Yi Wu
@yi-wu.bsky.social
CS master student at The University of Chicago, working with @chenhaotan.bsky.social
Reposted by Yi Wu
1/n
You may know that large language models (LLMs) can be biased in their decision-making, but ever wondered how those biases are encoded internally and whether we can surgically remove them?
You may know that large language models (LLMs) can be biased in their decision-making, but ever wondered how those biases are encoded internally and whether we can surgically remove them?
April 14, 2025 at 7:55 PM
1/n
You may know that large language models (LLMs) can be biased in their decision-making, but ever wondered how those biases are encoded internally and whether we can surgically remove them?
You may know that large language models (LLMs) can be biased in their decision-making, but ever wondered how those biases are encoded internally and whether we can surgically remove them?