按年被提到
20262026 · 3 次2026
AI 安全、伦理与社会影响›大模型与人类行为·arXiv:2603.18507 · cs.AI

Expert Personas Improve LLM Alignment but Damage Accuracy: Bootstrapping Intent-Based Persona Routing with PRISM

Zizhao Hu, Mohammad Rostami, Jesse Thomason · 2026
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 3 人首次 2026-03-24 · 最近 2026-06-13
3不同的人
2活跃月份
3讨论串
2被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Persona prompting can steer LLM generation towards a domain-specific tone and pattern. This behavior enables use cases in multi-agent systems where diverse interactions are crucial and human-centered tasks require high-level human alignment. Prior works provide mixed opinions on their utility: some report performance gains when using expert personas for certain domains and their contribution to data diversity in synthetic data creation, while others find near-zero or negative impact on general utility. To fully leverage the benefits of the LLM persona and avoid its harmfulness, a more comprehensive investigation of the mechanism is crucial. In this work, we study how model optimization, task type, prompt length, and placement can impact expert persona effectiveness across instruction-tuned and reasoning LLMs, and provide insight into conditions under which expert personas fail and succeed. Based on our findings, we developed a pipeline to fully leverage the benefits of an expert persona, named PRISM (Persona Routing via Intent-based Self-Modeling), which self-distills an intent-conditioned expert persona into a gated LoRA adapter through a bootstrapping process that requires no external data, models, or knowledge. PRISM enhances human preference and safety alignment on generative tasks while maintaining accuracy on discriminative tasks across all models, with minimal memory and computing overhead.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论not_a_bot_4sho · 2026-06

“Back with some papers. (Apologies in advance; I typically don't edit/format comments much here, please bear with me.) Notable papers describing performance improvements with prescribed roles and personas: - ExpertPrompting: Instructing Large Language Models to be Distinguished Experts (2023) https://arxiv.org/abs/2305.14688 (if you're going to only read…”

"Don't You Just Upload It to ChatGPT?"原评论 ↗
被提交为 story · 2 次