A Hybrid Supervised-LLM Pipeline for Actionable Suggestion Mining in Unstructured Customer Reviews

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Trivedi, Aakash, Upadhyay, Aniket, Narang, Pratik, Kumar, Dhruv, Kumar, Praveen
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918307909599232
author Trivedi, Aakash
Upadhyay, Aniket
Narang, Pratik
Kumar, Dhruv
Kumar, Praveen
author_facet Trivedi, Aakash
Upadhyay, Aniket
Narang, Pratik
Kumar, Dhruv
Kumar, Praveen
contents Extracting actionable suggestions from customer reviews is essential for operational decision-making, yet these directives are often embedded within mixed-intent, unstructured text. Existing approaches either classify suggestion-bearing sentences or generate high-level summaries, but rarely isolate the precise improvement instructions businesses need. We evaluate a hybrid pipeline combining a high-recall RoBERTa classifier trained with a precision-recall surrogate to reduce unrecoverable false negatives with a controlled, instruction-tuned LLM for suggestion extraction, categorization, clustering, and summarization. Across real-world hospitality and food datasets, the hybrid system outperforms prompt-only, rule-based, and classifier-only baselines in extraction accuracy and cluster coherence. Human evaluations further confirm that the resulting suggestions and summaries are clear, faithful, and interpretable. Overall, our results show that hybrid reasoning architectures achieve meaningful improvements fine-grained actionable suggestion mining while highlighting challenges in domain adaptation and efficient local deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2601_19214
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Hybrid Supervised-LLM Pipeline for Actionable Suggestion Mining in Unstructured Customer Reviews
Trivedi, Aakash
Upadhyay, Aniket
Narang, Pratik
Kumar, Dhruv
Kumar, Praveen
Computation and Language
Artificial Intelligence
Extracting actionable suggestions from customer reviews is essential for operational decision-making, yet these directives are often embedded within mixed-intent, unstructured text. Existing approaches either classify suggestion-bearing sentences or generate high-level summaries, but rarely isolate the precise improvement instructions businesses need. We evaluate a hybrid pipeline combining a high-recall RoBERTa classifier trained with a precision-recall surrogate to reduce unrecoverable false negatives with a controlled, instruction-tuned LLM for suggestion extraction, categorization, clustering, and summarization. Across real-world hospitality and food datasets, the hybrid system outperforms prompt-only, rule-based, and classifier-only baselines in extraction accuracy and cluster coherence. Human evaluations further confirm that the resulting suggestions and summaries are clear, faithful, and interpretable. Overall, our results show that hybrid reasoning architectures achieve meaningful improvements fine-grained actionable suggestion mining while highlighting challenges in domain adaptation and efficient local deployment.
title A Hybrid Supervised-LLM Pipeline for Actionable Suggestion Mining in Unstructured Customer Reviews
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2601.19214