2 papers
cs.LG2026
Suan: Rectifying Direct Preference Safety Alignment in Large Language Models
Oleksandr Cherednichenko, Roman Klypa
Integrating robust safety guardrails into Large Language Models (LLMs) is essential for delivering helpful yet harmless responses. While proprietary systems exhibit reliable safety…
cs.LG2026
Diversity in Large Language Models under Supervised Fine-Tuning
Roman Klypa, Oleksandr Cherednichenko
Supervised Fine-Tuning (SFT) is essential for aligning Large Language Models (LLMs) with user intent, yet it is believed to suppress generative diversity. Although this reduction i…