Large Language Models (LLMs) are increasingly used throughout the software development lifecycle. This growing reliance on LLMs raises concerns about their trustworthiness, with deception posing a particularly important risk. Deceptive behavior takes the form of misleading responses or assistance in fabricating, concea...
Xi-Ting Liu, Lin Yang, Yi-Tong Zhang et al.· 0 citations
As Large Language Models (LLMs) are increasingly integrated into software development workflows, their trustworthiness has become a critical concern. However, in dependency recommendation scenarios, the reliability of LLMs is undermined by widespread package hallucinations, where models often recommend hallucinated pac...
Xi-Ting Liu, Yue-Tong Liu, Yi-Tong Zhang et al.· 0 citations
DiffuTester employs a novel structural pattern based decoding approach, which dynamically identifies structural patterns across unit tests through their abstract syntax trees and additionally decodes the corresponding tokens, thereby achieving acceleration without compromising the quality of the output.
Le Yang, Yue-Tong Liu, Yi-Tong Zhang et al.· 3 citations
PriCoder is proposed, an approach that teaches LLMs to invoke private-library APIs through automatically synthesized data, and alternates between two graph operators that improves data diversity by progressively synthesizing more diverse training samples from basic ones.
This study presents the first empirical study of diffusion LLMs for code generation and explores factors impacting the effectiveness and efficiency of diffusion LLMs, and provides practical guidance.
Cheng-Ze Li, Yi-Tong Zhang, Jia Li et al.· ACM Transactions on Software...· 18 citations· ⚡1
Intentest is proposed, an intent-graph-guided automated penetration testing agent that externalizes long-horizon state from the LLM's context window onto a persistent fact-intent directed acyclic graph (DAG), thereby substantially reducing invalid transitions.
Wei-Zhe Wang, Yi-Tong Zhang, Yao Zhang et al.· 0 citations
CoACT is built on next-action preservation (NAP), which requires a compressed observation to induce the same next action as the raw observation, and uses an action-preservation reward based on NAP to filter out candidates that would change the agent's next action.
Hao Chen, Yuancheng Zhu, Yitong Zhang et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
