7 papers
KMMMU: Evaluation of Massive Multi-discipline Multimodal Understanding in Korean Language and Context
Nahyun Lee, Guijin Son, Hyunwoo Ko +4
Multimodal evaluation is strengthened when benchmarks reflect the languages, institutions, and disciplinary conventions that shape expert visual reasoning. We introduce KMMMU, a na…
EXAONE 4.5 Technical Report
Eunbi Choi, Kibong Choi, Sehyun Chun +55
This technical report introduces EXAONE 4.5, the first open-weight vision language model released by LG AI Research. EXAONE 4.5 is architected by integrating a dedicated visual enc…
LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understanding
Zhivar Sourati, Zheng Wang, Marianne Menglin Liu +8
Question answering over visually rich documents (VRDs) requires reasoning not only over isolated content but also over documents' structural organization and cross-page dependencie…
KAIO: A Collection of More Challenging Korean Questions
Nahyun Lee, Guijin Son, Hyunwoo Ko +1
With the advancement of mid/post-training techniques, LLMs are pushing their boundaries at an accelerated pace. Legacy benchmarks saturate quickly (e.g., broad suites like MMLU ove…
Exploring the Impact of Instruction-Tuning on LLM's Susceptibility to Misinformation
Kyubeen Han, Junseo Jang, Hongjin Kim +2
Instruction-tuning enhances the ability of large language models (LLMs) to follow user instructions more accurately, improving usability while reducing harmful outputs. However, th…
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…
Faithful, Unfaithful or Ambiguous? Multi-Agent Debate with Initial Stance for Summary Evaluation
Mahnaz Koupaee, Jake W. Vincent, Saab Mansour +9
Faithfulness evaluators based on large language models (LLMs) are often fooled by the fluency of the text and struggle with identifying errors in the summaries. We propose an appro…