Jichuan Zeng

Yiming Huang, Zhenbo Shi, Xin-Cheng Wen et al.

Unsupervised reinforcement learning (RL) has emerged as a promising paradigm for enabling self-improvement in large language models (LLMs). However, existing unsupervised RL-based methods often lack the capacity to adapt to the model's evolving reasoning capabilities during training. Therefore, these methods can misdirect policy optimization in the absence of ground-truth supervision. To address this issue, we introduce FREIA, a novel RL-based algorithm built on two key innovations: (1) Free Energy-Driven Reward (FER) adapts rewards to balance consensus and exploration based on the Free Energy Principle. (2) Adaptive Advantage Shaping (AAS) adaptively adjusts learning signals based on the statistical characteristics of sampled rewards. Empirical evaluations on nine datasets across three reasoning tasks showcase that FREIA outperforms other unsupervised RL-based baselines. Notably, in mathematical reasoning tasks, FREIA surpasses other methods by an average of 0.5 to 3.5 points in Pass@1 using the DeepSeek-R1-Distill-Qwen-1.5B model.

Chaozheng Wang, Zhenghao Nong, Cuiyun Gao et al.

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 natural language (i.e., queries). Due to the limited code-query pairs and large code-description pairs available, the prior studies based on deep learning techniques focus on learning the semantic matching relation between source code and corresponding description texts for the task, and hypothesize that the semantic gap between descriptions and user queries is marginal. In this work, we found that the code search models trained on code-description pairs may not perform well on user queries, which indicates the semantic distance between queries and code descriptions. To mitigate the semantic distance for more effective code search, we propose QueCos, a Query-enriched Code search model. QueCos learns to generate semantic enriched queries to capture the key semantics of given queries with reinforcement learning (RL). With RL, the code search performance is considered as a reward for producing accurate semantic enriched queries. The enriched queries are finally employed for code search. Experiments on the benchmark datasets show that QueCos can significantly outperform the state-of-the-art code search models.

Shuzheng Gao, Cuiyun Gao, Yulan He et al.

Code summaries help developers comprehend programs and reduce their time to infer the program functionalities during software maintenance. Recent efforts resort to deep learning techniques such as sequence-to-sequence models for generating accurate code summaries, among which Transformer-based approaches have achieved promising performance. However, effectively integrating the code structure information into the Transformer is under-explored in this task domain. In this paper, we propose a novel approach named SG-Trans to incorporate code structural properties into Transformer. Specifically, we inject the local symbolic information (e.g., code tokens and statements) and global syntactic structure (e.g., data flow graph) into the self-attention module of Transformer as inductive bias. To further capture the hierarchical characteristics of code, the local information and global structure are designed to distribute in the attention heads of lower layers and high layers of Transformer. Extensive evaluation shows the superior performance of SG-Trans over the state-of-the-art approaches. Compared with the best-performing baseline, SG-Trans still improves 1.4% and 2.0% in terms of METEOR score, a metric widely used for measuring generation quality, respectively on two benchmark datasets.

Cuiyun Gao, Jichuan Zeng, Federica Sarro et al.

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 experience and continuous profits. Previous studies mainly focus on addressing the hidden performance costs generated by ads, including consumption of memory, CPU, data traffic, and battery. However, there is no research onanalyzing users' perceptions of ads' performance costs to our knowledge. Objective: To fill this gap and better understand the effects of performance costs of in-app ads on user experience, we conduct a study on analyzing user concerns about ads' performance costs. Method: First, we propose RankMiner, an approach to quantify user concerns about specific appissues, including performance costs. Then, based on the usage traces of 20 subject apps, we measure the performance costs of ads. Finally, we conduct correlation analysis on the performance costs and quantified user concerns to explore whether users complain more for higher performance costs. Results: Our findings include the following: (1) RankMiner can quantify users' concerns better than baselines by an improvement of 214% and 2.5% in terms of Pearson correlation coefficient (a metricfor computing correlations between two variables) and NDCG score (a metric for computing accuracyin prioritizing issues), respectively. (2) The performance costs of the with-ads versions are statistically significantly larger than those of no-ads versions with negligible effect size; (3) Users are moreconcerned about the battery costs of ads, and tend to be insensitive to ads' data traffic costs. Conclusion: Our study is complementary to previous work on in-app ads, and can encourage devel-opers to pay more attention to alleviating the most user-concerned performance costs, such as battery cost.

Cuiyun Gao, Jichuan Zeng, Zhiyuan Wen et al.

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 enormous competitors and become prevalent among users. Good user experience and well-designed functionalities are the keys to a successful app. To achieve this, popular apps usually schedule their updates frequently. If we can capture the critical app issues faced by users in a timely and accurate manner, developers can make timely updates, and good user experience can be ensured. There exist prior studies on analyzing reviews for detecting emerging app issues. These studies are usually based on topic modeling or clustering techniques. However, the short-length characteristics and sentiment of user reviews have not been considered. In this paper, we propose a novel emerging issue detection approach named MERIT to take into consideration the two aforementioned characteristics. Specifically, we propose an Adaptive Online Biterm Sentiment-Topic (AOBST) model for jointly modeling topics and corresponding sentiments that takes into consideration app versions. Based on the AOBST model, we infer the topics negatively reflected in user reviews for one app version, and automatically interpret the meaning of the topics with most relevant phrases and sentences. Experiments on popular apps from Google Play and Apple's App Store demonstrate the effectiveness of MERIT in identifying emerging app issues, improving the state-of-the-art method by 22.3% in terms of F1-score. In terms of efficiency, MERIT can return results within acceptable time.

Cuiyun Gao, Jichuan Zeng, David Lo et al.

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 challenging to balance the ad revenue and user experience for app developers. In this paper, we present a large-scale analysis on ad-related user feedback. The large user feedback data from App Store and Google Play allow us to summarize ad-related app issues comprehensively and thus provide practical ad integration strategies for developers. We first define common ad issues by manually labeling a statistically representative sample of ad-related feedback, and then build an automatic classifier to categorize ad-related feedback. We study the relations between different ad issues and user ratings to identify the ad issues poorly scored by users. We also explore the fix durations of ad issues across platforms for extracting insights into prioritizing ad issues for ad maintenance. We summarize 15 types of ad issues by manually annotating 903/36,309 ad-related user reviews. From a statistical analysis of 36,309 ad-related reviews, we find that users care most about the number of unique ads and ad display frequency during usage. Besides, users tend to give relatively lower ratings when they report the security and notification related issues. Regarding different platforms, we observe that the distributions of ad issues are significantly different between App Store and Google Play. Moreover, some ad issue types are addressed more quickly by developers than other ad issues. We believe the findings we discovered can benefit app developers towards balancing ad revenue and user experience while ensuring app reliability.

Jichuan Zeng, Xi Victoria Lin, Caiming Xiong et al.

Natural language interfaces to databases (NLIDB) democratize end user access to relational data. Due to fundamental differences between natural language communication and programming, it is common for end users to issue questions that are ambiguous to the system or fall outside the semantic scope of its underlying query language. We present Photon, a robust, modular, cross-domain NLIDB that can flag natural language input to which a SQL mapping cannot be immediately determined. Photon consists of a strong neural semantic parser (63.2\% structure accuracy on the Spider dev benchmark), a human-in-the-loop question corrector, a SQL executor and a response generator. The question corrector is a discriminative neural sequence editor which detects confusion span(s) in the input question and suggests rephrasing until a translatable input is given by the user or a maximum number of iterations are conducted. Experiments on simulated data show that the proposed method effectively improves the robustness of text-to-SQL system against untranslatable user input. The live demo of our system is available at http://naturalsql.com.

Cuiyun Gao, Jichuan Zeng, Xin Xia et al.

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 responding to a review increases the chances of a user updating their given rating by up to six times compared to not responding. To alleviate the labor burden in replying to the bulk of user reviews, developers usually adopt a template-based strategy where the templates can express appreciation for using the app or mention the company email address for users to follow up. However, reading a large number of user reviews every day is not an easy task for developers. Thus, there is a need for more automation to help developers respond to user reviews. Addressing the aforementioned need, in this work we propose a novel approach RRGen that automatically generates review responses by learning knowledge relations between reviews and their responses. RRGen explicitly incorporates review attributes, such as user rating and review length, and learns the relations between reviews and corresponding responses in a supervised way from the available training data. Experiments on 58 apps and 309,246 review-response pairs highlight that RRGen outperforms the baselines by at least 67.4% in terms of BLEU-4 (an accuracy measure that is widely used to evaluate dialogue response generation systems). Qualitative analysis also confirms the effectiveness of RRGen in generating relevant and accurate responses.

Jichuan Zeng, Jing Li, Yulan He et al.

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 arguments, most progress made so far focus on the debate outcome, largely ignoring the dynamic patterns in argumentation processes. This paper presents a study that automatically analyzes the key factors in argument persuasiveness, beyond simply predicting who will persuade whom. Specifically, we propose a novel neural model that is able to dynamically track the changes of latent topics and discourse in argumentative conversations, allowing the investigation of their roles in influencing the outcomes of persuasion. Extensive experiments have been conducted on argumentative conversations on both social media and supreme court. The results show that our model outperforms state-of-the-art models in identifying persuasive arguments via explicitly exploring dynamic factors of topic and discourse. We further analyze the effects of topics and discourse on persuasiveness, and find that they are both useful - topics provide concrete evidence while superior discourse styles may bias participants, especially in social media arguments. In addition, we draw some findings from our empirical results, which will help people better engage in future persuasive conversations.

Jichuan Zeng, Jing Li, Yulan He et al.

This paper presents an unsupervised framework for jointly modeling topic content and discourse behavior in microblog conversations. Concretely, we propose a neural model to discover word clusters indicating what a conversation concerns (i.e., topics) and those reflecting how participants voice their opinions (i.e., discourse). Extensive experiments show that our model can yield both coherent topics and meaningful discourse behavior. Further study shows that our topic and discourse representations can benefit the classification of microblog messages, especially when they are jointly trained with the classifier.

Jichuan Zeng, Jing Li, Yan Song et al.

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 memory mechanism to encode latent topic representations indicative of class labels. Different from most prior work that focuses on extending features with external knowledge or pre-trained topics, our model jointly explores topic inference and text classification with memory networks in an end-to-end manner. Experimental results on four benchmark datasets show that our model outperforms state-of-the-art models on short text classification, meanwhile generates coherent topics.