User-Centric Evidence Ranking for Attribution and Fact Verification
This work addresses the challenge of user inefficiency in fact verification systems, offering an incremental improvement by optimizing evidence presentation for better interpretability and alignment with user needs.
The paper tackles the problem of inefficient evidence presentation in fact verification by proposing Evidence Ranking, a task that prioritizes sufficient information early in a ranked list to reduce user reading effort, and demonstrates through a user study that this approach improves verification compared to traditional evidence selection.
Attribution and fact verification are critical challenges in natural language processing for assessing information reliability. While automated systems and Large Language Models (LLMs) aim to retrieve and select concise evidence to support or refute claims, they often present users with either insufficient or overly redundant information, leading to inefficient and error-prone verification. To address this, we propose Evidence Ranking, a novel task that prioritizes presenting sufficient information as early as possible in a ranked list. This minimizes user reading effort while still making all available evidence accessible for sequential verification. We compare two approaches for the new ranking task: one-shot ranking and incremental ranking. We introduce a new evaluation framework, inspired by information retrieval metrics, and construct a unified benchmark by aggregating existing fact verification datasets. Extensive experiments with diverse models show that incremental ranking strategies better capture complementary evidence and that LLM-based methods outperform shallower baselines, while still facing challenges in balancing sufficiency and redundancy. Compared to evidence selection, we conduct a controlled user study and demonstrate that evidence ranking both reduces reading effort and improves verification. This work provides a foundational step toward more interpretable, efficient, and user-aligned information verification systems.