2026
Fine-Tuned LLMs Know They Don’t Know: A Parameter-Efficient Approach to Recovering Honesty
AAAI 2026technical
The honesty of Large Language Models (LLMs) is increasingly important for safe deployment in high-stakes domains. However, this crucial trait is severely undermined by supervised fine-tuning (SFT), a common technique for model specialization. Existing recovery methods rely on data-intensive global p