This work proposes a novel Rating-Aware Argument Generation framework designed to produce persuasive arguments aligned with fine-grained rating intensities, and demonstrates that this method is effective in improving rating alignment and mitigating rating drift.
This paper presents a framework that preserves semantics in LLM-based opinion summarization while minimizing token usage and computational cost and demonstrates that this method significantly reduces token usage and computational cost while consistently outperforming traditional AI-based and standard LLM summarization baselines in terms of content coverage, balance, and semantic preservation.
This work proposes the SENSE model, a confidence-aware soft sentiment assignment and a sentiment exchange mechanism to quantify fine-grained preferences and explicitly model sentiment interaction, and employs a confidence-aware soft sentiment assignment and a sentiment exchange mechanism to quantify fine-grained preferences and explicitly model sentiment interaction.
Ying-Jie Chen, Xiang Li, Dong Chen et al.· 0 citations
Obvious performance discrepancies exist across LLMs; high-quality annotations significantly boost downstream classification accuracy, which highlights the importance of selecting competent LLMs for sentiment labeling tasks.
Wenjing Pi, Changxian He· Computers and artificial int...· 0 citations
