# Domain Divergences: a Survey and Empirical Analysis

arXiv: https://arxiv.org/abs/2010.12198 · HTML: https://mlsanity.com/paper/2010.12198/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2020.

## Built on by (most cited first, 24 of 24)

- [Types of Out-of-Distribution Texts and How to Detect Them](https://mlsanity.com/paper/2109.06827/) (2021)
- [Large Language Models as Annotators: Enhancing Generalization of NLP Models at Minimal Cost](https://mlsanity.com/paper/2306.15766/) (2023)
- [Lost in Transcription, Found in Distribution Shift: Demystifying Hallucination in Speech Foundation Models](https://mlsanity.com/paper/2502.12414/) (2025)
- [Words as Gatekeepers: Measuring Discipline-specific Terms and Meanings in Scholarly Publications](https://mlsanity.com/paper/2212.09676/) (2022)
- [UDApter -- Efficient Domain Adaptation Using Adapters](https://mlsanity.com/paper/2302.03194/) (2023)
- [Measuring the Robustness of NLP Models to Domain Shifts](https://mlsanity.com/paper/2306.00168/) (2023)
- [Experimental Standards for Deep Learning in Natural Language Processing Research](https://mlsanity.com/paper/2204.06251/) (2022)
- [Domain shifts in dermoscopic skin cancer datasets: Evaluation of essential limitations for clinical translation](https://mlsanity.com/paper/2304.06968/) (2023)
- [Adapting to the Long Tail: A Meta-Analysis of Transfer Learning Research for Language Understanding Tasks](https://mlsanity.com/paper/2111.01340/) (2021)
- [How Useful is Continued Pre-Training for Generative Unsupervised Domain Adaptation?](https://mlsanity.com/paper/2401.17514/) (2024)
- [DUQGen: Effective Unsupervised Domain Adaptation of Neural Rankers by Diversifying Synthetic Query Generation](https://mlsanity.com/paper/2404.02489/) (2024)
- [Language Identification of Hindi-English tweets using code-mixed BERT](https://mlsanity.com/paper/2107.01202/) (2021)
- [CDMPP: A Device-Model Agnostic Framework for Latency Prediction of Tensor Programs](https://mlsanity.com/paper/2311.09690/) (2023)
- [Konooz: Multi-domain Multi-dialect Corpus for Named Entity Recognition](https://mlsanity.com/paper/2506.12615/) (2025)
- [Time Will Change Things: An Empirical Study on Dynamic Language Understanding in Social Media Classification](https://mlsanity.com/paper/2210.02857/) (2022)
- [Can Humans Identify Domains?](https://mlsanity.com/paper/2404.01785/) (2024)
- [Exploiting Domain-Specific Parallel Data on Multilingual Language Models for Low-resource Language Translation](https://mlsanity.com/paper/2412.19522/) (2024)
- [Predicting the Success of Domain Adaptation in Text Similarity](https://mlsanity.com/paper/2106.04641/) (2021)
- [Characterizing and Measuring Linguistic Dataset Drift](https://mlsanity.com/paper/2305.17127/) (2023)
- [Label Unification for Cross-Dataset Generalization in Cybersecurity NER](https://mlsanity.com/paper/2507.13870/) (2025)
- [XDomainBench: Diagnosing Reasoning Collapse in High-Dimensional Scientific Knowledge Composition](https://mlsanity.com/paper/2605.14754/) (2026)
- [Divergence-Based Domain Transferability for Zero-Shot Classification](https://mlsanity.com/paper/2302.05735/) (2023)
- [Gradual Fine-Tuning with Graph Routing for Multi-Source Unsupervised Domain Adaptation](https://mlsanity.com/paper/2411.07185/) (2024)
- [Can We Reliably Rank Model Performance across Domains without Labeled Data?](https://mlsanity.com/paper/2510.09519/) (2025)

## Abstract (arXiv)

Domain divergence plays a significant role in estimating the performance of a model in new domains. While there is a significant literature on divergence measures, researchers find it hard to choose an appropriate divergence for a given NLP application. We address this shortcoming by both surveying the literature and through an empirical study. We develop a taxonomy of divergence measures consisting of three classes -- Information-theoretic, Geometric, and Higher-order measures and identify the relationships between them. Further, to understand the common use-cases of these measures, we recognise three novel applications -- 1) Data Selection, 2) Learning Representation, and 3) Decisions in the Wild -- and use it to organise our literature. From this, we identify that Information-theoretic measures are prevalent for 1) and 3), and Higher-order measures are more common for 2). To further help researchers choose appropriate measures to predict drop in performance -- an important aspect of Decisions in the Wild, we perform correlation analysis spanning 130 domain adaptation scenarios, 3 varied NLP tasks and 12 divergence measures identified from our survey. To calculate these divergences, we consider the current contextual word representations (CWR) and contrast with the older distributed representations. We find that traditional measures over word distributions still serve as strong baselines, while higher-order measures with CWR are effective.