Year: 2025
Type: conference-paper
Abstract: Supervised fine-tuning (SFT) has enabled large language models (LLMs) to exhibit promising performance on various tasks.However, this fine-tuning process only compares current predictions and labels on each sample, yet fails to perceive and understand its error outputs from different degrees, which may potentially produce a large percentage of serious errors.This poses a problem for aspect-based sentiment analysis (ABSA), in that these serious errors bring a greater negative impact than slight ones.Humans tend to compare mistakes to understand the varying degrees of mistakes, thus avoiding major bad decisions.Inspired by this, we propose a simple yet effective framework, which could understand the degree of different errors by learning from comparative error pairs.It utilizes the SFT model to yield multiple outputs on each sample and selects slight and severe errors based on the acceptable scores.Together with the labels, we construct two comparative error pairs and exploit their calibration losses to optimize parameters.We conduct comprehensive experiments on ABSA datasets to demonstrate the effectiveness of our framework over baselines.
Authors: Qianlong Wang, Keyang Ding, Hengxin Gao, Hui Wang, Ruifeng Xu
Institutions: Harbin Institute of Technology, Peng Cheng Laboratory
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Awards: G2230680632, G6312846351, G7349572720
OpenAlex ID: W4412944974