TS-HINT: Enhancing Semiconductor Time Series Regression Using Attention Hints From Large Language Model Reasoning
By: Jonathan Adam Rico, Nagarajan Raghavan, Senthilnath Jayavelu
Existing data-driven methods rely on the extraction of static features from time series to approximate the material removal rate (MRR) of semiconductor manufacturing processes such as chemical mechanical polishing (CMP). However, this leads to a loss of temporal dynamics. Moreover, these methods require a large amount of data for effective training. In this paper, we propose TS-Hint, a Time Series Foundation Model (TSFM) framework, integrated with chain-of-thought reasoning which provides attention hints during training based on attention mechanism data and saliency data. Experimental results demonstrate the effectiveness of our model in limited data settings via few-shot learning and can learn directly from multivariate time series features.
Similar Papers
Semantic-Enhanced Time-Series Forecasting via Large Language Models
Machine Learning (CS)
Helps computers predict future events better.
Semantic-Enhanced Time-Series Forecasting via Large Language Models
Machine Learning (CS)
Helps computers predict future events better.
Toward Reasoning-Centric Time-Series Analysis
Artificial Intelligence
Helps computers understand why things change.