让大模型从问答工具变身为懂人性的陪伴者支持系统
Beyond Chat: a Framework for LLMs as Human-Centered Support Systems
- 基于角色设计人本化支持框架，涵盖陪伴、指导等多元角色
- 提出信任、参与度与长期效果等超越准确率的评估指标
- 聚焦隐私保护与情感共情平衡，适合心理辅导等敏感场景
大语言模型正从简单的问答工具演进为陪伴者、教练、调解者与内容策展人，辅助人类成长、决策与福祉。本文提出一种基于角色的人本化大模型支持系统框架，对比了跨领域真实部署案例，提炼出透明性、个性化、安全边界、带隐私的记忆机制以及共情与可靠性的平衡等通用设计原则。同时，提出涵盖信任、参与度与长期成效的评估体系，分析了过度依赖、幻觉、偏见、隐私泄露与访问不均等风险，并展望统一评估、人机混合模型、记忆架构、跨领域基准测试与治理机制等未来方向。目标是实现大模型在需陪伴与引导的敏感场景中负责任地集成。
原文摘要 · Abstract (English)
Large language models are moving beyond transactional question answering to act as companions, coaches, mediators, and curators that scaffold human growth, decision-making, and well-being. This paper proposes a role-based framework for human-centered LLM support systems, compares real deployments across domains, and identifies cross-cutting design principles: transparency, personalization, guardrails, memory with privacy, and a balance of empathy and reliability. It outlines evaluation metrics that extend beyond accuracy to trust, engagement, and longitudinal outcomes. It also analyzes risks including over-reliance, hallucination, bias, privacy exposure, and unequal access, and proposes future directions spanning unified evaluation, hybrid human-AI models, memory architectures, cross-domain benchmarking, and governance. The goal is to support responsible integration of LLMs in sensitive settings where people need accompaniment and guidance, not only answers.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。