HADSF: Aspect Aware Semantic Control for Explainable Recommendation
Not on the map. Why?
Abstract (arXiv)
Recent advances in large language models (LLMs) promise more effective information extraction for review-based recommender systems, yet current methods still (i) mine free-form reviews without scope control, producing redundant and noisy representations, (ii) lack principled metrics that link LLM hallucination to downstream effectiveness, and (iii) leave the cost-quality trade-off across model scales largely unexplored. We address these gaps with the Hyper-Adaptive Dual-Stage Semantic Framework (HADSF), a two-stage approach that first induces a compact, corpus-level aspect vocabulary via adaptive selection and then performs vocabulary-guided, explicitly constrained extraction of structured aspect-opinion triples. To assess the fidelity of the resulting representations, we introduce Aspect Drift Rate (ADR) and Opinion Fidelity Rate (OFR) and empirically uncover a nonmonotonic relationship between hallucination severity and rating prediction error. Experiments on approximately 3 million reviews across LLMs spanning 1.5B-70B parameters show that, when integrated into standard rating predictors, HADSF yields consistent reductions in prediction error and enables smaller models to achieve competitive performance in representative deployment scenarios. We release code, data pipelines, and metric implementations to support reproducible research on hallucination-aware, LLM-enhanced explainable recommendation. Code is available at https://github.com/niez233/HADSF
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 23 of its 41 references that are in the map. First posted on arXiv 30 Oct 2025.
Builds on
23 of 41 references.
References · 23
- 2014Convolutional Neural Networks for Sentence Classificationcited by 1,127
- 2022Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)cited by 402
- 2023A Survey on Large Language Models for Recommendationcited by 379
- 2023Is ChatGPT a Good Recommender? A Preliminary Studycited by 193
- 2023Recommender Systems in the Era of Large Language Models (LLMs)cited by 189
- 2023LLMRec: Large Language Models with Graph Augmentation for Recommendationcited by 172
- 2023Uncovering ChatGPT's Capabilities in Recommender Systemscited by 161
- 2023Representation Learning with Large Language Models for Recommendationcited by 155
- 2022Towards Universal Sequence Representation Learning for Recommender Systemscited by 121
- 2014Collaborative Deep Learning for Recommender Systemscited by 95
- 2017Joint Deep Modeling of Users and Items Using Reviews for Recommendationcited by 84
- 2022Personalized Prompt Learning for Explainable Recommendationcited by 79
11 more
- 2023Collaborative Large Language Model for Recommender Systemscited by 64
- 2024Leveraging LLM Reasoning Enhances Personalized Recommender Systemscited by 28
- 2024Review-driven Personalized Preference Reasoning with Large Language Models for Recommendationcited by 22
- 2025Reason4Rec: Deliberative User Preference Alignment of Large Language Models for Recommendationcited by 21
- 2018Aspect-Aware Latent Factor Model: Rating Prediction with Ratings and Reviewscited by 19
- 2021Training Large-Scale News Recommenders with Pretrained Language Models in the Loopcited by 18
- 2022A Review-aware Graph Contrastive Learning Framework for Recommendationcited by 18
- 2024Beyond Utility: Evaluating LLM as Recommendercited by 15
- 2023Prompt Tuning Large Language Models on Personalized Aspect Extraction for Recommendationscited by 13
- 2023Understanding Before Recommendation: Semantic Aspect-Aware Review Exploitation via Large Language Modelscited by 13
- 2018Attentive Aspect Modeling for Review-aware Recommendationcited by 12
Built on by
Citing papers per year: 2026: 2.
2 papers.