Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Gary Geunbae Lee

Gary Geunbae Lee

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

NLP×2AI×2

Frequent co-authors

Deokhyung Kang1×
Hyounghun Kim1×
Sangwon Ryu1×
Yihong Liu1×
Mingyang Wang1×
Yunsu Kim1×

Research Timeline

2026
Understanding LLM Behavior in Multi-Target Cross-Lingual Summarization

The paper introduces a new benchmark for multi-target cross-lingual summarization (MTXLS) and proposes an activation steering method that significantly improves LLM performance by guiding the generation process using English representations.

Learning When to Translate for Multilingual Reasoning

The paper proposes Luar, a framework that trains reasoning language models to selectively use English translation only when their direct understanding of a non-English input is unreliable, significantly improving multilingual reasoning.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.AIRecentJun 1, 2026

Learning When to Translate for Multilingual Reasoning

Deokhyung Kang, Hyounghun Kim, Gary Geunbae Lee

The paper proposes Luar, a framework that trains reasoning language models to selectively use English translation only when their direct understanding of a non-English input is unreliable, significant…

View →
cs.CLcs.AIRecentMay 31, 2026

Understanding LLM Behavior in Multi-Target Cross-Lingual Summarization

Sangwon Ryu, Yihong Liu, Mingyang Wang, Yunsu Kim +3 more

The paper introduces a new benchmark for multi-target cross-lingual summarization (MTXLS) and proposes an activation steering method that significantly improves LLM performance by guiding the generati…

View →