paper-with-me

Papers

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

2025-10-07 · Rikuto Kotoge, Yuichi Sasaki arxiv

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 primarily require paired desirable and undesirable samples at the utterance level. However, such pairs are often limited in TTS output data, and utterance-level formulation prevents fine-grained token-level optimization needed for accurate pronunciation alignment. In this study, we propose TKTO that eliminates the need for paired data, enabling a more data-efficient training paradigm, and directly targets token-level units, automatically providing fine-grained alignment signals without token-level annotations. TKTO improves the challenging Japanese TTS accuracy by 39% and reduces CER by 54%, automatically assigning 12.8 times stronger reward to targeted tokens.

📄 PDF Abstract BibTeX arXiv:2510.05799

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization

2025-06-10 · Hee Suk Yoon, Eunseop Yoon, Mark Hasegawa-Johnson, Sungwoong Kim 외

We introduce ConfPO, a method for preference learning in Large Language Models (LLMs) that identifies and optimizes preference-critical tokens based solely on the training policy's confidence, without requiring any auxil…

TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching

2026-05-12 · Truong Nguyen, Tien-Phat Nguyen, Linh Ngo Van, Duy Minh Ho Nguyen 외 arxiv

Direct Preference Optimization (DPO) is a widely used RL-free method for aligning language models from pairwise preferences, but it models preferences over full sequences even though generation is driven by per-token dec…

Instruction Following

DEPO: Dual-Efficiency Preference Optimization for LLM Agents

2025-11-19 · Sirui Chen, Mengshi Zhao, Lei Xu, Yuying Zhao 외 arxiv

Recent advances in large language models (LLMs) have greatly improved their reasoning and decision-making abilities when deployed as agents. Richer reasoning, however, often comes at the cost of longer chain of thought (…

Token Preference Optimization with Self-Calibrated Visual-Anchored Rewards for Hallucination Mitigation

2024-12-19 · Jihao Gu, Yingyao Wang, Meng Cao, Pi Bu 외

Direct Preference Optimization (DPO) has been demonstrated to be highly effective in mitigating hallucinations in Large Vision Language Models (LVLMs) by aligning their outputs more closely with human preferences. Despit…

Hallucination

Selective Preference Optimization via Token-Level Reward Function Estimation

2024-08-24 · Kailai Yang, Zhiwei Liu, Qianqian Xie, Jimin Huang 외

Recent advancements in large language model alignment leverage token-level supervisions to perform fine-grained preference optimization. However, existing token-level alignment methods either optimize on all available to…

Language ModellingLarge Language Model