4 papers
MEMORY Wins All: Indirect Bias Injection Attacks via Social Media Feeds
Minjae Seo, Wonwoo Choi, Geonwoo Han +7
Personal AI agents routinely consume external content while performing tasks such as web browsing, email processing, and SNS feed summarization, and they retain selected informatio…
An Evaluation of Data Leakage Risks in Tool-Using LLM Agents in Realistic Scenarios
Hankyul Baek, Jaewon Noh, Sang Seo +5
AI agents are increasingly being adopted in enterprise and personal settings with access to emails, databases, documents, and other tools where they can read, update, and dissemina…
XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity
Dasol Choi, Eugenia Kim, Jaewon Noh +14
Current LLM safety benchmarks are predominantly English-centric and often rely on translation, failing to capture country-specific harms. Moreover, they rarely evaluate a model's a…
EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes
Kyunghoon Bae, Eunbi Choi, Kibong Choi +37
This technical report introduces EXAONE 4.0, which integrates a Non-reasoning mode and a Reasoning mode to achieve both the excellent usability of EXAONE 3.5 and the advanced reaso…