LCFO: Long Context and Long Form Output Dataset and Benchmarking
This work addresses the need for a controllable evaluation framework for long-form text generation tasks, but it is incremental as it builds on existing benchmarking efforts by adding specific features like varied summary lengths and QA alignments.
The paper tackles the problem of evaluating gradual summarization and summary expansion by introducing the LCFO benchmark, which includes long input documents with multiple summary lengths and QA pairs across domains, and shows that GPT-4o-mini achieves the best human scores among automatic systems, with improvements of ~10% in summarization and ~20% in summary expansion, even surpassing human output in short summaries by ~7%.
This paper presents the Long Context and Form Output (LCFO) benchmark, a novel evaluation framework for assessing gradual summarization and summary expansion capabilities across diverse domains. LCFO consists of long input documents (5k words average length), each of which comes with three summaries of different lengths (20%, 10%, and 5% of the input text), as well as approximately 15 questions and answers (QA) related to the input content. Notably, LCFO also provides alignments between specific QA pairs and corresponding summaries in 7 domains. The primary motivation behind providing summaries of different lengths is to establish a controllable framework for generating long texts from shorter inputs, i.e. summary expansion. To establish an evaluation metric framework for summarization and summary expansion, we provide human evaluation scores for human-generated outputs, as well as results from various state-of-the-art large language models (LLMs). GPT-4o-mini achieves best human scores among automatic systems in both summarization and summary expansion tasks (~ +10% and +20%, respectively). It even surpasses human output quality in the case of short summaries (~ +7%). Overall automatic metrics achieve low correlations with human evaluation scores (~ 0.4) but moderate correlation on specific evaluation aspects such as fluency and attribution (~ 0.6).