XFBoost: Improving Text Generation with Controllable Decoders (2202.08124v1)

Abstract: Multimodal conditionality in transformer-based natural LLMs has demonstrated state-of-the-art performance in the task of product description generation. Recent approaches condition a LLM on one or more images and other textual metadata to achieve near-human performance for describing products from e-commerce stores. However, generated descriptions may exhibit degrees of inaccuracy or even contradictory claims relative to the inputs of a given product. In this paper, we propose a controllable language generation framework called Extract-Finetune-Boost (XFBoost), which addresses the problem of inaccurate low-quality inference. By using visual semantic attributes as constraints at the decoding stage of the generation process and finetuning the LLM with policy gradient techniques, the XFBoost framework is found to produce significantly more descriptive text with higher image relevancy, outperforming baselines and lowering the frequency of factually inaccurate descriptions. We further demonstrate the application of XFBoost to online learning wherein human-in-the-loop critics improve LLMs with active feedback.