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

Ukyo Honda

ACL 2026×2推理评测与基准检索与知识智能体与工具效率与系统
新星分资深
22
一作贡献0
核心/参与12
方向广度10
合作网络3
0 一作 · 2 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

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

Does Self-Consistency Improve the Recall of Encyclopedic Knowledge?

Sho Hoshino · Ukyo Honda · Peinan Zhang

摘要

While self-consistency is known to improve performance on symbolic reasoning, its effect on the recall of encyclopedic knowledge is unclear due to a lack of targeted evaluation grounds. To address this, we establish such a knowledge recall split for the popular MMLU benchmark by applying a data-d...

推理评测与基准检索与知识OpenReview 项目页
作者位次 #3/3ACL 2026Findings· Findings of ACL

B i CSR outer: Bi-Level Cross-System Routing for Utility-Aware LLM Inference

Mao Keyu · Eiki Murata · Ukyo Honda

摘要

Selecting an appropriate LLM configuration for a given query is critical, yet existing routing frameworks operate within a single computational paradigm. To address this gap, we formalize the Cross-System Routing Problem, a hierarchical decision-making task that decomposes routing into intra-regi...

推理智能体与工具效率与系统OpenReview 项目页

常见合作者