Controlled Diversity: Length-optimized Natural Language Generation
This is an incremental improvement for applications requiring precise text length control, such as summarization or user interfaces.
The paper tackled the problem of LLMs' inability to adjust output length based on strict requirements, and found that fine-tuning with augmented data enables models to better adhere to length specifications, though response quality may vary depending on the training data source.
LLMs are not generally able to adjust the length of their outputs based on strict length requirements, a capability that would improve their usefulness in applications that require adherence to diverse user and system requirements. We present an approach to train LLMs to acquire this capability by augmenting existing data and applying existing fine-tuning techniques, which we compare based on the trained models' adherence to the length requirement and overall response quality relative to the baseline model. Our results demonstrate that these techniques can be successfully applied to train LLMs to adhere to length requirements, with the trained models generating texts which better align to the length requirements. Our results indicate that our method may change the response quality when using training data that was not generated by the baseline model. This allows simultaneous alignment to another training objective in certain scenarios, but is undesirable otherwise. Training on a dataset containing the model's own responses eliminates this issue.