Controlling the length of generated text can be crucial in various text-generation tasks, including summarization. Existing methods often require complex model alterations, limiting compatibility with pre-trained models. We address these limitations by developing a simple approach for controlling the length of automatic text summaries by increasing the importance of correctly predicting the EOS token in the cross-entropy loss computation. The proposed methodology is agnostic to architecture and decoding algorithms and orthogonal to other inference-time techniques to control the generation length. We tested it with encoder-decoder and modern GPT-style LLMs, and show that this method can control generation length, often without affecting the quality of the summary.
@article{arxiv.2506.05017,
title = {Controlling Summarization Length Through EOS Token Weighting},
author = {Zeno Belligoli and Emmanouil Stergiadis and Eran Fainman and Ilya Gusev},
journal= {arXiv preprint arXiv:2506.05017},
year = {2025}
}