diff --git a/mle/agents/advisor.py b/mle/agents/advisor.py
index a48f2bf..ed5d79d 100644
--- a/mle/agents/advisor.py
+++ b/mle/agents/advisor.py
@@ -55,7 +55,7 @@ def __init__(self, model, console=None):
          the model (or method), and the evaluation metrics, etc. You should always follow the user's requirements.
         2. You should briefly analyze the user's dataset, and give a summary of the dataset, the dataset input can be
          a public dataset name or a path to a local CSV file. You can use the function `preview_csv_data` to preview
-         the CSV file.
+         the CSV file or not if the dataset is a public dataset.
         3. And then you should always use the function `search_arxiv` or `search_papers_with_code` to search the
          state-of-the-art machine learning tasks/models/algorithms that can be used to solve the user's requirements,
           and stay up-to-date with the latest.
diff --git a/mle/cli.py b/mle/cli.py
index 08a0bda..ea494aa 100644
--- a/mle/cli.py
+++ b/mle/cli.py
@@ -40,7 +40,7 @@ def cli():
 
 @cli.command()
 @click.pass_context
-@click.argument('mode', default='general')
+@click.argument('mode', default='baseline')
 @click.option('--model', default=None, help='The model to use for the chat.')
 def start(ctx, mode, model):
     """
@@ -49,14 +49,14 @@ def start(ctx, mode, model):
     if not check_config(console):
         return
 
-    if mode == 'general':
+    if mode == 'baseline':
         # Baseline mode
         return workflow.baseline(os.getcwd(), model)
     elif mode == 'report':
         # Report mode
         return ctx.invoke(report, model=model, visualize=False)
     else:
-        raise ValueError("Invalid mode. Supported modes: 'general', 'report'.")
+        raise ValueError("Invalid mode. Supported modes: 'baseline', 'report'.")
 
 
 @cli.command()