# PRISM: A Framework for Producing Interpretable Political Bias Embeddings with Political-Aware Cross-Encoder

arXiv: https://arxiv.org/abs/2505.24646 · HTML: https://mlsanity.com/paper/2505.24646/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 55 references that are in the map.
- First posted on arXiv 30 May 2025.

## Builds on (most cited first, 30 of 34)

- [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)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [One Embedder, Any Task: Instruction-Finetuned Text Embeddings](https://mlsanity.com/paper/2212.09741/) (2022)
- [We Can Detect Your Bias: Predicting the Political Ideology of News Articles](https://mlsanity.com/paper/2010.05338/) (2020)
- [In Plain Sight: Media Bias Through the Lens of Factual Reporting](https://mlsanity.com/paper/1909.02670/) (2019)
- [Neural Media Bias Detection Using Distant Supervision With BABE -- Bias Annotations By Experts](https://mlsanity.com/paper/2209.14557/) (2022)
- [POLITICS: Pretraining with Same-story Article Comparison for Ideology Prediction and Stance Detection](https://mlsanity.com/paper/2205.00619/) (2022)
- [BioSentVec: creating sentence embeddings for biomedical texts](https://mlsanity.com/paper/1810.09302/) (2018)
- [What Was Written vs. Who Read It: News Media Profiling Using Text Analysis and Social Media Context](https://mlsanity.com/paper/2005.04518/) (2020)
- [SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features](https://mlsanity.com/paper/2206.07023/) (2022)
- [Learning Interpretable Style Embeddings via Prompting LLMs](https://mlsanity.com/paper/2305.12696/) (2023)
- [Multi-view Models for Political Ideology Detection of News Articles](https://mlsanity.com/paper/1809.03485/) (2018)
- [Answer is All You Need: Instruction-following Text Embedding via Answering the Question](https://mlsanity.com/paper/2402.09642/) (2024)
- [Recommenders with a mission: assessing diversity in newsrecommendations](https://mlsanity.com/paper/2012.10185/) (2020)
- [IndiVec: An Exploration of Leveraging Large Language Models for Media Bias Detection with Fine-Grained Bias Indicators](https://mlsanity.com/paper/2402.00345/) (2024)
- [Toward Interpretable Semantic Textual Similarity via Optimal Transport-based Contrastive Sentence Learning](https://mlsanity.com/paper/2202.13196/) (2022)
- [Do We Need Domain-Specific Embedding Models? An Empirical Investigation](https://mlsanity.com/paper/2409.18511/) (2024)
- [Greenback Bears and Fiscal Hawks: Finance is a Jungle and Text Embeddings Must Adapt](https://mlsanity.com/paper/2411.07142/) (2024)
- [Assessing Viewpoint Diversity in Search Results Using Ranking Fairness Metrics](https://mlsanity.com/paper/2010.14531/) (2020)
- [A General Framework for Producing Interpretable Semantic Text Embeddings](https://mlsanity.com/paper/2410.03435/) (2024)
- [Modeling Ideological Salience and Framing in Polarized Online Groups with Graph Neural Networks and Structured Sparsity](https://mlsanity.com/paper/2104.08829/) (2021)

## Built on by (most cited first, 5 of 5)

- [Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning](https://mlsanity.com/paper/2506.08354/) (2025)
- [Measuring Social Bias in Vision-Language Models with Face-Only Counterfactuals from Real Photos](https://mlsanity.com/paper/2601.06931/) (2026)
- [Very Efficient Listwise Multimodal Reranking for Long Documents](https://mlsanity.com/paper/2605.11864/) (2026)
- [LLMs Should Incorporate Explicit Mechanisms for Human Empathy](https://mlsanity.com/paper/2604.10557/) (2026)
- [GGSS: Geodesic-Gated Spherical Steering for Inference-Time Debiasing of Generative Vision-Language Models](https://mlsanity.com/paper/2608.25375/) (2026)

## Abstract (arXiv)

Semantic Text Embedding is a fundamental NLP task that encodes textual content into vector representations, where proximity in the embedding space reflects semantic similarity. While existing embedding models excel at capturing general meaning, they often overlook ideological nuances, limiting their effectiveness in tasks that require an understanding of political bias. To address this gap, we introduce PRISM, the first framework designed to Produce inteRpretable polItical biaS eMbeddings. PRISM operates in two key stages: (1) Controversial Topic Bias Indicator Mining, which systematically extracts fine-grained political topics and their corresponding bias indicators from weakly labeled news data, and (2) Cross-Encoder Political Bias Embedding, which assigns structured bias scores to news articles based on their alignment with these indicators. This approach ensures that embeddings are explicitly tied to bias-revealing dimensions, enhancing both interpretability and predictive power. Through extensive experiments on two large-scale datasets, we demonstrate that PRISM outperforms state-of-the-art text embedding models in political bias classification while offering highly interpretable representations that facilitate diversified retrieval and ideological analysis. The source code is available at https://github.com/dukesun99/ACL-PRISM.