paper-with-me

Papers

Unsupervised Detection of Contextualized Embedding Bias with Application to Ideology

2022-12-14 · Valentin Hofmann, Janet B. Pierrehumbert, Hinrich Schütze

We propose a fully unsupervised method to detect bias in contextualized embeddings. The method leverages the assortative information latently encoded by social networks and combines orthogonality regularization, structured sparsity learning, and graph neural networks to find the embedding subspace capturing this information. As a concrete example, we focus on the phenomenon of ideological bias: we introduce the concept of an ideological subspace, show how it can be found by applying our method to online discussion forums, and present techniques to probe it. Our experiments suggest that the ideological subspace encodes abstract evaluative semantics and reflects changes in the political left-right spectrum during the presidency of Donald Trump.

📄 PDF Abstract BibTeX arXiv:2212.07547

Code (1)

valentinhofmann/unsupervised_bias 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Evaluating the Underlying Gender Bias in Contextualized Word Embeddings

2019-04-18 · WS 2019 8 · Christine Basta, Marta R. Costa-jussà, Noe Casas

Gender bias is highly impacting natural language processing applications. Word embeddings have clearly been proven both to keep and amplify gender biases that are present in current data sources. Recently, contextualized…

SentenceWord Embeddings

Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases

2020-06-06 · Wei Guo, Aylin Caliskan

With the starting point that implicit human biases are reflected in the statistical regularities of language, it is possible to measure biases in English static word embeddings. State-of-the-art neural language models ge…

Bias DetectionSentenceWord Embeddings

Unsupervised Hallucination Detection by Inspecting Reasoning Processes

2025-09-12 · Ponhvoan Srey, Xiaobao Wu, Anh Tuan Luu arxiv

Unsupervised hallucination detection aims to identify hallucinated content generated by large language models (LLMs) without relying on labeled data. While unsupervised methods have gained popularity by eliminating labor…

Towards Detection of Subjective Bias using Contextualized Word Embeddings

2020-02-16 · Tanvi Dadu, Kartikey Pant, Radhika Mamidi

Subjective bias detection is critical for applications like propaganda detection, content recommendation, sentiment analysis, and bias neutralization. This bias is introduced in natural language via inflammatory words an…

Bias DetectionPropaganda detectionSentiment AnalysisWord Embeddings

SenseCluster at SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detection

2020-12-01 · SEMEVAL 2020 · Amaru Cuba Gyllensten, Evangelia Gogoulou, Ariel Ekgren, Magnus Sahlgren

We (Team Skurt) propose a simple method to detect lexical semantic change by clustering contextualized embeddings produced by XLM-R, using K-Means++. The basic idea is that contextualized embeddings that encode the same …

Change DetectionClusteringXLM-R