17 papers · 1 filter
Region4Web: Rethinking Observation Space Granularity for Web Agents
Donguk Kwon, Dongha Lee
Web agents perceive web pages through an observation space, yet its granularity has remained an underexamined design choice. Existing work treats observation at the same element-le…
CONDESION-BENCH: Conditional Decision-Making of Large Language Models in Compositional Action Space
Yeonjun Hwang, Sungyong Park, Minju Kim +2
Large language models have been widely explored as decision-support tools in high-stakes domains due to their contextual understanding and reasoning capabilities. However, existing…
Quantifying Genuine Awareness in Hallucination Prediction Beyond Question-Side Shortcuts
Yeongbin Seo, Dongha Lee, Jinyoung Yeo
Many works have proposed methodologies for language model (LM) hallucination detection and reported seemingly strong performance. However, we argue that the reported performance to…
RPM: Reasoning-Level Personalization for Black-Box Large Language Models
Jieyong Kim, Tongyoung Kim, Soojin Yoon +2
While black-box large language models are widely deployed, they produce generic outputs that overlook individual user preferences. Current personalization methods are fundamentally…
Can Code-Switched Texts Activate a Knowledge Switch in LLMs? A Case Study on English-Korean Code-Switching
Seoyeon Kim, Huiseo Kim, Chanjun Park +2
Recent large language models (LLMs) demonstrate multilingual abilities, yet they are English-centric due to dominance of English in training corpora. The limited resource for low-r…
Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning
Yeongbin Seo, Dongha Lee, Jaehyung Kim +1
Autoregressive (AR) language models generate text one token at a time, which limits their inference speed. Diffusion-based language models offer a promising alternative, as they ca…