English(EN) Data-efficient Targeted Token-level Preference Optimization for LLM-based Text-to-Speech

LLM偏好优化提升TTS准确性和用户个性化

作者 PulseAugur 编辑部 · [2 个来源] · 2026-04-28 04:00

研究人员开发了新的方法来使大型语言模型（LLM）与用户偏好保持一致。一种方法TKTO专注于文本到语音系统，实现了数据高效的Token级优化，以提高发音准确性并减少错误。另一个框架POPI通过将过程分解为偏好摘要生成器和响应生成器来解决LLM个性化问题，从而实现用户特定的输出并减少上下文开销。 AI

影响 LLM对齐和个性化方面的新技术可能带来更准确和用户定制的AI应用。

排序理由该集群包含两篇arXiv论文，详细介绍了LLM对齐和个性化的新方法。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CL TIER_1 English(EN) · Rikuto Kotoge, Yuichi Sasaki · 2026-04-28 04:00

Data-efficient Targeted Token-level Preference Optimization for LLM-based Text-to-Speech

arXiv:2510.05799v2 Announce Type: replace Abstract: Aligning text-to-speech (TTS) system outputs with human feedback through preference optimization has been shown to effectively improve the robustness and naturalness of language model-based TTS models. Current approaches primari…
arXiv cs.CL TIER_1 English(EN) · Yizhuo Chen, Xin Liu, Ruijie Wang, Zheng Li, Pei Chen, Changlong Yu, Qingyu Yin, Priyanka Nigam, Meng Jiang, Bing Yin · 2026-04-28 04:00

POPI: Personalizing LLMs via Optimized Natural Language Preference Inference

arXiv:2510.17881v3 Announce Type: replace Abstract: Large language models (LLMs) are typically aligned with population-level preferences, despite substantial variation across individual users. We introduce POPI, a user-level personalization framework that separates the problem in…