惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

GbyAI
GbyAI
阮一峰的网络日志
阮一峰的网络日志
G
Google Developers Blog
J
Java Code Geeks
Blog — PlanetScale
Blog — PlanetScale
大猫的无限游戏
大猫的无限游戏
云风的 BLOG
云风的 BLOG
Vercel News
Vercel News
L
LangChain Blog
Hugging Face - Blog
Hugging Face - Blog
T
The Blog of Author Tim Ferriss
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
Stack Overflow Blog
Stack Overflow Blog
P
Proofpoint News Feed
腾讯CDC
博客园_首页
博客园 - 聂微东
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
M
MIT News - Artificial intelligence
WordPress大学
WordPress大学
D
DataBreaches.Net
Microsoft Security Blog
Microsoft Security Blog
有赞技术团队
有赞技术团队
博客园 - 叶小钗

cs.HC updates on arXiv.org

From Prompt to Service: An SLM-Based Agent Orchestration Gateway for AI-Driven Virtual Worlds What LLMs Must Forget to Teach Effectively: A DIY Approach to Premodern Japanese Language Pedagogy Quantitative Movement Testing: Measuring Patient Movements from a Single Smartphone Video Vision-Language Models Suppress Female Representations Under Ambiguous Input The New Social Image: How AI Competency and AI Proactivity Influence Self- and Peer-Perceptions in the Workplace TUX: Measuring Human--AI Tacit Understanding LLUMI: Improving LLM Writing Assistance for Mental Health Support with Online Community Feedback VideoFDB: Evaluating Full-Duplex Vision-Speech Capabilities in Conversational Agents Label Over Logic? How Source Cues Bias Human Fallacy Judgments More Than LLMs Inform, Coach, Relate, Listen: Auditing LLM Caregiving Support Roles How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessions MetaRanker: Human-in-the-loop Active Ranking for Metalens Image Quality Analyzing Persona Effects in Generated Explanations from Multimodal LLM Agents in Urban Perception First head-to-head comparison of agentic AI applied to the analysis of simulated data of the Einstein Telescope Granuscore: A Reference-Free Measure of Granularity for Text Analysis and Question Answering The Timing Dependencies of Trust: Speed, Accuracy, and cBCI Neuro-Decoupling in Human-AI Teams Bayesian Distributional Models of Executive Functioning Visual Matters: Connecting Aesthetic Appeal and Production Quality of Photos, Infographics and Data Visualizations to Credibility of Social Media Posts Data-driven Head Motion Generation through Natural Gaze-Head Coordination Agreement Metrics for LLM-as-Judge Evaluation: What to Report and Why Perceptually Lossless Tactile Texture Synthesis with Compact Spectral Envelope Models MambaGaze: Bidirectional Mamba with Explicit Missing Data Modeling for Cognitive Load Assessment from Eye-Gaze Tracking Data CogAdapt: Transferring Clinical ECG Foundation Models to Wearable Cognitive Load Assessment via Lead Adaptation Augmented Analytics and Decision Quality: The Role of Trust among Non-Technical BI Users Faster Completion, Less Learning: Generative AI Reduced Study Time on Math Problems and the Knowledge They Build PaintCopilot: Modeling Painting as Autonomous Artistic Continuation Personality Engineering with AI Agents: A New Methodology for Negotiation Research PULSE: Agentic Investigation with Passive Sensing for Proactive Intervention in Cancer Survivorship Access Timing as Scaffolding: A Reinforcement Learning Approach to GenAI in Education MAPLE: Self-Supervised Learning-Enhanced Nonlinear Dimensionality Reduction for Visual Analysis
MAP: Multi-Human-Value Alignment Palette
Xinran Wang, Qi Le, Ammar Ahmed, Enmao Diao, Yi Zhou, Nathalie B · 2024-10-25 · via cs.HC updates on arXiv.org

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.