2 papers
cs.CL2024
The Hyperfitting Phenomenon: Sharpening and Stabilizing LLMs for Open-Ended Text Generation
Fredrik Carlsson, Fangyu Liu, Daniel Ward +2
This paper introduces the counter-intuitive generalization results of overfitting pre-trained large language models (LLMs) on very small datasets. In the setting of open-ended text…
cs.CL2024
Faithful Chart Summarization with ChaTS-Pi
Syrine Krichene, Francesco Piccinno, Fangyu Liu +1
Chart-to-summary generation can help explore data, communicate insights, and help the visually impaired people. Multi-modal generative models have been used to produce fluent summa…