Year: 2024
Type: preprint
Abstract: Through end-to-end training to predict the next token, LLMs have become valuable tools for various tasks. Enhancing their core training in language modeling can improve numerous downstream applications. A successful approach to enhance language modeling uses a separate planning module to predict abstract labels of future sentences and conditions the LM on these predictions. However, this method is non-differentiable, preventing joint end-to-end tuning of the planner with the LM. We propose an effective method to improve this approach by enabling joint fine-tuning of the planner and the LM. We show that a naive way of approximating the gradient of selecting a label via the straight-through estimator is not effective. Instead, we propose to use the predicted label probabilities as mixing weights to condition the LM on a weighted average of label embeddings in a differentiable manner. This not only enables joint fine-tuning of the planner and the LM, but also allows the LM to draw on the full label distribution predicted by the planner, retaining more information. Our experimental results show consistent improvements in perplexity.
Source: arXiv (Cornell University)
Institution: KU Leuven
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Horizon 2020 Framework Programme
Awards: G338431185, G5591719479
OpenAlex ID: W4403578280