Multi-Objective Forward Reasoning and Multi-Reward Backward Refinement for Product Review Summarization
Libo Sun, Siyuan Wang, Meng Han, Ruofei Lai, Xinyu Zhang, Xuanjing Huang, Zhongyu Wei
Abstract
Product review summarization aims to generate a concise summary based on product reviews to facilitate purchasing decisions. This intricate task gives rise to three challenges in existing work: factual accuracy, aspect comprehensiveness, and content relevance. In this paper, we first propose an FB-Thinker framework to improve the summarization ability of LLMs with multi-objective forward reasoning and multi-reward backward refinement. To enable LLM with these dual capabilities, we present two Chinese product review summarization datasets, Product-CSum and Product-CSum-Cross, for both instruction-tuning and cross-domain evaluation. Specifically, these datasets are collected via GPT-assisted manual annotations from an online forum and public datasets. We further design an evaluation mechanism Product-Eval, integrating both automatic and human evaluation across multiple dimensions for product summarization. Experimental results show the competitiveness and generalizability of our proposed framework in the product review summarization tasks.- Anthology ID:
- 2024.lrec-main.1043
- Volume:
- Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
- Month:
- May
- Year:
- 2024
- Address:
- Torino, Italia
- Editors:
- Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
- Venues:
- LREC | COLING
- SIG:
- Publisher:
- ELRA and ICCL
- Note:
- Pages:
- 11944–11955
- Language:
- URL:
- https://aclanthology.org/2024.lrec-main.1043
- DOI:
- Cite (ACL):
- Libo Sun, Siyuan Wang, Meng Han, Ruofei Lai, Xinyu Zhang, Xuanjing Huang, and Zhongyu Wei. 2024. Multi-Objective Forward Reasoning and Multi-Reward Backward Refinement for Product Review Summarization. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 11944–11955, Torino, Italia. ELRA and ICCL.
- Cite (Informal):
- Multi-Objective Forward Reasoning and Multi-Reward Backward Refinement for Product Review Summarization (Sun et al., LREC-COLING 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.lrec-main.1043.pdf