Invisible Influences: Investigating Implicit Intersectional Biases through Persona Engineering in Large Language Models

• URL: http://arxiv.org/abs/2604.06213v1
• Date: Mon, 16 Mar 2026 15:57:12 GMT
• Title: Invisible Influences: Investigating Implicit Intersectional Biases through Persona Engineering in Large Language Models
• Abstract summary: Large Language Models (LLMs) excel at human-like language generation but often embed and amplify implicit, intersectional biases.<n>Existing bias audits rely on static, embedding-based tests (CEAT, I-WEAT, I-SEAT) that quantify absolute association strengths.<n>We introduce the Bias Amplification Differential and Explainability Score (BADx): a novel, scalable metric that measures persona-induced bias amplification.
• Score: 4.145971099162064
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) excel at human-like language generation but often embed and amplify implicit, intersectional biases, especially under persona-driven contexts. Existing bias audits rely on static, embedding-based tests (CEAT, I-WEAT, I-SEAT) that quantify absolute association strengths. We show that they have limitations in capturing dynamic shifts when models adopt social roles. We address this gap by introducing the Bias Amplification Differential and Explainability Score (BADx): a novel, scalable metric that measures persona-induced bias amplification and integrates local explainability insights. BADx comprises three components - differential bias scores (BAD, based on CEAT, I-WEAT, I-SEAT),Persona Sensitivity Index (PSI), and Volatility (Standard Deviation), augmented by LIME-based analysis for emphasizing explainability. This study is divided and performed as two different tasks. Task 1 establishes static bias baselines, and Task 2 applies six persona frames (marginalized and structurally advantaged) to measure BADx, PSI, and volatility. This is studied across five state-of-the-art LLMs (GPT-4o, DeepSeek-R1, LLaMA-4, Claude 4.0 Sonnet and Gemma-3n E4B). Results show persona context significantly modulates bias. GPT-4o exhibits high sensitivity and volatility; DeepSeek-R1 suppresses bias but with erratic volatility; LLaMA-4 maintains low volatility and a stable bias profile with limited amplification; Claude 4.0 Sonnet achieves balanced modulation; and Gemma-3n E4B attains the lowest volatility with moderate amplification. BADx performs better than static methods by revealing context-sensitive biases overlooked in static methods. Our unified method offers a systematic way to detect dynamic implicit intersectional bias in five popular LLMs.

Related papers

• UniNDM: A Unified Noise-driven Detection and Mitigation Framework Against Sexual Content in Text-to-Image Generation [90.0896070825457]
  We propose a unified noise-driven framework that rethinks safety mechanisms through the lens of noise dynamics in diffusion processes.<n>Our key insight is that early-stage predicted noise exhibits inherent separability between normal and sexually explicit content.<n>We develop a lightweight noise-based detector achieving superior accuracy with virtually no computational overhead.
  arXiv  Detail & Related papers  (2026-07-18T14:03:39Z)
• EBench: Elemental Diagnosis of Generalist Mobile Manipulation Policies [92.63011025295123]
  We present EBench, a simulation benchmark that diagnoses generalist mobile manipulation policies.<n>EBench comprises 26 diverse and challenging manipulation tasks annotated along 5 capability dimensions and 4 generalization dimensions.
  arXiv  Detail & Related papers  (2026-06-16T17:58:22Z)
• IV-ICL: Bounding Causal Effects with Instrumental Variables via In-Context Learning [11.804716294874018]
  IV-ICL is an amortized Bayesian in-context learning method that learns the marginal posterior distribution of the causal effects directly and derives bounds as its quantiles.<n>We evaluate IV-ICL on synthetic and semi-synthetic IV benchmarks and show it produces intervals that are more reliably valid and more informative.
  arXiv  Detail & Related papers  (2026-05-13T03:00:08Z)
• Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability [22.32075837181307]
  Large language models (LLMs) are increasingly deployed in settings that require nuanced ethical reasoning.<n>We introduce the Moral Sensitivity Index (MSI), a metric that quantifies the probability of biased output.<n>We select criminal-bias scenarios, which produced the highest MSI scores across models.
  arXiv  Detail & Related papers  (2026-05-04T23:12:32Z)
• How Independent are Large Language Models? A Statistical Framework for Auditing Behavioral Entanglement and Reweighting Verifier Ensembles [46.63622714488747]
  Shared pretraining data, distillation, and alignment pipelines can induce hidden behavioral dependencies, latent entanglement.<n>In practice, this manifests as correlated reasoning patterns and synchronized failures.<n>We develop a statistical framework for auditing behavioral entanglement among black-box language models.
  arXiv  Detail & Related papers  (2026-04-08T23:32:06Z)
• The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training [24.539689177262193]
  Large language models trained on natural language exhibit pronounced anisotropy.<n>In low-bit training regimes, this geometry becomes numerically unstable.<n>We show that this instability is primarily driven by a coherent rank-one mean bias.
  arXiv  Detail & Related papers  (2026-03-11T05:59:12Z)
• Steering and Rectifying Latent Representation Manifolds in Frozen Multi-modal LLMs for Video Anomaly Detection [52.5174167737992]
  Video anomaly detection (VAD) aims to identify abnormal events in videos.<n>We propose SteerVAD, which advances MLLM-based VAD by shifting from passively reading to actively steering and rectifying internal representations.<n>Our method achieves state-of-the-art performance among tuning-free approaches requiring only 1% of training data.
  arXiv  Detail & Related papers  (2026-02-27T13:48:50Z)
• ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-Tuning [85.20505958752928]
  Reinforcement Fine-Tuning (RFT) on flow-based models is crucial for preference alignment.<n>RFT often introduce visual hallucinations like over-optimized details and semantic misalignment.<n>This work preliminarily explores why visual hallucinations arise and how to reduce them.
  arXiv  Detail & Related papers  (2026-02-03T11:49:46Z)
• Mitigating Multimodal Hallucinations via Gradient-based Self-Reflection [49.26064449816502]
  We propose a Gradient-based Influence-Aware Constrained Decoding (GACD) method to address text-visual bias and co-occurrence bias.<n>GACD effectively reduces hallucinations and improves the visual grounding of MLLM outputs.
  arXiv  Detail & Related papers  (2025-09-03T08:13:52Z)
• Explicit vs. Implicit: Investigating Social Bias in Large Language Models through Self-Reflection [18.625071242029936]
  Large Language Models (LLMs) have been shown to exhibit various biases and stereotypes in their generated content.<n>This paper presents a systematic framework to investigate and compare explicit and implicit biases in LLMs.
  arXiv  Detail & Related papers  (2025-01-04T14:08:52Z)
• Probability of Differentiation Reveals Brittleness of Homogeneity Bias in GPT-4 [0.0]
  Homogeneity bias in Large Language Models (LLMs) refers to their tendency to homogenize the representations of some groups compared to others.<n>Previous studies documenting this bias have predominantly used encoder models, which may have inadvertently introduced biases.<n>This study directly assessed homogeneity bias from the model's outputs, bypassing encoder models.
  arXiv  Detail & Related papers  (2024-07-10T02:56:55Z)
• Delving into Identify-Emphasize Paradigm for Combating Unknown Bias [52.76758938921129]
  We propose an effective bias-conflicting scoring method (ECS) to boost the identification accuracy. We also propose gradient alignment (GA) to balance the contributions of the mined bias-aligned and bias-conflicting samples. Experiments are conducted on multiple datasets in various settings, demonstrating that the proposed solution can mitigate the impact of unknown biases.
  arXiv  Detail & Related papers  (2023-02-22T14:50:24Z)
• Feature-Level Debiased Natural Language Understanding [86.8751772146264]
  Existing natural language understanding (NLU) models often rely on dataset biases to achieve high performance on specific datasets. We propose debiasing contrastive learning (DCT) to mitigate biased latent features and neglect the dynamic nature of bias. DCT outperforms state-of-the-art baselines on out-of-distribution datasets while maintaining in-distribution performance.
  arXiv  Detail & Related papers  (2022-12-11T06:16:14Z)

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.