# HADSF: Aspect Aware Semantic Control for Explainable Recommendation

arXiv: https://arxiv.org/abs/2510.26994 · HTML: https://mlsanity.com/paper/2510.26994/

## 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 (most cited first, 23 of 23)

- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [A Survey on Large Language Models for Recommendation](https://mlsanity.com/paper/2305.19860/) (2023)
- [Is ChatGPT a Good Recommender? A Preliminary Study](https://mlsanity.com/paper/2304.10149/) (2023)
- [Recommender Systems in the Era of Large Language Models (LLMs)](https://mlsanity.com/paper/2307.02046/) (2023)
- [LLMRec: Large Language Models with Graph Augmentation for Recommendation](https://mlsanity.com/paper/2311.00423/) (2023)
- [Uncovering ChatGPT's Capabilities in Recommender Systems](https://mlsanity.com/paper/2305.02182/) (2023)
- [Representation Learning with Large Language Models for Recommendation](https://mlsanity.com/paper/2310.15950/) (2023)
- [Towards Universal Sequence Representation Learning for Recommender Systems](https://mlsanity.com/paper/2206.05941/) (2022)
- [Collaborative Deep Learning for Recommender Systems](https://mlsanity.com/paper/1409.2944/) (2014)
- [Joint Deep Modeling of Users and Items Using Reviews for Recommendation](https://mlsanity.com/paper/1701.04783/) (2017)
- [Personalized Prompt Learning for Explainable Recommendation](https://mlsanity.com/paper/2202.07371/) (2022)
- [Collaborative Large Language Model for Recommender Systems](https://mlsanity.com/paper/2311.01343/) (2023)
- [Leveraging LLM Reasoning Enhances Personalized Recommender Systems](https://mlsanity.com/paper/2408.00802/) (2024)
- [Review-driven Personalized Preference Reasoning with Large Language Models for Recommendation](https://mlsanity.com/paper/2408.06276/) (2024)
- [Reason4Rec: Deliberative User Preference Alignment of Large Language Models for Recommendation](https://mlsanity.com/paper/2502.02061/) (2025)
- [Aspect-Aware Latent Factor Model: Rating Prediction with Ratings and Reviews](https://mlsanity.com/paper/1802.07938/) (2018)
- [Training Large-Scale News Recommenders with Pretrained Language Models in the Loop](https://mlsanity.com/paper/2102.09268/) (2021)
- [A Review-aware Graph Contrastive Learning Framework for Recommendation](https://mlsanity.com/paper/2204.12063/) (2022)
- [Beyond Utility: Evaluating LLM as Recommender](https://mlsanity.com/paper/2411.00331/) (2024)
- [Prompt Tuning Large Language Models on Personalized Aspect Extraction for Recommendations](https://mlsanity.com/paper/2306.01475/) (2023)
- [Understanding Before Recommendation: Semantic Aspect-Aware Review Exploitation via Large Language Models](https://mlsanity.com/paper/2312.16275/) (2023)
- [Attentive Aspect Modeling for Review-aware Recommendation](https://mlsanity.com/paper/1811.04375/) (2018)

## Built on by (most cited first, 2 of 2)

- [Profiling What Matters: Context-Aware Item Profiles from Large-Scale Metadata for LLM Recommenders](https://mlsanity.com/paper/2608.20801/) (2026)
- [CVE-SAI: Counterfactual Visual Evidence-Guided Selective Attribute Indexing for Risk-Controlled E-commerce Search](https://mlsanity.com/paper/2608.25023/) (2026)

## 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