# Prompt Tuning Large Language Models on Personalized Aspect Extraction for Recommendations

arXiv: https://arxiv.org/abs/2306.01475 · HTML: https://mlsanity.com/paper/2306.01475/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 52 references that are in the map.
- First posted on arXiv 2 Jun 2023.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Multimodal Few-Shot Learning with Frozen Language Models](https://mlsanity.com/paper/2106.13884/) (2021)
- [Explainable Recommendation: A Survey and New Perspectives](https://mlsanity.com/paper/1804.11192/) (2018)
- [Deep Learning based Recommender System: A Survey and New Perspectives](https://mlsanity.com/paper/1707.07435/) (2017)
- [Personalized Prompt Learning for Explainable Recommendation](https://mlsanity.com/paper/2202.07371/) (2022)
- [An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/1906.06906/) (2019)
- [Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction](https://mlsanity.com/paper/1805.04601/) (2018)
- [Learning Multi-granular Quantized Embeddings for Large-Vocab Categorical Features in Recommender Systems](https://mlsanity.com/paper/2002.08530/) (2020)
- [Aspect-Aware Latent Factor Model: Rating Prediction with Ratings and Reviews](https://mlsanity.com/paper/1802.07938/) (2018)
- [Attentive Aspect Modeling for Review-aware Recommendation](https://mlsanity.com/paper/1811.04375/) (2018)
- [Understanding Pre-trained BERT for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2011.00169/) (2020)
- [MMALFM: Explainable Recommendation by Leveraging Reviews and Images](https://mlsanity.com/paper/1811.05318/) (2018)
- [SGAN: An Alternative Training of Generative Adversarial Networks](https://mlsanity.com/paper/1712.02330/) (2017)

## Built on by (most cited first, 13 of 13)

- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [How Can Recommender Systems Benefit from Large Language Models: A Survey](https://mlsanity.com/paper/2306.05817/) (2023)
- [Learning Personalized Alignment for Evaluating Open-ended Text Generation](https://mlsanity.com/paper/2310.03304/) (2023)
- [Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond](https://mlsanity.com/paper/2410.19744/) (2024)
- [ChatDiet: Empowering Personalized Nutrition-Oriented Food Recommender Chatbots through an LLM-Augmented Framework](https://mlsanity.com/paper/2403.00781/) (2024)
- [User Modeling in the Era of Large Language Models: Current Research and Future Directions](https://mlsanity.com/paper/2312.11518/) (2023)
- [A survey on fairness of large language models in e-commerce: progress, application, and challenge](https://mlsanity.com/paper/2405.13025/) (2024)
- [Generative Explore-Exploit: Training-free Optimization of Generative Recommender Systems using LLM Optimizers](https://mlsanity.com/paper/2406.05255/) (2024)
- [A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges](https://mlsanity.com/paper/2507.21117/) (2025)
- [Rehearse With User: Personalized Opinion Summarization via Role-Playing based on Large Language Models](https://mlsanity.com/paper/2503.00449/) (2025)
- [Behavioral Generative Agents for Energy Operations](https://mlsanity.com/paper/2506.12664/) (2025)
- [HADSF: Aspect Aware Semantic Control for Explainable Recommendation](https://mlsanity.com/paper/2510.26994/) (2025)
- [VisualLens: Personalization through Task-Agnostic Visual History](https://mlsanity.com/paper/2411.16034/) (2024)

## Abstract (arXiv)

Existing aspect extraction methods mostly rely on explicit or ground truth aspect information, or using data mining or machine learning approaches to extract aspects from implicit user feedback such as user reviews. It however remains under-explored how the extracted aspects can help generate more meaningful recommendations to the users. Meanwhile, existing research on aspect-based recommendations often relies on separate aspect extraction models or assumes the aspects are given, without accounting for the fact the optimal set of aspects could be dependent on the recommendation task at hand. In this work, we propose to combine aspect extraction together with aspect-based recommendations in an end-to-end manner, achieving the two goals together in a single framework. For the aspect extraction component, we leverage the recent advances in large language models and design a new prompt learning mechanism to generate aspects for the end recommendation task. For the aspect-based recommendation component, the extracted aspects are concatenated with the usual user and item features used by the recommendation model. The recommendation task mediates the learning of the user embeddings and item embeddings, which are used as soft prompts to generate aspects. Therefore, the extracted aspects are personalized and contextualized by the recommendation task. We showcase the effectiveness of our proposed method through extensive experiments on three industrial datasets, where our proposed framework significantly outperforms state-of-the-art baselines in both the personalized aspect extraction and aspect-based recommendation tasks. In particular, we demonstrate that it is necessary and beneficial to combine the learning of aspect extraction and aspect-based recommendation together. We also conduct extensive ablation studies to understand the contribution of each design component in our framework.