Information-Theoretic Distillation for Reference-less Summarization

• Published in: arXiv.org
• Main Authors: Jung, Jaehun, Lu, Ximing, Jiang, Liwei, Brahman, Faeze, West, Peter, Pang Wei Koh, Choi, Yejin
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 19.08.2024
• Subjects: Chatbots; Controllability; Distillation; Information theory; Large language models; Scale models; Teachers
• ISSN: 2331-8422

The current winning recipe for automatic summarization is using proprietary large-scale language models (LLMs) such as ChatGPT as is, or imitation learning from them as teacher models. While increasingly ubiquitous dependence on such large-scale language models is convenient, there remains an important question of whether small-scale models could have achieved competitive results, if we were to seek an alternative learning method -- that allows for a more cost-efficient, controllable, yet powerful summarizer. We present InfoSumm, a novel framework to distill a powerful summarizer based on the information-theoretic objective for summarization, without relying on either the LLM's capability or human-written references. To achieve this, we first propose a novel formulation of the desiderata of summarization (saliency, faithfulness and brevity) through the lens of mutual information between the original document and the summary. Based on this formulation, we start off from Pythia-2.8B as the teacher model, which is not yet capable of summarization, then self-train the model to optimize for the information-centric measures of ideal summaries. Distilling from the improved teacher, we arrive at a compact but powerful summarizer with only 568M parameters that performs competitively against ChatGPT, without ever relying on ChatGPT's capabilities. Extensive analysis demonstrates that our approach outperforms in-domain supervised models in human evaluation, let alone state-of-the-art unsupervised methods, and wins over ChatGPT in controllable summarization.