5 papers
CoreEval: Automatically Building Contamination-Resilient Datasets with Real-World Knowledge toward Reliable LLM Evaluation
Jingqian Zhao, Bingbing Wang, Geng Tu +5
Data contamination poses a significant challenge to the fairness of LLM evaluations in natural language processing tasks by inadvertently exposing models to test data during traini…
Comprehensive and Efficient Distillation for Lightweight Sentiment Analysis Models
Guangyu Xie, Yice Zhang, Jianzhu Bao +4
Recent efforts leverage knowledge distillation techniques to develop lightweight and practical sentiment analysis models. These methods are grounded in human-written instructions a…
Targeted Distillation for Sentiment Analysis
Yice Zhang, Guangyu Xie, Jingjie Lin +4
This paper explores targeted distillation methods for sentiment analysis, aiming to build compact and practical models that preserve strong and generalizable sentiment analysis cap…
Distilling Fine-grained Sentiment Understanding from Large Language Models
Yice Zhang, Guangyu Xie, Hongling Xu +5
Fine-grained sentiment analysis (FSA) aims to extract and summarize user opinions from vast opinionated text. Recent studies demonstrate that large language models (LLMs) possess e…
DS-ABSA: Dual-Stream Data Synthesis with Label Refinement for Few-Shot Aspect-Based Sentiment Analysis
Hongling Xu, Yice Zhang, Qianlong Wang +1
Recently developed large language models (LLMs) have presented promising new avenues to address data scarcity in low-resource scenarios. In few-shot aspect-based sentiment analysis…