Picture for Sooah Cho

Sooah Cho

Correcting Negative Bias in Large Language Models through Negative Attention Score Alignment

Add code
Jul 31, 2024
Figure 1 for Correcting Negative Bias in Large Language Models through Negative Attention Score Alignment
Figure 2 for Correcting Negative Bias in Large Language Models through Negative Attention Score Alignment
Figure 3 for Correcting Negative Bias in Large Language Models through Negative Attention Score Alignment
Figure 4 for Correcting Negative Bias in Large Language Models through Negative Attention Score Alignment
Viaarxiv icon