# Adapting AlignScore Mertic for Factual Consistency Evaluation of Text in Russian: A Student Abstract

arXiv: https://arxiv.org/abs/2512.06586 · HTML: https://mlsanity.com/paper/2512.06586/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 12 references that are in the map.
- First posted on arXiv 6 Dec 2025.

## Builds on (most cited first, 5 of 5)

- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://mlsanity.com/paper/1704.04683/) (2017)
- [QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization](https://mlsanity.com/paper/2112.08542/) (2021)
- [Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence](https://mlsanity.com/paper/2103.08541/) (2021)
- [Adaptation of Deep Bidirectional Multilingual Transformers for Russian Language](https://mlsanity.com/paper/1905.07213/) (2019)

## Abstract (arXiv)

Ensuring factual consistency in generated text is crucial for reliable natural language processing applications. However, there is a lack of evaluation tools for factual consistency in Russian texts, as existing tools primarily focus on English corpora. To bridge this gap, we introduce AlignRuScore, a comprehensive adaptation of the AlignScore metric for Russian. To adapt the metric, we fine-tuned a RuBERT-based alignment model with task-specific classification and regression heads on Russian and translated English datasets. Our results demonstrate that a unified alignment metric can be successfully ported to Russian, laying the groundwork for robust multilingual factual consistency evaluation. We release the translated corpora, model checkpoints, and code to support further research.