# Reconstruction Probing

arXiv: https://arxiv.org/abs/2212.10792 · HTML: https://mlsanity.com/paper/2212.10792/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 39 references that are in the map.
- First posted on arXiv 21 Dec 2022.

## Builds on (most cited first, 22 of 22)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [What do you learn from context? Probing for sentence structure in contextualized word representations](https://mlsanity.com/paper/1905.06316/) (2019)
- [Causal Abstractions of Neural Networks](https://mlsanity.com/paper/2106.02997/) (2021)
- [Assessing BERT's Syntactic Abilities](https://mlsanity.com/paper/1901.05287/) (2019)
- [Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT](https://mlsanity.com/paper/2004.14786/) (2020)
- [Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information](https://mlsanity.com/paper/1808.08079/) (2018)
- [Do Attention Heads in BERT Track Syntactic Dependencies?](https://mlsanity.com/paper/1911.12246/) (2019)
- [Investigating BERT's Knowledge of Language: Five Analysis Methods with NPIs](https://mlsanity.com/paper/1909.02597/) (2019)
- [Let's Play Mono-Poly: BERT Can Reveal Words' Polysemy Level and Partitionability into Senses](https://mlsanity.com/paper/2104.14694/) (2021)
- [Spying on your neighbors: Fine-grained probing of contextual embeddings for information about surrounding words](https://mlsanity.com/paper/2005.01810/) (2020)
- [Picking BERT's Brain: Probing for Linguistic Dependencies in Contextualized Embeddings Using Representational Similarity Analysis](https://mlsanity.com/paper/2011.12073/) (2020)
- [Probing for Bridging Inference in Transformer Language Models](https://mlsanity.com/paper/2104.09400/) (2021)
- [Probing for Constituency Structure in Neural Language Models](https://mlsanity.com/paper/2204.06201/) (2022)
- [Putting Words in BERT's Mouth: Navigating Contextualized Vector Spaces with Pseudowords](https://mlsanity.com/paper/2109.11491/) (2021)
- [Effect of Post-processing on Contextualized Word Representations](https://mlsanity.com/paper/2104.07456/) (2021)

## Built on by (most cited first, 2 of 2)

- [Probing the Category of Verbal Aspect in Transformer Language Models](https://mlsanity.com/paper/2406.02335/) (2024)
- [The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Models](https://mlsanity.com/paper/2601.19926/) (2026)

## Abstract (arXiv)

We propose reconstruction probing, a new analysis method for contextualized representations based on reconstruction probabilities in masked language models (MLMs). This method relies on comparing the reconstruction probabilities of tokens in a given sequence when conditioned on the representation of a single token that has been fully contextualized and when conditioned on only the decontextualized lexical prior of the model. This comparison can be understood as quantifying the contribution of contextualization towards reconstruction -- the difference in the reconstruction probabilities can only be attributed to the representational change of the single token induced by contextualization. We apply this analysis to three MLMs and find that contextualization boosts reconstructability of tokens that are close to the token being reconstructed in terms of linear and syntactic distance. Furthermore, we extend our analysis to finer-grained decomposition of contextualized representations, and we find that these boosts are largely attributable to static and positional embeddings at the input layer.