# Interpretable Coreference Resolution Evaluation Using Explicit Semantics

arXiv: https://arxiv.org/abs/2605.10627 · HTML: https://mlsanity.com/paper/2605.10627/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 27 references that are in the map.
- First posted on arXiv 11 May 2026.

## Builds on (most cited first, 7 of 7)

- [An Annotated Dataset of Coreference in English Literature](https://mlsanity.com/paper/1912.01140/) (2019)
- [PreCo: A Large-scale Dataset in Preschool Vocabulary for Coreference Resolution](https://mlsanity.com/paper/1810.09807/) (2018)
- [Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends](https://mlsanity.com/paper/2407.21489/) (2024)
- [Using Automatically Extracted Minimum Spans to Disentangle Coreference Evaluation from Boundary Detection](https://mlsanity.com/paper/1906.06703/) (2019)
- [Using Type Information to Improve Entity Coreference Resolution](https://mlsanity.com/paper/2010.05738/) (2020)
- [Challenges to Evaluating the Generalization of Coreference Resolution Models: A Measurement Modeling Perspective](https://mlsanity.com/paper/2303.09092/) (2023)
- [EnCore: Fine-Grained Entity Typing by Pre-Training Entity Encoders on Coreference Chains](https://mlsanity.com/paper/2305.12924/) (2023)

## Abstract (arXiv)

Coreference resolution is typically evaluated using aggregate statistical metrics such as CoNLL-F1, which measure structural overlap between predicted and gold clusters. While widely used, these metrics offer limited diagnostic insights, penalizing errors without revealing whether a system struggles with specific semantic categories, such as people, locations, or events, and making it difficult to interpret model capabilities or derive actionable improvements. We address this gap by introducing a semantically-enhanced evaluation framework for coreference resolution. Our approach overlays Concept and Named Entity Recognition (CNER) onto coreference outputs, assigning semantic labels to nominal mentions and propagating them to entire coreference clusters. This enables the computation of typed scores aimed at evaluating mention extraction and linking capabilities stratified by semantic class. Across our experiments on OntoNotes, LitBank, and PreCo, we show that our framework uncovers systematic weaknesses that remain obscured by aggregate metrics. Furthermore, we demonstrate that these diagnostics can be used to design targeted, low-cost data augmentation strategies, achieving measurable out-of-domain improvements.