会员服务
Layer of Truth: Probing Belief Shifts under Continual Pre-Training Poisoning
Arxiv
0+阅读 · 2月3日
PretrainRL: Alleviating Factuality Hallucination of Large Language Models at the Beginning
Arxiv
0+阅读 · 2月2日
Self-Blinding and Counterfactual Self-Simulation Mitigate Biases and Sycophancy in Large Language Models
Arxiv
0+阅读 · 1月21日
What Does Loss Optimization Actually Teach, If Anything? Knowledge Dynamics in Continual Pre-training of LLMs
Arxiv
0+阅读 · 1月7日
Through a Compressed Lens: Investigating The Impact of Quantization on Factual Knowledge Recall
Arxiv
0+阅读 · 1月1日
参考链接
微信扫码咨询专知VIP会员
Top