arXiv:2611.25151v1 Announce Type: new
Abstract: Powerful generative models including large language and vision models have demonstrated success across a wide range of content generation, editing and manipulation tasks via end-to-end prompt-based generation. However, current assessment of the quality of generative content manipulation remains subjective, limiting scientific understanding of model capabilities. Inspired by rate-distortion theory from Shannon information compression theory, in this work we formalize hierarchical content summarization as an information encoding problem. We design a principled framework to extract the semantic hierarchy of the source content to support quantitative characterization of the rate-distortion trade-off between compression efficiency (rate) against information loss (distortion) during generative content manipulation, which allows us to benchmark various models with respect to performance conditional on rate budget of interest. We demonstrate the use of the framework with empirical experiments on content summarization for long-context question-answering with state-of-the-art large language models, offering new insights into their efficiency and comprehension capabilities. We further demonstrate the use of the semantic hierarchy as guidance for performing effective retrieval augmented generation, showing improved rate-distortion characteristics against current baselines.
Trending
- The Trade-Offs Of Using Apple’s AirPods Max Headphones
- [2611.12466] Prediction with Foundation Models under Deployment Budgets
- A tale of two Nvidias
- What’s New With Apple’s Latest Siri Remote, And Does Your Old Apple TV Support It?
- [2611.26104] How Network Topology and Data Heterogeneity Shape Decentralized Learning: A Spectral Analysis
- Here’s How Much A Sony Walkman Cost In 1980 Vs. 2026
- [2610.32678] Probing the limits of materials design via a comprehensive crystal database of 14.6 million structures with 140 properties
- Discs Vs. Disks: What’s The Difference?
