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

Junghwan Kim

ACL 2026×2社会与人本可解释性安全对齐与偏好数据与预训练
新星分新星
60
一作贡献30
核心/参与5
方向广度10
合作网络6
1 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
一作ACL 2026Findings· Findings of ACL

Interpreting Style Representations via Style-Eliciting Prompts

Junghwan Kim · David Jurgens

摘要

Style representation learning is a powerful tool for authorship analysis and modeling writing style, yet the latent nature of learned representations makes them difficult to interpret. Recent work has attempted to explain these representations by generating natural language descriptions with larg...

可解释性社会与人本安全OpenReview 项目页
作者位次 #9/15ACL 2026Findings· Findings of ACL

Real or Robotic? Assessing Whether LLM s Accurately Simulate Qualities of Human Responses in Human- LLM Dialogue

Jonathan Ivey · Shivani Kumar · Jiayu Liu · Hua Shen · Sushrita Rakshit · Rohan Raju · Haotian Zhang · Aparna Ananthasubramaniam · Junghwan Kim · Bowen Yi · Dustin Wright · Abraham Israeli · Anders Giovanni Møller · Lechen Zhang · David Jurgens

摘要

Building datasets for dialogue tasks is expensive and time-consuming, requiring recruitment, training, and data collection from study participants. In response, much recent work has sought to use large language models (LLMs) to simulate both human-human and human-LLM interactions, as they have be...

社会与人本对齐与偏好数据与预训练OpenReview 项目页

常见合作者