DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mapping

• URL: http://arxiv.org/abs/2605.14420v1
• Date: Thu, 14 May 2026 06:06:43 GMT
• Title: DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mapping
• Abstract summary: Current Large Language Models (LLMs) typically rely on coarse-grained national labels for pluralistic value alignment.<n>We argue that resolving this limitation requires shifting from national labels to multi-dimensional demographic constraints.<n>We propose DVMap, a framework for fine-grained pluralistic value alignment.
• Score: 49.402442592047855
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Current Large Language Models (LLMs) typically rely on coarse-grained national labels for pluralistic value alignment. However, such macro-level supervision often obscures intra-country value heterogeneity, yielding a loose alignment. We argue that resolving this limitation requires shifting from national labels to multi-dimensional demographic constraints, which can identify groups with predictable, high-consensus value preference. To this end, we propose DVMap (High-Consensus Demographic-Value Mapping), a framework for fine-grained pluralistic value alignment. In this framework, we first present a demographic archetype extraction strategy to construct a high-quality value alignment corpus of 56,152 samples from the World Values Survey (WVS) by strictly retaining respondents with consistent value preferences under identical demographics. Over this corpus, we introduce a Structured Chain-of-Thought (CoT) mechanism that explicitly guides LLMs to reason about demographic-value correlations. Subsequently, we employ Group Relative Policy Optimization (GRPO) to achieve adaptive anchoring of value distributions. To rigorously evaluate generalization, we further establish a triple-generalization benchmark (spanning cross-demographic, cross-country, and cross-value) comprising 21,553 samples. Experimental results demonstrate that DVMap effectively learns the manifold mapping from demographics to values, exhibiting strong generalization and robustness. On cross-demographic tests, Qwen3-8B-DVMap achieves 48.6% accuracy, surpassing the advanced open-source LLM DeepSeek-v3.2 (45.1%). The source code and dataset are available at https://github.com/EnlightenedAI/DVMap.

Related papers

• Beyond Value Benchmarks: Measuring Value-Structure Alignment in Large Language Models via Symmetric Q-Sorts [47.02978329409663]
  We propose a symmetric human-LLM evaluation framework, grounded in Q methodology, to measure value-structure alignment.<n>Under our protocol, humans and models sort an identical 140-item moral statement set into a shared nine-column forced distribution.<n>We evaluate 12 LLMs across four model families via 240 replicated Q-sorts at two temperature settings.
  arXiv  Detail & Related papers  (2026-06-20T08:15:41Z)
• Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment [75.88231994139132]
  We show that even state-of-the-art models like GPT-4.1 achieve only 57.4% accuracy in predicting modal preferences.<n>We find significant pre-existing performance biases, where models better emulate young, male, Chinese, and Christian personas.
  arXiv  Detail & Related papers  (2026-04-14T15:06:13Z)
• Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook [50.10594064510559]
  DOVE is a distributional evaluation framework that directly compares human-written text with LLM-generated outputs.<n>We show that DOVE achieves superior predictive validity, attaining a 31.56% correlation with downstream tasks, while maintaining high reliability with as few as 500 samples per culture.
  arXiv  Detail & Related papers  (2026-03-16T08:33:10Z)
• PANC: Prior-Aware Normalized Cut for Object Segmentation [0.0]
  We propose a weakly supervised spectral segmentation framework that uses a minimal set of annotated visual tokens.<n>We report strong results on homogeneous, fine-grained, and texture-limited domains.<n>For multi-object benchmarks, the framework showcases explicit, user-controllable semantic segmentation.
  arXiv  Detail & Related papers  (2026-02-06T18:07:20Z)
• Where on Earth? A Vision-Language Benchmark for Probing Model Geolocation Skills Across Scales [61.03549470159347]
  Vision-language models (VLMs) have advanced rapidly, yet their capacity for image-grounded geolocation in open-world conditions has not been comprehensively evaluated.<n>We present EarthWhere, a comprehensive benchmark for VLM image geolocation that evaluates visual recognition, step-by-step reasoning, and evidence use.
  arXiv  Detail & Related papers  (2025-10-13T01:12:21Z)
• MVPBench: A Benchmark and Fine-Tuning Framework for Aligning Large Language Models with Diverse Human Values [23.048484118383616]
  We introduce MVPBench, a novel benchmark that evaluates large language models' alignment with human values across 75 countries.<n>Using MVPBench, we conduct an in-depth analysis of several state-of-the-art LLMs, revealing substantial disparities in alignment performance across geographic and demographic lines.<n>Our findings underscore the necessity for population-aware alignment evaluation and provide actionable insights for building culturally adaptive and value-sensitive LLMs.
  arXiv  Detail & Related papers  (2025-09-09T09:25:08Z)
• GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks [84.86699025256705]
  We present GEOBench-VLM, a benchmark specifically designed to evaluate Vision-Language Models (VLMs) on geospatial tasks.<n>Our benchmark features over 10,000 manually verified instructions and spanning diverse visual conditions, object types, and scales.<n>We evaluate several state-of-the-art VLMs to assess performance on geospatial-specific challenges.
  arXiv  Detail & Related papers  (2024-11-28T18:59:56Z)
• Relational Proxies: Emergent Relationships as Fine-Grained Discriminators [52.17542855760418]
  We propose a novel approach that leverages information between the global and local part of an object for encoding its label. We design Proxies based on our theoretical findings and evaluate it on seven challenging fine-grained benchmark datasets. We also experimentally validate our theory and obtain consistent results across multiple benchmarks.
  arXiv  Detail & Related papers  (2022-10-05T11:08:04Z)
• Rethinking Localization Map: Towards Accurate Object Perception with Self-Enhancement Maps [78.2581910688094]
  This work introduces a novel self-enhancement method to harvest accurate object localization maps and object boundaries with only category labels as supervision. In particular, the proposed Self-Enhancement Maps achieve the state-of-the-art localization accuracy of 54.88% on ILSVRC.
  arXiv  Detail & Related papers  (2020-06-09T12:35:55Z)

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.