2 papers
cs.CL2026
Can LLMs Normalize Databases? A Benchmark and Multi-Agent Framework for Schema Normalization
Dong-Jae Koh, Huisu Kim, SeongHwan Yoon +4
Large Language Models (LLMs) are increasingly used to generate structured outputs, but their reliability remains unclear when those outputs must satisfy database-level constraints.…
cs.LG2026
Dual Path Attribution: Efficient Attribution for SwiGLU-Transformers through Layer-Wise Target Propagation
Lasse Marten Jantsch, Dong-Jae Koh, Seonghyeon Lee +1
Understanding the internal mechanisms of transformer-based large language models (LLMs) is crucial for their reliable deployment and effective operation. While recent efforts have…