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

• URL: http://arxiv.org/abs/2505.24646v1
• Date: Fri, 30 May 2025 14:31:53 GMT
• Title: PRISM: A Framework for Producing Interpretable Political Bias Embeddings with Political-Aware Cross-Encoder
• Authors: Yiqun Sun, Qiang Huang, Anthony K. H. Tung, Jun Yu,
• Abstract summary: PRISM is a framework to produce inteRpretable polItical biaS eMbeddings.<n>It extracts political topics and their corresponding bias indicators from weakly labeled news data.<n>It then assigns structured bias scores to news articles based on their alignment with these indicators.
• Score: 17.00358234728804
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• The Medium Is Not the Message: Deconfounding Text Embeddings via Linear Concept Erasure [91.01653854955286]
  Embedding-based similarity metrics can be influenced by spurious attributes like the text's source or language.<n>This paper shows that a debiasing algorithm that removes information about observed confounders from the encoder representations substantially reduces these biases at a minimal computational cost.
  arXiv  Detail & Related papers  (2025-07-01T23:17:12Z)
• BiasLab: Toward Explainable Political Bias Detection with Dual-Axis Annotations and Rationale Indicators [0.0]
  BiasLab is a dataset of 300 political news articles annotated for perceived ideological bias.<n>Each article is labeled by crowdworkers along two independent scales, assessing sentiment toward the Democratic and Republican parties.<n>We quantify inter-annotator agreement, analyze misalignment with source-level outlet bias, and organize the resulting labels into interpretable subsets.
  arXiv  Detail & Related papers  (2025-05-21T23:50:42Z)
• Mitigating Gender Bias in Contextual Word Embeddings [1.208453901299241]
  We propose a novel objective function for Lipstick(Masked-Language Modeling) which largely mitigates the gender bias in contextual embeddings. We also propose new methods for debiasing static embeddings and provide empirical proof via extensive analysis and experiments.
  arXiv  Detail & Related papers  (2024-11-18T21:36:44Z)
• The GUS Framework: Benchmarking Social Bias Classification with Discriminative (Encoder-Only) and Generative (Decoder-Only) Language Models [3.7716682697752506]
  Generalizations, Unfairness, and Stereotypes (the GUS framework) are considered as key linguistic components underlying social bias.<n>The GUS framework employs a semi-automated approach to create a comprehensive synthetic dataset, which is verified by humans to maintain ethical standards.<n>Our methodology, which combines discriminative (encoder-only) models and generative (auto-regressive large language models) identifies biased entities in text.
  arXiv  Detail & Related papers  (2024-10-10T21:51:22Z)
• GradBias: Unveiling Word Influence on Bias in Text-to-Image Generative Models [75.04426753720553]
  We propose a framework to identify, quantify, and explain biases in an open set setting. This pipeline leverages a Large Language Model (LLM) to propose biases starting from a set of captions. We show two variations of this framework: OpenBias and GradBias.
  arXiv  Detail & Related papers  (2024-08-29T16:51:07Z)
• Identifying and Mitigating Social Bias Knowledge in Language Models [52.52955281662332]
  We propose a novel debiasing approach, Fairness Stamp (FAST), which enables fine-grained calibration of individual social biases.<n>FAST surpasses state-of-the-art baselines with superior debiasing performance.<n>This highlights the potential of fine-grained debiasing strategies to achieve fairness in large language models.
  arXiv  Detail & Related papers  (2024-08-07T17:14:58Z)
• A Debiased Nearest Neighbors Framework for Multi-Label Text Classification [13.30576550077694]
  We introduce a DEbiased Nearest Neighbors (DENN) framework for Multi-Label Text Classification (MLTC) To address embedding alignment bias, we propose a debiased contrastive learning strategy, enhancing neighbor consistency on label co-occurrence. For confidence estimation bias, we present a debiased confidence estimation strategy, improving the adaptive combination of predictions from $k$NN and inductive binary classifications.
  arXiv  Detail & Related papers  (2024-08-06T14:00:23Z)
• Evaluating the Fairness of Discriminative Foundation Models in Computer Vision [51.176061115977774]
  We propose a novel taxonomy for bias evaluation of discriminative foundation models, such as Contrastive Language-Pretraining (CLIP) We then systematically evaluate existing methods for mitigating bias in these models with respect to our taxonomy. Specifically, we evaluate OpenAI's CLIP and OpenCLIP models for key applications, such as zero-shot classification, image retrieval and image captioning.
  arXiv  Detail & Related papers  (2023-10-18T10:32:39Z)
• Discovering and Mitigating Visual Biases through Keyword Explanation [66.71792624377069]
  We propose the Bias-to-Text (B2T) framework, which interprets visual biases as keywords. B2T can identify known biases, such as gender bias in CelebA, background bias in Waterbirds, and distribution shifts in ImageNet-R/C. B2T uncovers novel biases in larger datasets, such as Dollar Street and ImageNet.
  arXiv  Detail & Related papers  (2023-01-26T13:58:46Z)
• Mitigating Political Bias in Language Models Through Reinforced Calibration [6.964628305312507]
  We describe metrics for measuring political bias in GPT-2 generation. We propose a reinforcement learning (RL) framework for mitigating political biases in generated text.
  arXiv  Detail & Related papers  (2021-04-30T07:21:30Z)
• Weakly-Supervised Aspect-Based Sentiment Analysis via Joint Aspect-Sentiment Topic Embedding [71.2260967797055]
  We propose a weakly-supervised approach for aspect-based sentiment analysis. We learn sentiment, aspect> joint topic embeddings in the word embedding space. We then use neural models to generalize the word-level discriminative information.
  arXiv  Detail & Related papers  (2020-10-13T21:33:24Z)
• Consensus-Aware Visual-Semantic Embedding for Image-Text Matching [69.34076386926984]
  Image-text matching plays a central role in bridging vision and language. Most existing approaches only rely on the image-text instance pair to learn their representations. We propose a Consensus-aware Visual-Semantic Embedding model to incorporate the consensus information.
  arXiv  Detail & Related papers  (2020-07-17T10:22:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.