Long-Span Question-Answering: Automatic Question Generation and QA-System Ranking via Side-by-Side Evaluation

TL;DR

This paper leverages large language models' long-context capabilities to automatically generate and evaluate reading comprehension questions from entire books, demonstrating improved performance over baseline methods.

Contribution

It introduces a holistic pipeline for automatic question generation, answering, and model evaluation using pairwise comparison and a Bradley-Terry ranking model, advancing long-span comprehension assessment.

Findings

Pairwise model comparison yields more consistent scores.

LLMs show moderate agreement in answer ratings.

Using entire books as context improves comprehension performance.

Abstract

We explore the use of long-context capabilities in large language models to create synthetic reading comprehension data from entire books. Previous efforts to construct such datasets relied on crowd-sourcing, but the emergence of transformers with a context size of 1 million or more tokens now enables entirely automatic approaches. Our objective is to test the capabilities of LLMs to analyze, understand, and reason over problems that require a detailed comprehension of long spans of text, such as questions involving character arcs, broader themes, or the consequences of early actions later in the story. We propose a holistic pipeline for automatic data generation including question generation, answering, and model scoring using an ``Evaluator''. We find that a relative approach, comparing answers between models in a pairwise fashion and ranking with a Bradley-Terry model, provides a more consistent and differentiating scoring mechanism than an absolute scorer that rates answers individually. We also show that LLMs from different model families produce moderate agreement in their ratings. We ground our approach using the manually curated NarrativeQA dataset, where our evaluator shows excellent agreement with human judgement and even finds errors in the dataset. Using our automatic evaluation approach, we show that using an entire book as context produces superior reading comprehension performance compared to baseline no-context (parametric knowledge only) and retrieval-based approaches.