Yang Gao, Yinghao Li, Heyan Huang, Siyu Miao
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Domain adaptation aims to enable Large Language Models (LLMs) to generalize domain datasets unseen effectively during the training phase. However, factors such as the size of the model parameters and the scale of training data are general influencers and do not reflect the nuances of domain adaptation performance. This paper investigates the fine-grained factors affecting domain adaptation performance, analyzing the specific impact of 'words' in training data on summarization tasks. We propose quantifying dataset learning difficulty as the learning difficulty of generative summarization, which is determined by two indicators: wordbased compression rate and abstraction level. Our experiments conclude that, when considering dataset learning difficulty, the cross-domain overlap and the performance gain in summarization tasks exhibit an approximate linear relationship, which is not directly related to the number of words. Based on this finding, predicting a model's performance on unknown domain datasets is possible without undergoing training. Source code and scripts are available at https://github.com/li-aolong/ Word-Matters.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2406.14828")
get_code_for_paper("2406.14828")
have("2406.14828")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2406.14828.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2406.14828)
Connect an agent — have() is free.