Towards Trustworthy LLM-Based Recommendation via Rationale Integration

• URL: http://arxiv.org/abs/2601.02364v1
• Date: Fri, 07 Nov 2025 08:30:29 GMT
• Title: Towards Trustworthy LLM-Based Recommendation via Rationale Integration
• Authors: Chung Park, Taesan Kim, Hyeongjun Yun, Dongjoon Hong, Junui Hong, Kijung Park, MinCheol Cho, Mira Myong, Jihoon Oh, Min sung Choi,
• Abstract summary: We propose an LLM-based recommender (LLM-Rec) that not only predicts items but also generates logically grounded rationales.<n>Our approach leverages a self-annotated rationale dataset and instruction tuning in a rationale-first format.<n> Experiments on the Fashion and Scientific domains of the Amazon Review dataset demonstrate significant improvements over well-established baselines.
• Score: 1.9124955180802976
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Traditional recommender systems (RS) have been primarily optimized for accuracy and short-term engagement, often overlooking transparency and trustworthiness. Recently, platforms such as Amazon and Instagram have begun providing recommendation rationales to users, acknowledging their critical role in fostering trust and enhancing engagement; however, most existing systems still treat them as post-hoc artifacts. We propose an LLM-based recommender (LLM-Rec) that not only predicts items but also generates logically grounded rationales. Our approach leverages a self-annotated rationale dataset and instruction tuning in a rationale-first format, where the model generates an explanation before outputting the recommended item. By adopting this strategy and representing rationales in a chain-of-thought (CoT) style, LLM-Rec strengthens both interpretability and recommendation performance. Experiments on the Fashion and Scientific domains of the Amazon Review dataset demonstrate significant improvements over well-established baselines. To encourage reproducibility and future research, we publicly release a rationale-augmented recommendation dataset containing user histories, rationales, and recommended items.

Related papers

• Tree of Preferences for Diversified Recommendation [54.183647833064136]
  We study diversified recommendation from a data-bias perspective.<n>Inspired by the outstanding performance of large language models (LLMs) in zero-shot inference leveraging world knowledge, we propose a novel approach.
  arXiv  Detail & Related papers  (2025-12-24T04:13:17Z)
• Do Reviews Matter for Recommendations in the Era of Large Language Models? [8.772803183525284]
  With the advent of large language models (LLMs), the landscape of recommender systems is undergoing a significant transformation.<n>Traditionally, user reviews have served as a critical source of rich, contextual information for enhancing recommendation quality.<n>This paper provides a systematic investigation of the evolving role of text reviews in recommendation by comparing deep learning methods and LLM approaches.
  arXiv  Detail & Related papers  (2025-12-15T04:46:48Z)
• OneRec-Think: In-Text Reasoning for Generative Recommendation [55.53292983432484]
  OneRec-Think is a unified framework that seamlessly integrates dialogue, reasoning, and personalized recommendation.<n>Our proposed "Think-Ahead" architecture enables effective industrial deployment on Kuaishou, achieving a 0.159% gain in APP Stay Time.
  arXiv  Detail & Related papers  (2025-10-13T17:20:13Z)
• Learning to Shop Like Humans: A Review-driven Retrieval-Augmented Recommendation Framework with LLMs [30.748667156183004]
  RevBrowse is a review-driven recommendation framework inspired by the "browse-then-decide" decision process.<n>RevBrowse integrates user reviews into the LLM-based reranking process to enhance its ability to distinguish between candidate items.<n>PrefRAG is a retrieval-augmented module that disentangles user and item representations into structured forms.
  arXiv  Detail & Related papers  (2025-08-31T04:37:43Z)
• Towards Comprehensible Recommendation with Large Language Model Fine-tuning [41.218487308635126]
  We propose a novel Content Understanding from a Collaborative Perspective framework (CURec) for recommendation systems.<n>Curec generates collaborative-aligned content features for more comprehensive recommendations.<n>Experiments on public benchmarks demonstrate the superiority of CURec over existing methods.
  arXiv  Detail & Related papers  (2025-08-11T03:55:31Z)
• R$^2$ec: Towards Large Recommender Models with Reasoning [59.32598867813266]
  We propose R$2$ec, a unified large recommender model with intrinsic reasoning capability.<n>R$2$ec introduces a dual-head architecture that supports both reasoning chain generation and efficient item prediction in a single model.<n>To overcome the lack of annotated reasoning data, we design RecPO, a reinforcement learning framework.
  arXiv  Detail & Related papers  (2025-05-22T17:55:43Z)
• A Survey of Direct Preference Optimization [103.59317151002693]
  Large Language Models (LLMs) have demonstrated unprecedented generative capabilities.<n>Their alignment with human values remains critical for ensuring helpful and harmless deployments.<n>Direct Preference Optimization (DPO) has recently gained prominence as a streamlined alternative.
  arXiv  Detail & Related papers  (2025-03-12T08:45:15Z)
• LLM-based User Profile Management for Recommender System [15.854727020186408]
  PURE builds and maintains evolving user profiles by systematically extracting and summarizing key information from user reviews.<n>We introduce a continuous sequential recommendation task that reflects real-world scenarios by adding reviews over time and updating predictions incrementally.<n>Our experimental results on Amazon datasets demonstrate that PURE outperforms existing LLM-based methods.
  arXiv  Detail & Related papers  (2025-02-20T13:20:19Z)
• RDRec: Rationale Distillation for LLM-based Recommendation [3.7623606729515133]
  This paper proposes a compact model designed to learn rationales generated by a larger language model (LM)<n>By leveraging rationales from reviews related to users and items, RDRec remarkably specifies their profiles for recommendations.<n> Experiments show that RDRec achieves state-of-the-art (SOTA) performance in both top-N and sequential recommendations.
  arXiv  Detail & Related papers  (2024-05-17T07:22:02Z)
• Is ChatGPT Fair for Recommendation? Evaluating Fairness in Large Language Model Recommendation [52.62492168507781]
  We propose a novel benchmark called Fairness of Recommendation via LLM (FaiRLLM) This benchmark comprises carefully crafted metrics and a dataset that accounts for eight sensitive attributes. By utilizing our FaiRLLM benchmark, we conducted an evaluation of ChatGPT and discovered that it still exhibits unfairness to some sensitive attributes when generating recommendations.
  arXiv  Detail & Related papers  (2023-05-12T16:54:36Z)
• Reward Constrained Interactive Recommendation with Natural Language Feedback [158.8095688415973]
  We propose a novel constraint-augmented reinforcement learning (RL) framework to efficiently incorporate user preferences over time. Specifically, we leverage a discriminator to detect recommendations violating user historical preference. Our proposed framework is general and is further extended to the task of constrained text generation.
  arXiv  Detail & Related papers  (2020-05-04T16:23:34Z)

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.