# Similarity Analysis of Contextual Word Representation Models

arXiv: https://arxiv.org/abs/2005.01172 · HTML: https://mlsanity.com/paper/2005.01172/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 May 2020.

## Built on by (most cited first, 30 of 54)

- [Do Vision Transformers See Like Convolutional Neural Networks?](https://mlsanity.com/paper/2108.08810/) (2021)
- [Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking](https://mlsanity.com/paper/2402.14811/) (2024)
- [Similarity of Neural Network Models: A Survey of Functional and Representational Measures](https://mlsanity.com/paper/2305.06329/) (2023)
- [Neuron-level Interpretation of Deep NLP Models: A Survey](https://mlsanity.com/paper/2108.13138/) (2021)
- [Similarity and Matching of Neural Network Representations](https://mlsanity.com/paper/2110.14633/) (2021)
- [Representation Topology Divergence: A Method for Comparing Neural Network Representations](https://mlsanity.com/paper/2201.00058/) (2021)
- [Discovering Latent Concepts Learned in BERT](https://mlsanity.com/paper/2205.07237/) (2022)
- [PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition](https://mlsanity.com/paper/2106.05933/) (2021)
- [Do Vision and Language Encoders Represent the World Similarly?](https://mlsanity.com/paper/2401.05224/) (2024)
- [Who's asking? User personas and the mechanics of latent misalignment](https://mlsanity.com/paper/2406.12094/) (2024)
- [Analyzing Encoded Concepts in Transformer Language Models](https://mlsanity.com/paper/2206.13289/) (2022)
- [How transfer learning impacts linguistic knowledge in deep NLP models?](https://mlsanity.com/paper/2105.15179/) (2021)
- [Fine-Tuned Transformers Show Clusters of Similar Representations Across Layers](https://mlsanity.com/paper/2109.08406/) (2021)
- [ModelDiff: A Framework for Comparing Learning Algorithms](https://mlsanity.com/paper/2211.12491/) (2022)
- [Large Language Models Relearn Removed Concepts](https://mlsanity.com/paper/2401.01814/) (2024)
- [Mechanistic?](https://mlsanity.com/paper/2410.09087/) (2024)
- [Looking Right is Sometimes Right: Investigating the Capabilities of Decoder-only LLMs for Sequence Labeling](https://mlsanity.com/paper/2401.14556/) (2024)
- [Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs](https://mlsanity.com/paper/2404.09971/) (2024)
- [Of Non-Linearity and Commutativity in BERT](https://mlsanity.com/paper/2101.04547/) (2021)
- [On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers](https://mlsanity.com/paper/2106.01335/) (2021)
- [Beyond Benchmarks: Evaluating Embedding Model Similarity for Retrieval Augmented Generation Systems](https://mlsanity.com/paper/2407.08275/) (2024)
- [Layers at Similar Depths Generate Similar Activations Across LLM Architectures](https://mlsanity.com/paper/2504.08775/) (2025)
- [What Do Self-Supervised Speech and Speaker Models Learn? New Findings From a Cross Model Layer-Wise Analysis](https://mlsanity.com/paper/2401.17632/) (2024)
- [Representation Projection Invariance Mitigates Representation Collapse](https://mlsanity.com/paper/2205.11603/) (2022)
- [How Familiar Does That Sound? Cross-Lingual Representational Similarity Analysis of Acoustic Word Embeddings](https://mlsanity.com/paper/2109.10179/) (2021)
- [On Robustness of Finetuned Transformer-based NLP Models](https://mlsanity.com/paper/2305.14453/) (2023)
- [Effect of Post-processing on Contextualized Word Representations](https://mlsanity.com/paper/2104.07456/) (2021)
- [On the Effect of Pre-training for Transformer in Different Modality on Offline Reinforcement Learning](https://mlsanity.com/paper/2211.09817/) (2022)
- [Tending Towards Stability: Convergence Challenges in Small Language Models](https://mlsanity.com/paper/2410.11451/) (2024)
- [Towards Measuring Representational Similarity of Large Language Models](https://mlsanity.com/paper/2312.02730/) (2023)

## Abstract (arXiv)

This paper investigates contextual word representation models from the lens of similarity analysis. Given a collection of trained models, we measure the similarity of their internal representations and attention. Critically, these models come from vastly different architectures. We use existing and novel similarity measures that aim to gauge the level of localization of information in the deep models, and facilitate the investigation of which design factors affect model similarity, without requiring any external linguistic annotation. The analysis reveals that models within the same family are more similar to one another, as may be expected. Surprisingly, different architectures have rather similar representations, but different individual neurons. We also observed differences in information localization in lower and higher layers and found that higher layers are more affected by fine-tuning on downstream tasks.