# Offline Reasoning for Efficient Recommendation: LLM-Empowered Persona-Profiled Item Indexing

arXiv: https://arxiv.org/abs/2602.21756 · HTML: https://mlsanity.com/paper/2602.21756/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning.
- Builds on 19 of its 54 references that are in the map.
- First posted on arXiv 25 Feb 2026.

## Placed in

- LLM reasoning / [LLM reasoning for recommendation](https://mlsanity.com/lr/llm-reasoning-for-recommendation/)

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

- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents](https://mlsanity.com/paper/2304.09542/) (2023)
- [Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting](https://mlsanity.com/paper/2306.17563/) (2023)
- [Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders](https://mlsanity.com/paper/2403.03952/) (2024)
- [RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!](https://mlsanity.com/paper/2312.02724/) (2023)
- [PALR: Personalization Aware LLMs for Recommendation](https://mlsanity.com/paper/2305.07622/) (2023)
- [Zero-Shot Listwise Document Reranking with a Large Language Model](https://mlsanity.com/paper/2305.02156/) (2023)
- [RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models](https://mlsanity.com/paper/2309.15088/) (2023)
- [LlamaRec: Two-Stage Recommendation using Large Language Models for Ranking](https://mlsanity.com/paper/2311.02089/) (2023)
- [XRec: Large Language Models for Explainable Recommendation](https://mlsanity.com/paper/2406.02377/) (2024)
- [User Modeling and User Profiling: A Comprehensive Survey](https://mlsanity.com/paper/2402.09660/) (2024)
- [Scaling Down, LiTting Up: Efficient Zero-Shot Listwise Reranking with Seq2seq Encoder-Decoder Models](https://mlsanity.com/paper/2312.16098/) (2023)
- [Aligning Large Language Models for Controllable Recommendations](https://mlsanity.com/paper/2403.05063/) (2024)
- [Guided Profile Generation Improves Personalization with LLMs](https://mlsanity.com/paper/2409.13093/) (2024)
- [Pearl: A Review-driven Persona-Knowledge Grounded Conversational Recommendation Dataset](https://mlsanity.com/paper/2403.04460/) (2024)
- [Imagine All The Relevance: Scenario-Profiled Indexing with Knowledge Expansion for Dense Retrieval](https://mlsanity.com/paper/2503.23033/) (2025)
- [Can Large Language Models be Effective Online Opinion Miners?](https://mlsanity.com/paper/2505.15695/) (2025)
- [Towards Unified and Adaptive Cross-Domain Collaborative Filtering via Graph Signal Processing](https://mlsanity.com/paper/2407.12374/) (2024)
- [HIPPO-Video: Simulating Watch Histories with Large Language Models for Personalized Video Highlighting](https://mlsanity.com/paper/2507.16873/) (2025)

## Built on by (most cited first, 1 of 1)

- [Ocean4Rec: Offline LLM-Derived OCEAN Profiles for Request-Time VOD Reranking](https://mlsanity.com/paper/2605.27429/) (2026)

## Abstract (arXiv)

Recent advances in large language models (LLMs) offer new opportunities for recommender systems by capturing the nuanced semantics of user interests and item characteristics through rich semantic understanding and contextual reasoning. In particular, LLMs have been employed as rerankers that reorder candidate items based on inferred user-item relevance. However, these approaches often require expensive online inference-time reasoning, leading to high latency that hampers real-world deployment. In this work, we introduce Persona4Rec, a recommendation framework that performs offline reasoning to construct interpretable persona representations of items, enabling lightweight and scalable real-time inference. In the offline stage, Persona4Rec leverages LLMs to reason over item reviews, inferring diverse user motivations that explain why different types of users may engage with an item; these inferred motivations are materialized as persona representations, providing multiple, human-interpretable views of each item. Unlike conventional approaches that rely on a single item representation, Persona4Rec learns to align user profiles with the most plausible item-side persona through a dedicated encoder, effectively transforming user-item relevance into user-persona relevance. At the online stage, this persona-profiled item index allows fast relevance computation without invoking expensive LLM reasoning. Extensive experiments show that Persona4Rec achieves performance comparable to recent LLM-based rerankers while substantially reducing inference time. Moreover, qualitative analysis confirms that persona representations not only drive efficient scoring but also provide intuitive, review-grounded explanations. These results demonstrate that Persona4Rec offers a practical and interpretable solution for next-generation recommender systems.