Operationalizing Pluralistic Values in Large Language Model Alignment Reveals Trade-offs in Safety, Inclusivity, and Model Behavior

• URL: http://arxiv.org/abs/2511.14476v2
• Date: Tue, 25 Nov 2025 20:42:51 GMT
• Title: Operationalizing Pluralistic Values in Large Language Model Alignment Reveals Trade-offs in Safety, Inclusivity, and Model Behavior
• Authors: Dalia Ali, Dora Zhao, Allison Koenecke, Orestis Papakyriakopoulos,
• Abstract summary: Large language models (LLMs) are increasingly trained using human feedback for safety and alignment with human values.<n>This study examines how incorporating pluralistic values affects LLM behavior by systematically evaluating demographic variation and design parameters in the alignment pipeline.
• Score: 9.90941081429899
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Although large language models (LLMs) are increasingly trained using human feedback for safety and alignment with human values, alignment decisions often overlook human social diversity. This study examines how incorporating pluralistic values affects LLM behavior by systematically evaluating demographic variation and design parameters in the alignment pipeline. We collect alignment data from US and German participants (N = 1,095 participants, 27,375 ratings) who rated LLM responses across five dimensions: Toxicity, Emotional Awareness (EA), Sensitivity, Stereotypical Bias, and Helpfulness. We fine-tuned multiple Large Language Models and Large Reasoning Models using preferences from different social groups while varying rating scales, disagreement handling methods, and optimization techniques. The results revealed systematic demographic effects: male participants rated responses 18% less toxic than female participants; conservative and Black participants rated responses 27.9% and 44% higher on EA than liberal and White participants, respectively. Models fine-tuned on group-specific preferences exhibited distinct behaviors. Technical design choices showed strong effects: the preservation of rater disagreement achieved roughly 53% greater toxicity reduction than majority voting, and 5-point scales yielded about 22% more reduction than binary formats; and Direct Preference Optimization (DPO) consistently outperformed Group Relative Policy Optimization (GRPO) in multi-value optimization. These findings represent a preliminary step in answering a critical question: How should alignment balance expert-driven and user-driven signals to ensure both safety and fair representation?

Related papers

• Multi-Reward GRPO Fine-Tuning for De-biasing Large Language Models: A Study Based on Chinese-Context Discrimination Data [0.0]
  Large Language Models (LLMs) often exhibit implicit biases and discriminatory tendencies that reflect underlying social stereotypes.<n>This paper proposes a Multi-Reward Group Relative Policy Optimization framework to fine-tune LLMs toward ethical and bias-free behavior.<n> Experimental results demonstrate significant reductions in bias intensity and improved alignment with non-discriminatory standards.
  arXiv  Detail & Related papers  (2025-11-08T14:33:21Z)
• Investigating Intersectional Bias in Large Language Models using Confidence Disparities in Coreference Resolution [5.061421107401101]
  Large language models (LLMs) have achieved impressive performance, leading to their widespread adoption as decision-support tools in resource-constrained contexts like hiring and admissions.<n>There is, however, scientific consensus that AI systems can reflect and exacerbate societal biases, raising concerns about identity-based harm when used in critical social contexts.<n>In this work, we extend single-axis fairness evaluations to examine intersectional bias, recognizing that when multiple axes of discrimination intersect, they create distinct patterns of disadvantage.
  arXiv  Detail & Related papers  (2025-08-09T22:24:40Z)
• When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning [39.22503425640312]
  Reinforcement Learning from Human Feedback (RLHF) typically assumes homogeneous preferences across users, overlooking diverse human values and minority viewpoints.<n>We present a multi-faceted evaluation framework that measures not only performance but also fairness, unintended effects, and adaptability across varying levels of preference divergence.<n>These findings highlight the critical need for holistic evaluation approaches to advance the development of more effective and inclusive preference learning systems.
  arXiv  Detail & Related papers  (2025-02-26T14:14:58Z)
• The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models [91.86718720024825]
  We center transgender, nonbinary, and other gender-diverse identities to investigate how alignment procedures interact with pre-existing gender-diverse bias.<n>Our findings reveal that DPO-aligned models are particularly sensitive to supervised finetuning.<n>We conclude with recommendations tailored to DPO and broader alignment practices.
  arXiv  Detail & Related papers  (2024-11-06T06:50:50Z)
• Diverging Preferences: When do Annotators Disagree and do Models Know? [92.24651142187989]
  We develop a taxonomy of disagreement sources spanning 10 categories across four high-level classes. We find that the majority of disagreements are in opposition with standard reward modeling approaches. We develop methods for identifying diverging preferences to mitigate their influence on evaluation and training.
  arXiv  Detail & Related papers  (2024-10-18T17:32:22Z)
• Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment [84.32768080422349]
  Alignment with human preference prevents large language models from generating misleading or toxic content. We propose a new formulation of prompt diversity, implying a linear correlation with the final performance of LLMs after fine-tuning.
  arXiv  Detail & Related papers  (2024-03-17T07:08:55Z)
• Dissecting Human and LLM Preferences [80.55271307662365]
  We find that humans are less sensitive to errors, favor responses that support their stances, and show clear dislike when models admit their limits. advanced LLMs like GPT-4-Turbo emphasize correctness, clarity, and harmlessness more. We show that preference-based evaluation can be intentionally manipulated.
  arXiv  Detail & Related papers  (2024-02-17T14:34:31Z)
• MaxMin-RLHF: Alignment with Diverse Human Preferences [101.57443597426374]
  Reinforcement Learning from Human Feedback (RLHF) aligns language models to human preferences by employing a singular reward model derived from preference data.<n>We learn a mixture of preference distributions via an expectation-maximization algorithm to better represent diverse human preferences.<n>Our algorithm achieves an average improvement of more than 16% in win-rates over conventional RLHF algorithms.
  arXiv  Detail & Related papers  (2024-02-14T03:56:27Z)
• On Diversified Preferences of Large Language Model Alignment [51.26149027399505]
  This paper presents the first quantitative analysis of the experimental scaling law for reward models with varying sizes. Our analysis reveals that the impact of diversified human preferences depends on both model size and data size. Larger models with sufficient capacity mitigate the negative effects of diverse preferences, while smaller models struggle to accommodate them.
  arXiv  Detail & Related papers  (2023-12-12T16:17:15Z)
• Sociodemographic Prompting is Not Yet an Effective Approach for Simulating Subjective Judgments with LLMs [13.744746481528711]
  Large Language Models (LLMs) are widely used to simulate human responses across diverse contexts.<n>We evaluate nine popular LLMs on their ability to understand demographic differences in two subjective judgment tasks: politeness and offensiveness.<n>We find that in zero-shot settings, most models' predictions for both tasks align more closely with labels from White participants than those from Asian or Black participants.
  arXiv  Detail & Related papers  (2023-11-16T10:02:24Z)

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.