4 papers
From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs
Yuchuan Tian, Yuchen Liang, Shuo Zhang +10
Diffusion Language Models (DLMs) enable fast generation, yet training large DLMs from scratch is costly. As a practical shortcut, adapting off-the-shelf Auto-Regressive (AR) model…
Sphinx: Benchmarking and Modeling for LLM-Driven Pull Request Review
Daoan Zhang, Shuo Zhang, Zijian Jin +3
Pull request (PR) review is essential for ensuring software quality, yet automating this task remains challenging due to noisy supervision, limited contextual understanding, and in…
Measuring the Impact of Lexical Training Data Coverage on Hallucination Detection in Large Language Models
Shuo Zhang, Fabrizio Gotti, Fengran Mo +1
Hallucination in large language models (LLMs) is a fundamental challenge, particularly in open-domain question answering. Prior work attempts to detect hallucination with model-int…
MTVHunter: Smart Contracts Vulnerability Detection Based on Multi-Teacher Knowledge Translation
Guokai Sun, Yuan Zhuang, Shuo Zhang +3
Smart contracts, closely intertwined with cryptocurrency transactions, have sparked widespread concerns about considerable financial losses of security issues. To counteract this,…