113 citations · 147 across the 11 of their papers we have counts for
11 papers
Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs
Yiming Huang, Zhenbo Shi, Xin-Cheng Wen +4
Unsupervised reinforcement learning (RL) has emerged as a promising paradigm for enabling self-improvement in large language models (LLMs). However, existing unsupervised RL-based…
Enriching Query Semantics for Code Search with Reinforcement Learning
Chaozheng Wang, Zhenghao Nong, Cuiyun Gao +4
Code search is a common practice for developers during software implementation. The challenges of accurate code search mainly lie in the knowledge gap between source code and natur…
Code Structure Guided Transformer for Source Code Summarization
Shuzheng Gao, Cuiyun Gao, Yulan He +4
Code summaries help developers comprehend programs and reduce their time to infer the program functionalities during software maintenance. Recent efforts resort to deep learning te…
Do Users Care about Ad's Performance Costs? Exploring the Effects of the Performance Costs of In-App Ads on User Experience
Cuiyun Gao, Jichuan Zeng, Federica Sarro +3
Context: In-app advertising is the primary source of revenue for many mobile apps. The cost of advertising (ad cost) is non-negligible for app developers to ensure a good user expe…
Emerging App Issue Identification via Online Joint Sentiment-Topic Tracing
Cuiyun Gao, Jichuan Zeng, Zhiyuan Wen +4
Millions of mobile apps are available in app stores, such as Apple's App Store and Google Play. For a mobile app, it would be increasingly challenging to stand out from the enormou…
An Empirical Study of In-App Advertising Issues Based on Large Scale App Review Analysis
Cuiyun Gao, Jichuan Zeng, David Lo +3
In-app advertising closely relates to app revenue. Reckless ad integration could adversely impact app reliability and user experience, leading to loss of income. It is very challen…
Photon: A Robust Cross-Domain Text-to-SQL System
Jichuan Zeng, Xi Victoria Lin, Caiming Xiong +4
Natural language interfaces to databases (NLIDB) democratize end user access to relational data. Due to fundamental differences between natural language communication and programmi…
Automating App Review Response Generation
Cuiyun Gao, Jichuan Zeng, Xin Xia +3
Previous studies showed that replying to a user review usually has a positive effect on the rating that is given by the user to the app. For example, Hassan et al. found that respo…
What Changed Your Mind: The Roles of Dynamic Topics and Discourse in Argumentation Process
Jichuan Zeng, Jing Li, Yulan He +3
In our world with full of uncertainty, debates and argumentation contribute to the progress of science and society. Despite of the increasing attention to characterize human argume…
What You Say and How You Say it: Joint Modeling of Topics and Discourse in Microblog Conversations
Jichuan Zeng, Jing Li, Yulan He +3
This paper presents an unsupervised framework for jointly modeling topic content and discourse behavior in microblog conversations. Concretely, we propose a neural model to discove…
Topic Memory Networks for Short Text Classification
Jichuan Zeng, Jing Li, Yan Song +3
Many classification models work poorly on short texts due to data sparsity. To address this issue, we propose topic memory networks for short text classification with a novel topic…