新着スライド
【DL輪読会】 SAFECHAIN: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities
Deep Learning JP
1.1K
【DL輪読会】Prompt-to-SQL Injections in LLM-Integrated Web Applications: Risks and Defenses
Deep Learning JP
852
【DL輪読会】Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
Deep Learning JP
881
