Progress Ratio Embeddings: An Impatience Signal for Robust Length Control in Neural Text Generation
This addresses a specific challenge in text generation for applications requiring controlled output length, but it is incremental as it builds on existing methods.
The paper tackled the problem of precise length control in neural text generation by introducing Progress Ratio Embeddings (PRE), which improved stability and generalization to unseen lengths without degrading text accuracy on news-summarization benchmarks.
Modern neural language models achieve high accuracy in text generation, yet precise control over generation length remains underdeveloped. In this paper, we first investigate a recent length control method based on Reverse Positional Embeddings (RPE) and show its limits when control is requested beyond the training distribution. In particular, using a discrete countdown signal tied to the absolute remaining token count leads to instability. To provide robust length control, we introduce Progress Ratio Embeddings (PRE), as continuous embeddings tied to a trigonometric impatience signal. PRE integrates seamlessly into standard Transformer architectures, providing stable length fidelity without degrading text accuracy under standard evaluation metrics. We further show that PRE generalizes well to unseen target lengths. Experiments on two widely used news-summarization benchmarks validate these findings.