Supervised fine-tuning increases LLM hallucinations via interference among overlapping semantic representations; self-distillation mitigates this by regularizing output-distribution drift while freezing parameters preserves performance when new facts are unnecessary.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Why Fine-Tuning Encourages Hallucinations and How to Fix It
Supervised fine-tuning increases LLM hallucinations via interference among overlapping semantic representations; self-distillation mitigates this by regularizing output-distribution drift while freezing parameters preserves performance when new facts are unnecessary.