Can Language Models Reason about Individualistic Human Values and Preferences?

• URL: http://arxiv.org/abs/2410.03868v2
• Date: Sat, 31 May 2025 03:22:11 GMT
• Title: Can Language Models Reason about Individualistic Human Values and Preferences?
• Authors: Liwei Jiang, Taylor Sorensen, Sydney Levine, Yejin Choi,
• Abstract summary: We study language models (LMs) on the challenge of individualistic value reasoning.<n>We find critical limitations in frontier LMs, which achieve only 55 % to 65% accuracy in predicting individualistic values.<n>We also identify a partiality of LMs in reasoning about global individualistic values, as measured by our proposed Value Inequity Index (sigmaInequity)
• Score: 44.249817353449146
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent calls for pluralistic alignment emphasize that AI systems should address the diverse needs of all people. Yet, efforts in this space often require sorting people into fixed buckets of pre-specified diversity-defining dimensions (e.g., demographics), risking smoothing out individualistic variations or even stereotyping. To achieve an authentic representation of diversity that respects individuality, we propose individualistic alignment. While individualistic alignment can take various forms, we introduce IndieValueCatalog, a dataset transformed from the influential World Values Survey (WVS), to study language models (LMs) on the specific challenge of individualistic value reasoning. Given a sample of an individual's value-expressing statements, models are tasked with predicting this person's value judgments in novel cases. With IndieValueCatalog, we reveal critical limitations in frontier LMs, which achieve only 55 % to 65% accuracy in predicting individualistic values. Moreover, our results highlight that a precise description of individualistic values cannot be approximated only with demographic information. We also identify a partiality of LMs in reasoning about global individualistic values, as measured by our proposed Value Inequity Index ({\sigma}Inequity). Finally, we train a series of IndieValueReasoners to reveal new patterns and dynamics into global human values.

Related papers

• Value Profiles for Encoding Human Variation [17.23399556310694]
  We propose representing individuals using value profiles -- natural language descriptions of underlying values compressed from in-context demonstrations. We find that demonstrations contain the most information, followed by value profiles and then demographics. Value profiles offer advantages in terms of scrutability, interpretability, and steerability due to their compressed natural language format.
  arXiv  Detail & Related papers  (2025-03-19T17:57:49Z)
• iNews: A Multimodal Dataset for Modeling Personalized Affective Responses to News [25.367927300697424]
  iNews is a novel dataset specifically designed to facilitate the modeling of personalized affective responses to news content.<n>Our dataset comprises annotations from 291 demographically diverse UK participants across 2,899 multimodal Facebook news posts from major UK outlets.
  arXiv  Detail & Related papers  (2025-03-05T10:09:53Z)
• Democratizing Reward Design for Personal and Representative Value-Alignment [10.1630183955549]
  We introduce Interactive-Reflective Dialogue Alignment, a method that iteratively engages users in reflecting on and specifying their subjective value definitions. This system learns individual value definitions through language-model-based preference elicitation and constructs personalized reward models. Our findings demonstrate diverse definitions of value-aligned behaviour and show that our system can accurately capture each person's unique understanding.
  arXiv  Detail & Related papers  (2024-10-29T16:37:01Z)
• Personality Alignment of Large Language Models [26.071445846818914]
  Current methods for aligning large language models (LLMs) typically aim to reflect general human values and behaviors. We introduce the concept of Personality Alignment. This approach tailors LLMs' responses and decisions to match the specific preferences of individual users or closely related groups.
  arXiv  Detail & Related papers  (2024-08-21T17:09:00Z)
• CIVICS: Building a Dataset for Examining Culturally-Informed Values in Large Language Models [59.22460740026037]
  "CIVICS: Culturally-Informed & Values-Inclusive Corpus for Societal impacts" dataset is designed to evaluate the social and cultural variation of Large Language Models (LLMs) We create a hand-crafted, multilingual dataset of value-laden prompts which address specific socially sensitive topics, including LGBTQI rights, social welfare, immigration, disability rights, and surrogacy.
  arXiv  Detail & Related papers  (2024-05-22T20:19:10Z)
• Beyond Human Norms: Unveiling Unique Values of Large Language Models through Interdisciplinary Approaches [69.73783026870998]
  This work proposes a novel framework, ValueLex, to reconstruct Large Language Models' unique value system from scratch. Based on Lexical Hypothesis, ValueLex introduces a generative approach to elicit diverse values from 30+ LLMs. We identify three core value dimensions, Competence, Character, and Integrity, each with specific subdimensions, revealing that LLMs possess a structured, albeit non-human, value system.
  arXiv  Detail & Related papers  (2024-04-19T09:44:51Z)
• High-Dimension Human Value Representation in Large Language Models [60.33033114185092]
  We propose UniVaR, a high-dimensional representation of human value distributions in Large Language Models (LLMs) We show that UniVaR is a powerful tool to compare the distribution of human values embedded in different LLMs with different langauge sources.
  arXiv  Detail & Related papers  (2024-04-11T16:39:00Z)
• 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)
• JPAVE: A Generation and Classification-based Model for Joint Product Attribute Prediction and Value Extraction [59.94977231327573]
  We propose a multi-task learning model with value generation/classification and attribute prediction called JPAVE. Two variants of our model are designed for open-world and closed-world scenarios. Experimental results on a public dataset demonstrate the superiority of our model compared with strong baselines.
  arXiv  Detail & Related papers  (2023-11-07T18:36:16Z)
• Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties [68.66719970507273]
  Value pluralism is the view that multiple correct values may be held in tension with one another. As statistical learners, AI systems fit to averages by default, washing out potentially irreducible value conflicts. We introduce ValuePrism, a large-scale dataset of 218k values, rights, and duties connected to 31k human-written situations.
  arXiv  Detail & Related papers  (2023-09-02T01:24:59Z)
• Heterogeneous Value Alignment Evaluation for Large Language Models [91.96728871418]
  Large Language Models (LLMs) have made it crucial to align their values with those of humans. We propose a Heterogeneous Value Alignment Evaluation (HVAE) system to assess the success of aligning LLMs with heterogeneous values.
  arXiv  Detail & Related papers  (2023-05-26T02:34:20Z)
• Model-agnostic Fits for Understanding Information Seeking Patterns in Humans [0.0]
  In decision making tasks under uncertainty, humans display characteristic biases in seeking, integrating, and acting upon information relevant to the task. Here, we reexamine data from previous carefully designed experiments, collected at scale, that measured and catalogued these biases in aggregate form. We design deep learning models that replicate these biases in aggregate, while also capturing individual variation in behavior.
  arXiv  Detail & Related papers  (2020-12-09T04:34:58Z)
• Beyond Our Behavior: The GDPR and Humanistic Personalization [0.0]
  We propose a new paradigm of humanistic personalization. We re-frame distinction between implicit and explicit data collection as one of nonconscious ("organismic") behavior and conscious ("reflective") action. We discuss how an emphasis on narrative accuracy can reduce opportunities for data done done of injustice subjects.
  arXiv  Detail & Related papers  (2020-08-31T07:40:09Z)

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.