Actionable Advice from Reviews via Mixture of LoRA Experts: A Two-LLM Pipeline for Issue Extraction and Business Recommendations

TL;DR

This paper introduces a modular two-LLM pipeline that extracts issues from reviews and generates actionable recommendations, utilizing a mixture of LoRA experts for efficient specialization and improved performance.

Contribution

It presents a novel two-LLM framework with LoRA expert mixture training for review-to-action generation, enabling effective issue extraction and recommendation generation without full fine-tuning.

Findings

Outperforms prompting-only baselines in actionability and specificity.

Uses synthetic review-issue-advice triples for supervised training.

Achieves favorable efficiency-quality trade-offs across domains.

Abstract

Customer reviews contain detailed, domain specific signals about service failures and user expectations, but converting this unstructured feedback into actionable business decisions remains difficult. We study review-to-action generation: producing concrete, implementable recommendations grounded in review text. We propose a modular two-LLM framework in which an Issue model extracts salient issues and assigns coarse themes, and an Advice model generates targeted operational fixes conditioned on the extracted issue representation. To enable specialization without expensive full fine-tuning, we adapt the Advice model using a mixture of LoRA experts strategy: multiple low-rank adapters are trained and a lightweight gating mechanism performs token-level expert mixing at inference, combining complementary expertise across issue types. We construct synthetic review-issue-advice triples from Yelp reviews (airlines and restaurants) to supervise training, and evaluate recommendations using an eight dimension operational rubric spanning actionability, specificity, feasibility, expected impact, novelty, non-redundancy, bias, and clarity. Across both domains, our approach consistently outperforms prompting-only and single-adapter baselines, yielding higher actionability and specificity while retaining favorable efficiency-quality trade-offs.