Preference Distillation for Personalized Generative Recommendation

• URL: http://arxiv.org/abs/2407.05033v1
• Date: Sat, 06 Jul 2024 09:58:58 GMT
• Title: Preference Distillation for Personalized Generative Recommendation
• Authors: Jerome Ramos, Bin Wu, Aldo Lipani,
• Abstract summary: We propose a PErsonAlized PrOmpt Distillation (PeaPOD) approach to distill user preferences as personalized soft prompts. Considering the complexities of user preferences in the real world, we maintain a shared set of learnable prompts that are dynamically weighted based on the user's interests. Experimental results on three real-world datasets demonstrate the effectiveness of our PeaPOD model on sequential recommendation, top-n recommendation, and explanation generation tasks.
• Score: 11.27949757550442
• License:
• Abstract: Recently, researchers have investigated the capabilities of Large Language Models (LLMs) for generative recommender systems. Existing LLM-based recommender models are trained by adding user and item IDs to a discrete prompt template. However, the disconnect between IDs and natural language makes it difficult for the LLM to learn the relationship between users. To address this issue, we propose a PErsonAlized PrOmpt Distillation (PeaPOD) approach, to distill user preferences as personalized soft prompts. Considering the complexities of user preferences in the real world, we maintain a shared set of learnable prompts that are dynamically weighted based on the user's interests to construct the user-personalized prompt in a compositional manner. Experimental results on three real-world datasets demonstrate the effectiveness of our PeaPOD model on sequential recommendation, top-n recommendation, and explanation generation tasks.

Related papers

• PersonalLLM: Tailoring LLMs to Individual Preferences [11.717169516971856]
  We present a public benchmark, PersonalLLM, focusing on adapting LLMs to provide maximal benefits for a particular user. We curate open-ended prompts paired with many high-quality answers over which users would be expected to display heterogeneous latent preferences. Our dataset and generated personalities offer an innovative testbed for developing personalization algorithms.
  arXiv  Detail & Related papers  (2024-09-30T13:55:42Z)
• Laser: Parameter-Efficient LLM Bi-Tuning for Sequential Recommendation with Collaborative Information [76.62949982303532]
  We propose a parameter-efficient Large Language Model Bi-Tuning framework for sequential recommendation with collaborative information (Laser) In our Laser, the prefix is utilized to incorporate user-item collaborative information and adapt the LLM to the recommendation task, while the suffix converts the output embeddings of the LLM from the language space to the recommendation space for the follow-up item recommendation. M-Former is a lightweight MoE-based querying transformer that uses a set of query experts to integrate diverse user-specific collaborative information encoded by frozen ID-based sequential recommender systems.
  arXiv  Detail & Related papers  (2024-09-03T04:55:03Z)
• Doing Personal LAPS: LLM-Augmented Dialogue Construction for Personalized Multi-Session Conversational Search [9.243535345193711]
  Our method uses large language models to guide a single human worker in generating personalized dialogues. LAPS can collect large-scale, human-written, multi-session, and multi-domain conversations. Our results show that responses generated explicitly using extracted preferences better match user's actual preferences.
  arXiv  Detail & Related papers  (2024-05-06T13:53:03Z)
• Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts [95.09994361995389]
  Relative Preference Optimization (RPO) is designed to discern between more and less preferred responses derived from both identical and related prompts. RPO has demonstrated a superior ability to align large language models with user preferences and to improve their adaptability during the training process.
  arXiv  Detail & Related papers  (2024-02-12T22:47:57Z)
• User Embedding Model for Personalized Language Prompting [9.472634942498859]
  We introduce a new User Embedding Module (UEM) that efficiently processes user history in free-form text by compressing and representing them as embeddings. Our experiments demonstrate the superior capability of this approach in handling significantly longer histories. The main contribution of this research is to demonstrate the ability to bias language models with user signals represented as embeddings.
  arXiv  Detail & Related papers  (2024-01-10T00:35:52Z)
• Explainable Active Learning for Preference Elicitation [0.0]
  We employ Active Learning (AL) to solve the addressed problem with the objective of maximizing information acquisition with minimal user effort. AL operates for selecting informative data from a large unlabeled set to inquire an oracle to label them. It harvests user feedback (given for the system's explanations on the presented items) over informative samples to update an underlying machine learning (ML) model.
  arXiv  Detail & Related papers  (2023-09-01T09:22:33Z)
• Unlocking the Potential of User Feedback: Leveraging Large Language Model as User Simulator to Enhance Dialogue System [65.93577256431125]
  We propose an alternative approach called User-Guided Response Optimization (UGRO) to combine it with a smaller task-oriented dialogue model. This approach uses LLM as annotation-free user simulator to assess dialogue responses, combining them with smaller fine-tuned end-to-end TOD models. Our approach outperforms previous state-of-the-art (SOTA) results.
  arXiv  Detail & Related papers  (2023-06-16T13:04:56Z)
• Large Language Model Augmented Narrative Driven Recommendations [51.77271767160573]
  Narrative-driven recommendation (NDR) presents an information access problem where users solicit recommendations with verbose descriptions of their preferences and context. NDR lacks abundant training data for models, and current platforms commonly do not support these requests. We use large language models (LLMs) for data augmentation to train NDR models.
  arXiv  Detail & Related papers  (2023-06-04T03:46:45Z)
• Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach [83.62750225073341]
  We consider recommendation as instruction following by large language models (LLMs) We first design a general instruction format for describing the preference, intention, task form and context of a user in natural language. Then we manually design 39 instruction templates and automatically generate a large amount of user-personalized instruction data.
  arXiv  Detail & Related papers  (2023-05-11T17:39:07Z)
• Latent User Intent Modeling for Sequential Recommenders [92.66888409973495]
  Sequential recommender models learn to predict the next items a user is likely to interact with based on his/her interaction history on the platform. Most sequential recommenders however lack a higher-level understanding of user intents, which often drive user behaviors online. Intent modeling is thus critical for understanding users and optimizing long-term user experience.
  arXiv  Detail & Related papers  (2022-11-17T19:00:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.