ElementCheck: Complexity-Aware Long-Form Text Factuality Evaluation via Sentence Elements

ElementCheck：基于句子要素的复杂性感知长文本事实性评估

Abstract: Existing long-form factuality evaluation relies on the decompose-retrieve-verify pipeline. However, the pipeline suffers from noise from claim decomposition and fixed verification granularity, resulting in unreliable results.

摘要： 现有的长文本事实性评估主要依赖于“分解-检索-验证”（decompose-retrieve-verify）流程。然而，该流程容易受到声明分解过程中的噪声干扰，且验证粒度固定，导致评估结果不可靠。

We propose ElementCheck, a complexity-aware framework that verifies long-form outputs via sentence elements. Instead of uniformly decomposing sentences into atomic sub-claims, ElementCheck extracts entity pairs that are explicitly linked through verifiable connections in the original sentence as elements, and organizes these into an element graph.

我们提出了 ElementCheck，这是一个能够感知复杂性的框架，通过句子要素来验证长文本输出。ElementCheck 不再将句子统一分解为原子级子声明，而是提取在原句中通过可验证连接明确关联的实体对作为“要素”，并将这些要素组织成一个要素图（element graph）。

The graph topology provides a structural signal for estimating sentence complexity, enabling direct verification for simple sentences and targeted element-level refinement and verification for complex ones.

图的拓扑结构为评估句子复杂性提供了结构化信号，使得简单句子可以直接进行验证，而复杂句子则可以进行针对性的要素级细化与验证。

To support fine-grained evaluation, we construct a new benchmark FastFact-Sent by mapping isolated claims from FastFact-Bench back to their source sentences.

为了支持细粒度评估，我们构建了一个新的基准测试 FastFact-Sent，通过将 FastFact-Bench 中的孤立声明映射回其原始句子来实现。

Experiments on FastFact-Sent and two domain-specific benchmarks show ElementCheck consistently improves factuality verification across five backbone models while maintaining a favorable accuracy-cost trade-off.

在 FastFact-Sent 和两个特定领域基准测试上的实验表明，ElementCheck 在五个主干模型上均能持续提升事实性验证效果，同时保持了良好的准确性与成本平衡。

Further analyses demonstrate that complexity-aware verification reduces unnecessary re-verification and maintains stability across different backbones.

进一步分析表明，这种复杂性感知验证减少了不必要的重复验证，并在不同的主干模型中保持了稳定性。