3 accepted papers
Reverse Chain-of-Thought Generation (RCG) synthesizes reasoning traces from query-answer pairs, but runs the risk of producing post-hoc rationalizations: when models can see the answer during generation, the answer serves as a cognitive anchor that shapes the entire explanation. We formalize this ph…
Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they often exhibit a specific cultural bias, neglecting the values and linguistic diversity of low-resource regions. This cultural bias not only undermines universal equality but also risks reinforcing s…
The unlearning method aims at effectively removing harmful, sensitive, or outdated knowledge without costly retraining the model. However, existing methods suffer from two critical limitations: (1) collateral forgetting, where erasing target data inadvertently removes related but desirable knowledge