Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability

• URL: http://arxiv.org/abs/2605.03217v1
• Date: Mon, 04 May 2026 23:12:32 GMT
• Title: Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability
• Abstract summary: 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.
• Score: 22.32075837181307
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are increasingly deployed in settings that require nuanced ethical reasoning, yet existing bias evaluations treat model outputs as simply "biased" or "unbiased." This binary framing misses the gradual, context-sensitive way bias actually emerges. We address this gap in two stages: behavioral profiling and mechanistic validation. In the behavioral stage, we introduce the Moral Sensitivity Index (MSI), a metric that quantifies the probability of biased output across a graduated, seven-tier stress test ranging from abstract numerical problems to scenarios rooted in historical and socioeconomic injustice. Evaluating four leading models (Claude 3.5, Qwen 3.5, Llama 3, and Gemini 1.5), we identify distinct behavioral signatures shaped by alignment design: for instance, Gemini 1.5 reaches 72.7% MSI by Tier 5 under socioeconomic framing, while Claude exhibits sharp suppression consistent with identity-based safety training. We then verify these behavioral patterns mechanistically. We select criminal-bias scenarios, which produced the highest MSI scores across models, as probes and apply logit lens, attention analysis, activation patching, and semantic probing to a controlled set of six models spanning three capability tiers: small language models (SLMs), instruction-tuned base models, and reasoning-distilled variants. Circuit-level analysis reveals a U-curve of bias: SLMs exhibit strong criminal bias; scaling to instruction-tuned models eliminates it; reasoning distillation reintroduces bias to SLM-like levels despite identical parameter counts, suggesting distillation compresses reasoning traces in ways that reactivate shallow statistical associations. Critically, the socially loaded cues that drive high MSI scores activate the same bias-driving circuits identified mechanistically, providing cross-stage validation.

Related papers

• Does Reasoning Preserve Alignment? On the Trustworthiness of Large Reasoning Models [55.788110316999166]
  We compare reasoning models produced via supervised fine-tuning, RL-based post-training, and distillation against instruction-tuned baselines.<n>We observe that reasoning models often improve on reasoning benchmarks but exhibit alignment regressions.<n>These regressions are consistent with behavioral drift from the instruction-tuned baseline, measured by KL divergence.
  arXiv  Detail & Related papers  (2026-06-09T16:14:27Z)
• Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality? [74.69723255239663]
  Grounded Personality Reasoning requires MLLMs to anchor each Big Five rating in observable evidence through a chain of rating, reasoning, and grounding.<n> MM-OCEAN is produced by a multi-agent pipeline with human verification, with timestamped behavioral observations, evidence-grounded trait analyses, and seven categories of cue-grounding MCQs.<n>The analysis uncovers a striking Prejudice Gap: across the field, 51% of correct ratings are not grounded in retrieved cues, and the Holistic-Grounding Rate spans only 0-33.5%.
  arXiv  Detail & Related papers  (2026-05-21T07:42:47Z)
• MANTA: Multi-turn Assessment for Nonhuman Thinking & Alignment [0.1452394725421793]
  MANTA is a dynamic multi-turn evaluation framework built on the Inspect AI platform.<n>We present preliminary results from evaluations of claude-sonnet-4-20250514 and openai/gpt-4o.<n>We additionally present STYLEJUDGE, a controlled four-judge study demonstrating systematic format bias in LLM-as-judge evaluation.
  arXiv  Detail & Related papers  (2026-04-18T19:51:32Z)
• Redirected, Not Removed: Task-Dependent Stereotyping Reveals the Limits of LLM Alignments [0.19703625025720697]
  Single-task benchmarks miss this because they capture only one slice of a model's bias profile.<n>We introduce a hierarchical taxonomy covering 9 bias types, including under-studied axes like caste, linguistic, and geographic bias.<n>We Auditing 7 commercial and open-weight LLMs with textasciitilde45K prompts, we find three systematic patterns.
  arXiv  Detail & Related papers  (2026-04-03T03:03:21Z)
• Invisible Influences: Investigating Implicit Intersectional Biases through Persona Engineering in Large Language Models [4.145971099162064]
  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.
  arXiv  Detail & Related papers  (2026-03-16T15:57:12Z)
• MBD: A Model-Based Debiasing Framework Across User, Content, and Model Dimensions [50.00784452900918]
  We propose a general, model-based debiasing (MBD) framework that addresses this challenge.<n>We explicitly estimate the contextual mean and variance of the engagement distribution for arbitrary cohorts.<n>This integration allows the framework to convert biased raw signals into unbiased representations.
  arXiv  Detail & Related papers  (2026-03-15T15:07:01Z)
• RoboView-Bias: Benchmarking Visual Bias in Embodied Agents for Robotic Manipulation [67.38036090822982]
  We propose RoboView-Bias, the first benchmark specifically designed to quantify visual bias in robotic manipulation.<n>We create 2,127 task instances that enable robust measurement of biases induced by individual visual factors and their interactions.<n>Our results highlight that systematic analysis of visual bias is a prerequisite for developing safe and reliable general-purpose embodied agents.
  arXiv  Detail & Related papers  (2025-09-26T13:53:25Z)
• FairReason: Balancing Reasoning and Social Bias in MLLMs [54.26091556079722]
  Multimodal Large Language Models (MLLMs) already achieve state-of-the-art results across a wide range of tasks and modalities.<n>Recent studies explore advanced prompting schemes and post-training fine-tuning to push their reasoning ability further.
  arXiv  Detail & Related papers  (2025-07-30T19:57:22Z)
• Implicit Bias-Like Patterns in Reasoning Models [0.5729426778193398]
  Implicit biases refer to automatic mental processes that shape perceptions, judgments, and behaviors.<n>We present the Reasoning Model Implicit Association Test (RM-IAT) to study implicit bias-like processing in reasoning models.
  arXiv  Detail & Related papers  (2025-03-14T16:40:02Z)
• Semantic Image Attack for Visual Model Diagnosis [80.36063332820568]
  In practice, metric analysis on a specific train and test dataset does not guarantee reliable or fair ML models. This paper proposes Semantic Image Attack (SIA), a method based on the adversarial attack that provides semantic adversarial images.
  arXiv  Detail & Related papers  (2023-03-23T03:13:04Z)
• 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)

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.