Add pipeline tag and library name, include paper abstract

README.md

@@ -1,9 +1,11 @@
 ---
-license: mit
-datasets:
-- tsunghanwu/reverse-instruct-1.3m
 base_model:
 - meta-llama/Llama-3.1-8B-Instruct
+datasets:
+- tsunghanwu/reverse-instruct-1.3m
+license: mit
+pipeline_tag: image-text-to-text
+library_name: transformers
 ---
 
 # REVERSE-LLaVA-MORE-8B
@@ -60,4 +62,8 @@ Please refer to the installation guide on GitHub to get started:
 - Research on grounded and trustworthy multimodal reasoning
 
 **Target Users:**  
-Researchers, developers, and students working on VLMs, hallucination mitigation, and vision-language alignment.
+Researchers, developers, and students working on VLMs, hallucination mitigation, and vision-language alignment.
+
+## Paper abstract
+
+Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling