diff --git a/index.html b/index.html
index 177e032..0232b90 100644
--- a/index.html
+++ b/index.html
@@ -254,7 +254,7 @@ <h2 class="title is-3">Retrieval Performance</h2>
                         <h2 class="subtitle has-text-centered">
                             Figure 2: The retrieval performance on NQ.
                         </h2>
-                        <p>
+                        <p style="text-align: left;">
                             Employing a long-context retriever (with an average number of tokens for each retrieval unit up to 6K) compresses the corpus size by up to 30 times (from 22M to
                             600K), enhancing top-1 answer recall by approximately 20 points (from 52.24 to 71.69). Furthermore, long-context retrieval requires significantly fewer retrieval
                             units (10 times fewer) to achieve comparable results. Therefore, integrating long-context retrieval significantly alleviates the burden on the retriever model.
@@ -267,7 +267,7 @@ <h2 class="subtitle has-text-centered">
                         <h2 class="subtitle has-text-centered">
                             Figure 2: The retrieval performance on HotpotQA.
                         </h2>
-                        <p>
+                        <p style="text-align: left;">
                             Similar to the findings on NQ, a long-context retrieval could significantly alleviate the burden on the retriever component within the entire RAG framework.
                         </p>
                     </div>