answer conditioning 1chain of thought 1knowledge distillation 1large language models 1verifiable reasoning 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.CL2026
Answer-Conditioned Chains of Thought Degrade Verifiable-Reasoning Distillation in Large Language Models
Jungseob Lee, Seungyoon Lee, Suhyune Son +4
The paper shows that conditioning large language models on the correct answer when generating chains of thought harms the quality of distilled reasoning data, leading to large drop…
cs.AI2026
Skin-Deep: A Geometric Diagnostic for Alignment Fragility in Large Language Model Representations
Dongyub Jude Lee, Jungseob Lee, Seungyoon Lee +5
Alignment tuning is meant to make harmful-request refusal robust, yet this safety behavior can be erased by a small set of benign fine-tuning examples. This is a deployment risk fo…