# Using Sentence Embeddings and Semantic Similarity for Seeking Consensus when Assessing Trustworthy AI

arXiv: https://arxiv.org/abs/2208.04608 · HTML: https://mlsanity.com/paper/2208.04608/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 32 references that are in the map.
- First posted on arXiv 9 Aug 2022.

## Builds on (most cited first, 7 of 7)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://mlsanity.com/paper/1708.00055/) (2017)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [Universal Sentence Encoder](https://mlsanity.com/paper/1803.11175/) (2018)
- [Supervised Learning of Universal Sentence Representations from Natural Language Inference Data](https://mlsanity.com/paper/1705.02364/) (2017)

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

- [Specious Sites: Tracking the Spread and Sway of Spurious News Stories at Scale](https://mlsanity.com/paper/2308.02068/) (2023)
- [Partial Mobilization: Tracking Multilingual Information Flows Amongst Russian Media Outlets and Telegram](https://mlsanity.com/paper/2301.10856/) (2023)

## Abstract (arXiv)

Assessing the trustworthiness of artificial intelligence systems requires knowledge from many different disciplines. These disciplines do not necessarily share concepts between them and might use words with different meanings, or even use the same words differently. Additionally, experts from different disciplines might not be aware of specialized terms readily used in other disciplines. Therefore, a core challenge of the assessment process is to identify when experts from different disciplines talk about the same problem but use different terminologies. In other words, the problem is to group problem descriptions (a.k.a. issues) with the same semantic meaning but described using slightly different terminologies. In this work, we show how we employed recent advances in natural language processing, namely sentence embeddings and semantic textual similarity, to support this identification process and to bridge communication gaps in interdisciplinary teams of experts assessing the trustworthiness of an artificial intelligence system used in healthcare.