# Improve Temporal Awareness of LLMs for Sequential Recommendation

arXiv: https://arxiv.org/abs/2405.02778 · HTML: https://mlsanity.com/paper/2405.02778/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 May 2024.

## Built on by (most cited first, 8 of 8)

- [LLM-based Human Simulations Have Not Yet Been Reliable](https://mlsanity.com/paper/2501.08579/) (2025)
- [Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond](https://mlsanity.com/paper/2410.19744/) (2024)
- [Attention Instruction: Amplifying Attention in the Middle via Prompting](https://mlsanity.com/paper/2406.17095/) (2024)
- [Agentic AI for autonomous anomaly management in complex systems](https://mlsanity.com/paper/2507.15676/) (2025)
- [DELRec: Distilling Sequential Pattern to Enhance LLMs-based Sequential Recommendation](https://mlsanity.com/paper/2406.11156/) (2024)
- [Enhancing Time Awareness in Generative Recommendation](https://mlsanity.com/paper/2509.13957/) (2025)
- [Enhancing Temporal Sensitivity of Large Language Model for Recommendation with Counterfactual Tuning](https://mlsanity.com/paper/2507.03047/) (2025)
- [Using LLMs to Capture Users' Temporal Context for Recommendation](https://mlsanity.com/paper/2508.08512/) (2025)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated impressive zero-shot abilities in solving a wide range of general-purpose tasks. However, it is empirically found that LLMs fall short in recognizing and utilizing temporal information, rendering poor performance in tasks that require an understanding of sequential data, such as sequential recommendation. In this paper, we aim to improve temporal awareness of LLMs by designing a principled prompting framework inspired by human cognitive processes. Specifically, we propose three prompting strategies to exploit temporal information within historical interactions for LLM-based sequential recommendation. Besides, we emulate divergent thinking by aggregating LLM ranking results derived from these strategies. Evaluations on MovieLens-1M and Amazon Review datasets indicate that our proposed method significantly enhances the zero-shot capabilities of LLMs in sequential recommendation tasks.