MAP: Multi-Human-Value Alignment Palette

• URL: http://arxiv.org/abs/2410.19198v1
• Date: Thu, 24 Oct 2024 23:16:39 GMT
• Title: MAP: Multi-Human-Value Alignment Palette
• Authors: Xinran Wang, Qi Le, Ammar Ahmed, Enmao Diao, Yi Zhou, Nathalie Baracaldo, Jie Ding, Ali Anwar,
• Abstract summary: We develop a novel, first-principle approach called Multi-Human-Value Alignment Palette (MAP) MAP navigates the alignment across multiple human values in a structured and reliable way. We conduct a detailed theoretical analysis of MAP by quantifying the trade-offs between values, the sensitivity to constraints, the fundamental connection between multi-value alignment and sequential alignment, and proving that linear weighted rewards are sufficient for multi-value alignment.
• Score: 22.74688073469946
• License:
• Abstract: Ensuring that generative AI systems align with human values is essential but challenging, especially when considering multiple human values and their potential trade-offs. Since human values can be personalized and dynamically change over time, the desirable levels of value alignment vary across different ethnic groups, industry sectors, and user cohorts. Within existing frameworks, it is hard to define human values and align AI systems accordingly across different directions simultaneously, such as harmlessness, helpfulness, and positiveness. To address this, we develop a novel, first-principle approach called Multi-Human-Value Alignment Palette (MAP), which navigates the alignment across multiple human values in a structured and reliable way. MAP formulates the alignment problem as an optimization task with user-defined constraints, which define human value targets. It can be efficiently solved via a primal-dual approach, which determines whether a user-defined alignment target is achievable and how to achieve it. We conduct a detailed theoretical analysis of MAP by quantifying the trade-offs between values, the sensitivity to constraints, the fundamental connection between multi-value alignment and sequential alignment, and proving that linear weighted rewards are sufficient for multi-value alignment. Extensive experiments demonstrate MAP's ability to align multiple values in a principled manner while delivering strong empirical performance across various tasks.

Related papers

• 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)
• Aligning LLMs with Individual Preferences via Interaction [51.72200436159636]
  We train large language models (LLMs) that can ''interact to align'' We develop a multi-turn preference dataset containing 3K+ multi-turn conversations in tree structures. For evaluation, we establish the ALOE benchmark, consisting of 100 carefully selected examples and well-designed metrics to measure the customized alignment performance during conversations.
  arXiv  Detail & Related papers  (2024-10-04T17:48:29Z)
• ValueCompass: A Framework of Fundamental Values for Human-AI Alignment [15.35489011078817]
  We introduce Value, a framework of fundamental values, grounded in psychological theory and a systematic review. We apply Value to measure the value alignment of humans and language models (LMs) across four real-world vignettes. Our findings uncover risky misalignment between humans and LMs, such as LMs agreeing with values like "Choose Own Goals", which are largely disagreed by humans.
  arXiv  Detail & Related papers  (2024-09-15T02:13:03Z)
• Towards Bidirectional Human-AI Alignment: A Systematic Review for Clarifications, Framework, and Future Directions [101.67121669727354]
  Recent advancements in AI have highlighted the importance of guiding AI systems towards the intended goals, ethical principles, and values of individuals and groups, a concept broadly recognized as alignment. The lack of clarified definitions and scopes of human-AI alignment poses a significant obstacle, hampering collaborative efforts across research domains to achieve this alignment. We introduce a systematic review of over 400 papers published between 2019 and January 2024, spanning multiple domains such as Human-Computer Interaction (HCI), Natural Language Processing (NLP), Machine Learning (ML)
  arXiv  Detail & Related papers  (2024-06-13T16:03:25Z)
• Joint Demonstration and Preference Learning Improves Policy Alignment with Human Feedback [58.049113055986375]
  We develop a single stage approach named Alignment with Integrated Human Feedback (AIHF) to train reward models and the policy. The proposed approach admits a suite of efficient algorithms, which can easily reduce to, and leverage, popular alignment algorithms. We demonstrate the efficiency of the proposed solutions with extensive experiments involving alignment problems in LLMs and robotic control problems in MuJoCo.
  arXiv  Detail & Related papers  (2024-06-11T01:20:53Z)
• Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment [103.12563033438715]
  Alignment in artificial intelligence pursues consistency between model responses and human preferences as well as values. Existing alignment techniques are mostly unidirectional, leading to suboptimal trade-offs and poor flexibility over various objectives. We introduce controllable preference optimization (CPO), which explicitly specifies preference scores for different objectives.
  arXiv  Detail & Related papers  (2024-02-29T12:12:30Z)
• 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)
• Multi-Value Alignment in Normative Multi-Agent System: Evolutionary Optimisation Approach [1.160208922584163]
  This research proposes a multi-value promotion model that uses multi-objective evolutionary algorithms to produce the optimum parametric set of norms. Several evolutionary algorithms were used to find a set of optimised norm parameters considering two toy tax scenarios with two and five values are considered.
  arXiv  Detail & Related papers  (2023-05-12T10:30:20Z)
• What are you optimizing for? Aligning Recommender Systems with Human Values [9.678391591582582]
  We describe cases where real recommender systems were modified in the service of various human values. We look to AI alignment work for approaches that could learn complex values directly from stakeholders.
  arXiv  Detail & Related papers  (2021-07-22T21:52:43Z)

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.