Learning Perspectivist Social Meaning via Demographic-Conditioned Fusion Embeddings

• URL: http://arxiv.org/abs/2606.07123v1
• Date: Fri, 05 Jun 2026 10:25:01 GMT
• Title: Learning Perspectivist Social Meaning via Demographic-Conditioned Fusion Embeddings
• Abstract summary: Social meaning in language inherently perspectival, varying across annotator backgrounds, demographics, and ideological positions.<n>Most NLP systems collapse this variation into a single ground-truth label, ignoring the diversity of interpretations.<n>We model social dimensions along a perspectivist spectrum, capturing how interpretations vary across demographic groups on a dataset consisting of 28k human annotations.
• Score: 11.048086031066624
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Social meaning in language is inherently perspectival, varying across annotator backgrounds, demographics, and ideological positions. However, most NLP systems collapse this variation into a single ground-truth label, ignoring the diversity of interpretations. In this work, we model social dimensions along a perspectivist spectrum, capturing how interpretations vary across demographic groups on a dataset consisting of 28k human annotations. We benchmark multiple modeling paradigms, including zero-shot, few-shot, and fine-tuned approaches, and propose fusion embeddings that integrate textual and demographic representations. Our fusion models yield consistent and statistically significant improvements over text-only baselines across all fusion strategies (+5.9-6.5% relative macro PR-AUC), with shuffle ablations confirming that demographic profiles carry genuine predictive signal rather than spurious correlations.

Related papers

• Alignment by Stereotyping: How LLMs Sacrifice Individual Distinctiveness for Cultural Adaptation [30.1403215719712]
  We find that demographic profiles improve value alignment accuracy for most models, but at a systematic cost to individuality.<n>Top-performing models compress individuals far above the human baseline; within-family scaling amplifies this tradeoff while degrading intrinsic cultural understanding.<n>We further show that distributing demographic signals across conversational turns partially suppresses prototype retrieval compared to compact demographic labels.
  arXiv  Detail & Related papers  (2026-09-05T09:33:08Z)
• 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)
• The Ghost Annotator: a Framework to Explore Human Label Variation in Content Moderation through Conformal Prediction [39.10305114526259]
  We introduce a framework combining conformal prediction with Collaborative Filtering-style annotators' representation.<n>Using Non-Conformity Scores, we introduce the Ghost Prediction metric and the Ghost Annotator representation to quantify cases in which model predictions diverge from all available human annotations.<n>Our finding shows that while all models uncertainty increases with annotator disagreement, larger models tend to be more confident in the classification of texts that are not aligned with any human annotation.
  arXiv  Detail & Related papers  (2026-06-01T21:32:37Z)
• 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)
• Measuring Social Bias in Vision-Language Models with Face-Only Counterfactuals from Real Photos [79.03150233804458]
  Real-world images entangle race and gender with correlated factors such as background and clothing, obscuring attribution.<n>We propose a textbfface-only counterfactual evaluation paradigm<n>We generate counterfactual variants by editing only facial attributes related to race and gender, keeping all other visual factors fixed.
  arXiv  Detail & Related papers  (2026-01-11T14:35:06Z)
• Mitigating Bias with Words: Inducing Demographic Ambiguity in Face Recognition Templates by Text Encoding [18.08946802592489]
  Face recognition systems are often prone to demographic biases, partially due to the entanglement of demographic-specific information with identity-relevant features in facial embeddings.<n>We propose a novel strategy, Unified Text-Image Embedding (UTIE), which aims to induce demographic ambiguity in face embeddings.<n>We show that UTIE consistently reduces bias metrics while maintaining, or even improving in several cases, the face verification accuracy.
  arXiv  Detail & Related papers  (2025-12-05T10:41:58Z)
• Us-vs-Them bias in Large Language Models [0.569978892646475]
  We find consistent ingroup-positive and outgroup-negative associations across foundational large language models.<n>For personas examined, conservative personas exhibit greater outgroup hostility, whereas liberal personas display stronger ingroup solidarity.
  arXiv  Detail & Related papers  (2025-12-03T07:11:22Z)
• MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework [53.82097200295448]
  Mean-Field LLM (MF-LLM) is first to incorporate mean field theory into social simulation.<n>MF-LLM models bidirectional interactions between individuals and the population through an iterative process.<n> IB-Tune is a novel fine-tuning method inspired by the Information Bottleneck principle.
  arXiv  Detail & Related papers  (2025-04-30T12:41:51Z)
• Robustness and Confounders in the Demographic Alignment of LLMs with Human Perceptions of Offensiveness [10.194622474615462]
  Large language models (LLMs) are known to exhibit demographic biases, yet few studies systematically evaluate these biases across multiple datasets or account for confounding factors. Our findings reveal that while demographic traits, particularly race, influence alignment, these effects are inconsistent across datasets and often entangled with other factors.
  arXiv  Detail & Related papers  (2024-11-13T19:08:23Z)
• 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)
• Fair Abstractive Summarization of Diverse Perspectives [103.08300574459783]
  A fair summary should provide a comprehensive coverage of diverse perspectives without underrepresenting certain groups. We first formally define fairness in abstractive summarization as not underrepresenting perspectives of any groups of people. We propose four reference-free automatic metrics by measuring the differences between target and source perspectives.
  arXiv  Detail & Related papers  (2023-11-14T03:38:55Z)
• On the steerability of large language models toward data-driven personas [98.9138902560793]
  Large language models (LLMs) are known to generate biased responses where the opinions of certain groups and populations are underrepresented. Here, we present a novel approach to achieve controllable generation of specific viewpoints using LLMs.
  arXiv  Detail & Related papers  (2023-11-08T19:01:13Z)
• Stable Bias: Analyzing Societal Representations in Diffusion Models [72.27121528451528]
  We propose a new method for exploring the social biases in Text-to-Image (TTI) systems. Our approach relies on characterizing the variation in generated images triggered by enumerating gender and ethnicity markers in the prompts. We leverage this method to analyze images generated by 3 popular TTI systems and find that while all of their outputs show correlations with US labor demographics, they also consistently under-represent marginalized identities to different extents.
  arXiv  Detail & Related papers  (2023-03-20T19:32:49Z)

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.