When Does Demographic Information Help? Data and Modeling Regimes for Perspective-Aware Hate Speech Detection

• URL: http://arxiv.org/abs/2605.27313v1
• Date: Tue, 26 May 2026 17:24:41 GMT
• Title: When Does Demographic Information Help? Data and Modeling Regimes for Perspective-Aware Hate Speech Detection
• Abstract summary: We analyze demographic gain as a function of both data split properties and modeling frameworks.<n>We find that demographic gains concentrate in regimes with low training disagreement, high test disagreement, fine-grained ambiguity measurement, sufficient training data, and greater demographic overlap.
• Score: 3.685453775072903
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Demographic information is often used to model annotator perspectives in subjective tasks such as hate speech detection, but its benefit is inconsistent: it improves performance in some settings and behaves as noise in others. This paper asks when demographic features help. We analyze demographic gain as a function of both data split properties and modeling frameworks. For data splits, we measure annotator disagreement, namely how often annotators assign different labels to the same example, along with training size and train-test demographic coverage. We find that demographic gains concentrate in regimes with low training disagreement, high test disagreement, fine-grained ambiguity measurement, sufficient training data, and greater demographic overlap. Motivated by these regimes, we introduce a gated demographic residual model that treats demographics as a selective adjustment to text-only predictions. Experiments on MHS and POPQUORN show that this design is effective, especially on high disagreement or low confidence examples. Overall, our results suggest that demographics should not be assumed useful by default; their value depends jointly on the data regime and the modeling framework.

Related papers

• FairForensics: Seeing Expressions and Parsing Demographics via Vision-Language Modeling for Generalizable Fair Deepfake Detection [60.2868121662026]
  Existing fairness-enhanced detectors often suffer from suboptimal generalization to unseen manipulations and fairness across demographic groups.<n>We construct a novel demographically balanced FDD benchmark to train and evaluate the fairness of detectors under both balanced and imbalanced population scenarios.<n>We also introduce a novel expression and demographic perceptual vision-language model, termed FairForensics, for generalizable fair deepfake detection.
  arXiv  Detail & Related papers  (2026-08-03T03:51:14Z)
• Demographic Probing of Large Language Models Lacks Construct Validity [16.29607362682272]
  We study how large language models adapt their behavior to demographic attributes.<n>This approach typically uses a single demographic cue in isolation as a signal for group membership.<n>We find that cues intended to represent the same demographic group induce only partially overlapping changes in model behavior.
  arXiv  Detail & Related papers  (2026-01-26T13:41:35Z)
• Assessing the Reliability of LLMs Annotations in the Context of Demographic Bias and Model Explanation [5.907945985868999]
  This study investigates the extent to which annotator demographic features influence labeling decisions compared to text content.<n>Using a Generalized Linear Mixed Model, we quantify this inf luence, finding that demographic factors account for a minor fraction ( 8%) of the observed variance.<n>We then assess the reliability of Generative AI (GenAI) models as annotators, specifically evaluating if guiding them with demographic personas improves alignment with human judgments.
  arXiv  Detail & Related papers  (2025-07-17T14:00:13Z)
• CO-VADA: A Confidence-Oriented Voice Augmentation Debiasing Approach for Fair Speech Emotion Recognition [49.27067541740956]
  We present CO-VADA, a Confidence-Oriented Voice Augmentation Debiasing Approach that mitigates bias without modifying model architecture or relying on demographic information.<n>CO-VADA identifies training samples that reflect bias patterns present in the training data and then applies voice conversion to alter irrelevant attributes and generate samples.<n>Our framework is compatible with various SER models and voice conversion tools, making it a scalable and practical solution for improving fairness in SER systems.
  arXiv  Detail & Related papers  (2025-06-06T13:25:56Z)
• Value Profiles for Encoding Human Variation [12.302443348395117]
  Value profiles are descriptions of underlying values compressed from in-context demonstrations.<n>Value profiles offer advantages in terms of scrutability, interpretability, and steerability.<n>We show that the decoder predictions change in line with semantic profile differences, are well-calibrated, and can help explain instance-level disagreement.
  arXiv  Detail & Related papers  (2025-03-19T17:57:49Z)
• Accurate and Data-Efficient Toxicity Prediction when Annotators Disagree [1.3749490831384268]
  When annotators disagree, predicting the labels given by individual annotators can capture nuances overlooked by traditional label aggregation. We introduce three approaches to predicting individual annotator ratings on the toxicity of text. We study the utility of demographic information for rating prediction.
  arXiv  Detail & Related papers  (2024-10-16T04:26:40Z)
• Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information [50.29934517930506]
  DAFair is a novel approach to address social bias in language models. We leverage prototypical demographic texts and incorporate a regularization term during the fine-tuning process to mitigate bias.
  arXiv  Detail & Related papers  (2024-03-14T15:58:36Z)
• Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Prompting [64.80538055623842]
  sociodemographic prompting is a technique that steers the output of prompt-based models towards answers that humans with specific sociodemographic profiles would give. We show that sociodemographic information affects model predictions and can be beneficial for improving zero-shot learning in subjective NLP tasks.
  arXiv  Detail & Related papers  (2023-09-13T15:42:06Z)
• Metrics for Dataset Demographic Bias: A Case Study on Facial Expression Recognition [4.336779198334903]
  One of the most prominent types of demographic bias are statistical imbalances in the representation of demographic groups in the datasets. We develop a taxonomy for the classification of these metrics, providing a practical guide for the selection of appropriate metrics. The paper provides valuable insights for researchers in AI and related fields to mitigate dataset bias and improve the fairness and accuracy of AI models.
  arXiv  Detail & Related papers  (2023-03-28T11:04:18Z)
• Perceptual Score: What Data Modalities Does Your Model Perceive? [73.75255606437808]
  We introduce the perceptual score, a metric that assesses the degree to which a model relies on the different subsets of the input features. We find that recent, more accurate multi-modal models for visual question-answering tend to perceive the visual data less than their predecessors. Using the perceptual score also helps to analyze model biases by decomposing the score into data subset contributions.
  arXiv  Detail & Related papers  (2021-10-27T12:19:56Z)
• Balancing out Bias: Achieving Fairness Through Training Reweighting [58.201275105195485]
  Bias in natural language processing arises from models learning characteristics of the author such as gender and race. Existing methods for mitigating and measuring bias do not directly account for correlations between author demographics and linguistic variables. This paper introduces a very simple but highly effective method for countering bias using instance reweighting.
  arXiv  Detail & Related papers  (2021-09-16T23:40:28Z)

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.