12:["$","div",null,{"className":"Post_post__BuG2d","style":{"display":"flex","flexDirection":"column","gap":"0.1rem","width":"100%","boxShadow":"0.2rem 0.2rem 0.4rem var(--shadow-color), inset 0.08rem 0.12rem 0.06rem var(--grow-color), inset -0.08rem -0.12rem 0.06rem var(--shade-color)","borderRadius":"none","padding":"1.4rem 8vw"},"children":[["$","div",null,{"className":"$undefined","style":{"display":"flex","gap":"0.4rem","flexWrap":"wrap"},"children":[false,[["$","a","E7F3",{"href":"/E7F3","style":{"border":"solid 1px var(--post-edge-color)","borderBottom":"none","borderRadius":"0.6rem 0.6rem 0 0","padding":"0.1rem 0.5rem"},"children":"DPO"}]]]}],["$","article",null,{"className":"article","children":[["$","div",null,{"className":"$undefined","style":{"display":"flex","justifyContent":"space-between","flexWrap":"wrap"},"children":[["$","h2",null,{"style":{"margin":"0.6rem"},"children":["$","a",null,{"href":"///AA42","children":"『Direct Preference Optimization: Your Language Model is Secretly a Reward Model』"}]}],["$","div",null,{"className":"$undefined","style":{"display":"flex","justifyContent":"end","alignItems":"center","flex":"1","textAlign":"right","whiteSpace":"nowrap"},"children":["$","div",null,{"children":"2024/3/10 13:46:00"}]}]]}],["$","div",null,{"className":"article_body","dangerouslySetInnerHTML":{"__html":"

https://arxiv.org/abs/2305.18290\n

"}}]]}],["$","div",null,{"className":"$undefined","style":{"display":"flex","gap":"0.4rem","flexWrap":"wrap"},"children":[["$","a","",{"href":"/","style":{"border":"solid 1px var(--post-edge-color)","borderTop":"none","borderRadius":"0 0 0.6rem 0.6rem","padding":"0.1rem 0.5rem","opacity":0},"children":"あれ"}],[]]}]]}]