HADSF: Aspect Aware Semantic Control for Explainable Recommendation

TL;DR

HADSF introduces a two-stage semantic framework that improves review-based recommendation by controlling scope, reducing noise, and linking hallucination to effectiveness, leading to better prediction accuracy across various LLMs.

Contribution

This work presents HADSF, a novel aspect-aware semantic control framework that enhances explainable recommendation by explicitly constraining review extraction and introducing new fidelity metrics.

Findings

HADSF reduces prediction error across multiple LLMs.

Smaller models with HADSF achieve competitive performance.

New metrics effectively measure hallucination fidelity.

Abstract

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