Quality Estimation (QE) is essential for assessing machine translation quality in reference-less settings, particularly for domain-specific and low-resource language scenarios. In this paper, we investigate sentence-level QE for English to Indic machine translation across four domains (Healthcare, Legal, Tourism, and General) and five language pairs. We systematically compare zero-shot, few-shot, and guideline-anchored prompting across selected closed-weight and open-weight LLMs. Findings indicate that while closed-weight models achieve strong performance via prompting alone, prompt-only approaches remain fragile for open-weight models, especially in high-risk domains. To address this, we adopt ALOPE, a framework for LLM-based QE that uses Low-Rank Adaptation with regression heads attached to selected intermediate Transformer layers. We also extend ALOPE with recently proposed Low-Rank Multiplicative Adaptation (LoRMA). Our results show that intermediate-layer adaptation consistently improves QE performance, with gains in semantically complex domains, indicating a path toward more robust QE in practical scenarios. We release code and domain-specific QE datasets publicly to support further research.

翻译：质量评估(QE)在无参考译文的场景下对机器翻译质量进行评判至关重要，尤其对于领域特定和低资源语言场景。本文针对英语到印度语系语言的机器翻译，在四个领域（医疗健康、法律、旅游和通用领域）及五组语言对上研究了句子级质量评估。我们系统比较了在选定的闭源权重与开源权重大语言模型(LLM)上采用零样本、少样本及基于指导原则的提示方法的效果。研究发现，虽然闭源权重模型仅通过提示即可获得强劲性能，但纯提示方法对于开源权重模型而言仍显脆弱，尤其在风险较高的领域。为解决此问题，我们采用ALOPE框架——一种基于大语言模型的质量评估方法，该方法将低秩适配与回归头结合，并附加到选定的Transformer中间层。我们还使用近期提出的低秩乘性适配(LoRMA)对ALOPE进行了扩展。结果表明，中间层适配能持续提升质量评估性能，在语义复杂的领域收益尤为显著，这为实际场景中实现更鲁棒的质量评估指明了一条路径。我们公开了代码和领域特定的质量评估数据集以支持进一步研究。