6 papers
JsonTuning: Towards Generalizable, Robust, and Controllable Instruction Tuning
Chang Gao, Wenxuan Zhang, Guizhen Chen +1
Instruction tuning is vital for enhancing the performance of large language models (LLMs), but existing text-to-text methods, referred to as TextTuning, struggle with issues such a…
Pruning General Large Language Models into Customized Expert Models
Yirao Zhao, Guizhen Chen, Kenji Kawaguchi +2
Large language models (LLMs) have revolutionized natural language processing, yet their substantial model sizes often require substantial computational resources. To preserve compu…
FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving
Guizhen Chen, Weiwen Xu, Hao Zhang +6
Many challenging reasoning tasks require not just rapid, intuitive responses, but a more deliberate, multi-step approach. Recent progress in large language models (LLMs) highlights…
How do Large Language Models Handle Multilingualism?
Yiran Zhao, Wenxuan Zhang, Guizhen Chen +2
Large language models (LLMs) have demonstrated impressive capabilities across diverse languages. This study explores how LLMs handle multilingualism. Based on observed language rat…
Domain-Expanded ASTE: Rethinking Generalization in Aspect Sentiment Triplet Extraction
Yew Ken Chia, Hui Chen, Wei Han +4
Aspect Sentiment Triplet Extraction (ASTE) is a challenging task in sentiment analysis, aiming to provide fine-grained insights into human sentiments. However, existing benchmarks…
Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths
Yew Ken Chia, Guizhen Chen, Weiwen Xu +3
Advanced models such as OpenAI o1 exhibit impressive problem-solving capabilities through step-by-step reasoning. However, they may still falter on more complex problems, making er…