update

app.py

@@ -25,7 +25,7 @@ from nltk.tokenize import sent_tokenize
 
 # Load original app constants
 APP_TITLE = '<div class="app-title"><span class="brand">AttnTrace: </span><span class="subtitle">Attention-based Context Traceback for Long-Context LLMs</span></div>'
-APP_DESCRIPTION = """AttnTrace traces a model's generated statements back to specific parts of the context using attention-based traceback. Try it out with Meta-Llama-3.1-8B-Instruct here! See the [[paper](https://arxiv.org/abs/2506.04202)] and [[code](https://github.com/Wang-Yanting/TracLLM-Kit)] for more!
+APP_DESCRIPTION = """AttnTrace traces a model's generated statements back to specific parts of the context using attention-based traceback. Try it out with Meta-Llama-3.1-8B-Instruct here! See the [[paper](https://arxiv.org/abs/2508.03793)] and [[code](https://github.com/Wang-Yanting/AttnTrace)] for more!
 Maintained by the AttnTrace team."""
 # NEW_TEXT = """Long-context large language models (LLMs), such as Gemini-2.5-Pro and Claude-Sonnet-4, are increasingly used to empower advanced AI systems, including retrieval-augmented generation (RAG) pipelines and autonomous agents. In these systems, an LLM receives an instruction along with a context—often consisting of texts retrieved from a knowledge database or memory—and generates a response that is contextually grounded by following the instruction. Recent studies have designed solutions to trace back to a subset of texts in the context that contributes most to the response generated by the LLM. These solutions have numerous real-world applications, including performing post-attack forensic analysis and improving the interpretability and trustworthiness of LLM outputs. While significant efforts have been made, state-of-the-art solutions such as TracLLM often lead to a high computation cost, e.g., it takes TracLLM hundreds of seconds to perform traceback for a single response-context pair. In this work, we propose {\name}, a new context traceback method based on the attention weights produced by an LLM for a prompt. To effectively utilize attention weights, we introduce two techniques designed to enhance the effectiveness of {\name}, and we provide theoretical insights for our design choice. %Moreover, we perform both theoretical analysis and empirical evaluation to demonstrate their effectiveness. 
 # We also perform a systematic evaluation for {\name}. The results demonstrate that {\name} is more accurate and efficient than existing state-of-the-art context traceback methods. We also show {\name} can improve state-of-the-art methods in detecting prompt injection under long contexts through the attribution-before-detection paradigm. As a real-world application, we demonstrate that {\name} can effectively pinpoint injected instructions in a paper designed to manipulate LLM-generated reviews.