# Global Explainability of BERT-Based Evaluation Metrics by Disentangling along Linguistic Factors

arXiv: https://arxiv.org/abs/2110.04399 · HTML: https://mlsanity.com/paper/2110.04399/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 55 references that are in the map.
- First posted on arXiv 8 Oct 2021.

## Builds on (most cited first, 30 of 38)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://mlsanity.com/paper/1708.00055/) (2017)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [Language-agnostic BERT Sentence Embedding](https://mlsanity.com/paper/2007.01852/) (2020)
- [Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation](https://mlsanity.com/paper/2004.09813/) (2020)
- [BERT-ATTACK: Adversarial Attack Against BERT Using BERT](https://mlsanity.com/paper/2004.09984/) (2020)
- [What you can cram into a single vector: Probing sentence embeddings for linguistic properties](https://mlsanity.com/paper/1805.01070/) (2018)
- [Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond](https://mlsanity.com/paper/1812.10464/) (2018)
- [MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance](https://mlsanity.com/paper/1909.02622/) (2019)
- [PAWS: Paraphrase Adversaries from Word Scrambling](https://mlsanity.com/paper/1904.01130/) (2019)
- [Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection](https://mlsanity.com/paper/2004.10643/) (2020)
- [Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks](https://mlsanity.com/paper/1608.04207/) (2016)
- [A Survey of the State of Explainable AI for Natural Language Processing](https://mlsanity.com/paper/2010.00711/) (2020)
- [Multilingual Universal Sentence Encoder for Semantic Retrieval](https://mlsanity.com/paper/1907.04307/) (2019)
- [Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics](https://mlsanity.com/paper/2006.06264/) (2020)
- [Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance?](https://mlsanity.com/paper/2005.00719/) (2020)
- [Multilingual Alignment of Contextual Word Representations](https://mlsanity.com/paper/2002.03518/) (2020)
- [BLEU might be Guilty but References are not Innocent](https://mlsanity.com/paper/2004.06063/) (2020)
- [Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems](https://mlsanity.com/paper/1903.11508/) (2019)
- [Scientific Credibility of Machine Translation Research: A Meta-Evaluation of 769 Papers](https://mlsanity.com/paper/2106.15195/) (2021)
- [SUPERT: Towards New Frontiers in Unsupervised Evaluation Metrics for Multi-Document Summarization](https://mlsanity.com/paper/2005.03724/) (2020)
- [SBERT-WK: A Sentence Embedding Method by Dissecting BERT-based Word Models](https://mlsanity.com/paper/2002.06652/) (2020)

## Built on by (most cited first, 25 of 25)

- [Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text](https://mlsanity.com/paper/2202.06935/) (2022)
- [On the Blind Spots of Model-Based Evaluation Metrics for Text Generation](https://mlsanity.com/paper/2212.10020/) (2022)
- [Multi-Objective Hyperparameter Optimization in Machine Learning -- An Overview](https://mlsanity.com/paper/2206.07438/) (2022)
- [DiscoScore: Evaluating Text Generation with BERT and Discourse Coherence](https://mlsanity.com/paper/2201.11176/) (2022)
- [DEMETR: Diagnosing Evaluation Metrics for Translation](https://mlsanity.com/paper/2210.13746/) (2022)
- [SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features](https://mlsanity.com/paper/2206.07023/) (2022)
- [ExPerT: Effective and Explainable Evaluation of Personalized Long-Form Text Generation](https://mlsanity.com/paper/2501.14956/) (2025)
- [The Eval4NLP 2023 Shared Task on Prompting Large Language Models as Explainable Metrics](https://mlsanity.com/paper/2310.19792/) (2023)
- [MENLI: Robust Evaluation Metrics from Natural Language Inference](https://mlsanity.com/paper/2208.07316/) (2022)
- [NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklist](https://mlsanity.com/paper/2305.08566/) (2023)
- [USCORE: An Effective Approach to Fully Unsupervised Evaluation Metrics for Machine Translation](https://mlsanity.com/paper/2202.10062/) (2022)
- [Towards Explainable Evaluation Metrics for Natural Language Generation](https://mlsanity.com/paper/2203.11131/) (2022)
- [Towards Explainable Evaluation Metrics for Machine Translation](https://mlsanity.com/paper/2306.13041/) (2023)
- [Explainability in Practice: A Survey of Explainable NLP Across Various Domains](https://mlsanity.com/paper/2502.00837/) (2025)
- [Layer or Representation Space: What makes BERT-based Evaluation Metrics Robust?](https://mlsanity.com/paper/2209.02317/) (2022)
- [FastKASSIM: A Fast Tree Kernel-Based Syntactic Similarity Metric](https://mlsanity.com/paper/2203.08299/) (2022)
- [Description-Based Text Similarity](https://mlsanity.com/paper/2305.12517/) (2023)
- [Towards explainable evaluation of language models on the semantic similarity of visual concepts](https://mlsanity.com/paper/2209.03723/) (2022)
- [EffEval: A Comprehensive Evaluation of Efficiency for MT Evaluation Metrics](https://mlsanity.com/paper/2209.09593/) (2022)
- [PromptOptMe: Error-Aware Prompt Compression for LLM-based MT Evaluation Metrics](https://mlsanity.com/paper/2412.16120/) (2024)
- [Onco-Retriever: Generative Classifier for Retrieval of EHR Records in Oncology](https://mlsanity.com/paper/2404.06680/) (2024)
- [Beyond N-Grams: Rethinking Evaluation Metrics and Strategies for Multilingual Abstractive Summarization](https://mlsanity.com/paper/2507.08342/) (2025)
- [LexChronos: An Agentic Framework for Structured Event Timeline Extraction in Indian Jurisprudence](https://mlsanity.com/paper/2603.01651/) (2026)
- [DeMeVa at LeWiDi-2025: Modeling Perspectives with In-Context Learning and Label Distribution Learning](https://mlsanity.com/paper/2509.09524/) (2025)
- [Parametric Knowledge in RAG-SFT for Domain-Specific Document Generation](https://mlsanity.com/paper/2603.23047/) (2026)

## Abstract (arXiv)

Evaluation metrics are a key ingredient for progress of text generation systems. In recent years, several BERT-based evaluation metrics have been proposed (including BERTScore, MoverScore, BLEURT, etc.) which correlate much better with human assessment of text generation quality than BLEU or ROUGE, invented two decades ago. However, little is known what these metrics, which are based on black-box language model representations, actually capture (it is typically assumed they model semantic similarity). In this work, we use a simple regression based global explainability technique to disentangle metric scores along linguistic factors, including semantics, syntax, morphology, and lexical overlap. We show that the different metrics capture all aspects to some degree, but that they are all substantially sensitive to lexical overlap, just like BLEU and ROUGE. This exposes limitations of these novelly proposed metrics, which we also highlight in an adversarial test scenario.