Safety
ITL: Interpretable Document Alignment with Structured Reference Frameworks
arXiv:2608.27031v1 Announce Type: new Abstract: Measuring alignment between documents and structured reference frameworks requires identifying conceptual evidence distributed throughout the text and r
arXiv:2608.27031v1 Announce Type: new Abstract: Measuring alignment between documents and structured reference frameworks requires identifying conceptual evidence distributed throughout the text and reporting it through measures that are quantitative, interpretable, and traceable. Many commonly used retrieval and classification approaches return either pairwise similarity scores or one or more class labels, whereas fewer methods provide concept-level scores that are directly traceable to the terminological evidence supporting them. We present Intelligent Target Locator (ITL), a domain-agnostic and language-portable methodology that estimates the affinity between the textual units of a target document and the concepts defined in a Structured Reference Document (SRD). From the SRD, ITL induces concept-specific terminological profiles built from independent terms, bigrams, trigrams, and co-occurrences. Each term is assigned an importance weight that combines concept membership, term-type specificity and inter-concept discriminability. The output is a textual-unit--concept affinity matrix that can be aggregated at different levels of granularity. We conduct an internal consistency assessment using the 17 Sustainable Development Goals (SDGs), evaluating each official goal statement against the SRD induced from the same set of descriptors. Every statement reached its highest affinity with the corresponding concept, and the mean affinity across the remaining concepts stayed marginal relative to the mean reference affinity. This separation indicates that ITL distinguishes the conceptual profiles of the framework. ITL thus offers a general basis for quantifying document alignment with structured frameworks while keeping each result traceable to the terminological evidence that supports it.
Related
- Scaling Unsupervised Word Alignment to Documents via Structural Constraints
- Beyond Topical Similarity: Contrastive Evidence Retrieval with Interpretable Attention Alignment in RAG
- Hallucination Span Detection with Input-Side Evidence Alignment
- BoundRL: Efficient Structured Text Segmentation through Reinforced Boundary Generation
Source: arXiv cs.CL | 2026-08-28