paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达
登录 DINQ
返回新星榜
DK

Daisuke Kawahara

ACL 2026×3检索与知识强化学习与后训练社会与人本评测与基准推理
新星分资深
14
一作贡献0
核心/参与5
方向广度10
合作网络0
0 一作 · 3 篇 · ACL 2026

获取完整研究档案

首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。

联系方式

实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。

2026 顶会论文

3
作者位次 #2/2ACL 2026Workshop· Natural Language Processing

Constructing a J apanese Rap Lyric Generation Model with GRPO

Hayato Ogawa · Daisuke Kawahara

摘要

Rap is a vocal style rooted in Hip-Hop culture, characterized by producing rhymes in synchrony with a rhythmic beat.This paper proposes a method for generating Japanese rap lyrics with a large language model (LLM) whose rhyming behavior is improved via reinforcement learning.We design a reward fu...

强化学习与后训练社会与人本评测与基准OpenReview 项目页
作者位次 #9/9ACL 2026Workshop· Natural Language Processing

Constructing a J apanese Verdict Prediction Dataset for Fact-Checking of LLM -Generated Texts

Miwa Masano · Hirokazu Kiyomaru · Atsushi Keyaki · Kaito Horio · Rei Minamoto · Ribeka Keyaki · Kouta Nakayama · Hideyuki Tachibana · Daisuke Kawahara

摘要

The development of fact-checking systems for verifying the factuality of text generated by large language models (LLMs) has been advancing.In the verdict prediction step of such systems, the system determines whether claims in the generated text are supported by retrieved evidence, formulated as...

推理检索与知识可解释性OpenReview 项目页
作者位次 #3/3ACL 2026Findings· Findings of ACL

Detecting Sensitive Personal Information in J apanese Pre-Training Corpora for Large Language Models

Rei Minamoto · Yusuke Oda · Daisuke Kawahara

摘要

Sensitive personal information can appear in large-scale pre-training corpora for large language models (LLMs). Detecting and filtering such information is therefore essential to ensure compliance with privacy regulations and prevent unintended information leakage. However, in contrast to English...

数据与预训练安全检索与知识OpenReview 项目页

常见合作者