaller models, distillation, hybrid sparse+dense retrieval |
Glossary
| Term | Meaning | |------|---------| | IR | Information Retrieval | | RAG | Retrieval-Augmented Generation | | LTR | Learning to Rank | | nDCG | Normalized Discounted Cumulative Gain, a ranking quality metric | | Agentic Search | Modeling search as sequential decision-making and tool invocation | | Gen-IR | Generative Information Retrieval |