arXiv subjects

Michael Lyu

Publications and source records attributed to Michael Lyu.

At least 19 recordsLinked to original sources

arXiv2026

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding

Rendering source code as images offers a promising way to reduce the input costs of Multimodal Large Language Models (MLLMs). Adjusting image resolution can trade visual token cost against content fidelity. However, resolution scaling alone overlooks two sources of inefficiency: blank regions created by line breaks and indentation, and code regions irrelevant to the current instruction. Moreover, the best compression setting varies across inputs, tasks, and models, limiting fixed-ratio strategies. We propose CodeShrink, an adaptive visual compression framework with three components. Blank-Free Rendering replaces whitespace-dependent layouts with compact layouts and explicit structural markers, removing layout-induced tokens. Adaptive Compression Configuration uses a lightweight agent trained with reinforcement learning to predict a per-input setting that balances token efficiency and readability. Dominant Token Selection jointly analyzes the instruction and code image to prune task-irrelevant visual tokens during inference. We evaluate CodeShrink on code question answering, clone detection, and code completion. CodeShrink reduces visual token use by up to 71.2\% while matching or exceeding uncompressed text-only inputs, and consistently outperforms text-based and visual compression baselines across all three tasks. These results show that combining layout compaction, adaptive configuration, and instruction-aware pruning can make multimodal code understanding more efficient. Our code is available at https://github.com/vinsontang1/CodeShrink.

cs.CV↗

arXiv2025

RAG or Fine-tuning? A Comparative Study on LCMs-based Code Completion in Industry

Code completion, a crucial practice in industrial settings, helps developers improve programming efficiency by automatically suggesting code snippets during development. With the emergence of Large Code Models (LCMs), this field has witnessed significant advancements. Due to the natural differences between open-source and industrial codebases, such as coding patterns and unique internal dependencies, it is a common practice for developers to conduct domain adaptation when adopting LCMs in industry. There exist multiple adaptation approaches, among which retrieval-augmented generation (RAG) and fine-tuning are the two most popular paradigms. However, no prior research has explored the trade-off of the two approaches in industrial scenarios. To mitigate the gap, we comprehensively compare the two paradigms including Retrieval-Augmented Generation (RAG) and Fine-tuning (FT), for industrial code completion in this paper. In collaboration with Tencent's WXG department, we collect over 160,000 internal C++ files as our codebase. We then compare the two types of adaptation approaches from three dimensions that are concerned by industrial practitioners, including effectiveness, efficiency, and parameter sensitivity, using six LCMs. Our findings reveal that RAG, when implemented with appropriate embedding models that map code snippets into dense vector representations, can achieve higher accuracy than fine-tuning alone. Specifically, BM25 presents superior retrieval effectiveness and efficiency among studied RAG methods. Moreover, RAG and fine-tuning are orthogonal and their combination leads to further improvement. We also observe that RAG demonstrates better scalability than FT, showing more sustained performance gains with larger scales of codebase.

cs.SE↗

arXiv2025

Learning to Reason from Feedback at Test-Time

Solving complex tasks in a single attempt is challenging for large language models (LLMs). Iterative interaction with the environment and feedback is often required to achieve success, making effective feedback utilization a critical topic. Existing approaches either struggle with length generalization or rely on naive retries without leveraging prior information. In this paper, we introduce FTTT, a novel paradigm that formulates feedback utilization as an optimization problem at test time. Additionally, we propose a learnable test-time optimizer, OpTune, to effectively exploit feedback. Experiments on two LLMs across four reasoning datasets demonstrate that FTTT and OpTune achieve superior scalability and performance.

cs.LG↗

arXiv2025

The Prompt Alchemist: Automated LLM-Tailored Prompt Optimization for Test Case Generation

Test cases are essential for validating the reliability and quality of software applications. Recent studies have demonstrated the capability of Large Language Models (LLMs) to generate useful test cases for given source code. However, the existing work primarily relies on human-written plain prompts, which often leads to suboptimal results since the performance of LLMs can be highly influenced by the prompts. Moreover, these approaches use the same prompt for all LLMs, overlooking the fact that different LLMs might be best suited to different prompts. Given the wide variety of possible prompt formulations, automatically discovering the optimal prompt for each LLM presents a significant challenge. Although there are methods on automated prompt optimization in the natural language processing field, they are hard to produce effective prompts for the test case generation task. First, the methods iteratively optimize prompts by simply combining and mutating existing ones without proper guidance, resulting in prompts that lack diversity and tend to repeat the same errors in the generated test cases. Second, the prompts are generally lack of domain contextual knowledge, limiting LLMs' performance in the task.

cs.SE↗

arXiv2024

Medchain: Bridging the Gap Between LLM Agents and Clinical Practice with Interactive Sequence

Clinical decision making (CDM) is a complex, dynamic process crucial to healthcare delivery, yet it remains a significant challenge for artificial intelligence systems. While Large Language Model (LLM)-based agents have been tested on general medical knowledge using licensing exams and knowledge question-answering tasks, their performance in the CDM in real-world scenarios is limited due to the lack of comprehensive testing datasets that mirror actual medical practice. To address this gap, we present MedChain, a dataset of 12,163 clinical cases that covers five key stages of clinical workflow. MedChain distinguishes itself from existing benchmarks with three key features of real-world clinical practice: personalization, interactivity, and sequentiality. Further, to tackle real-world CDM challenges, we also propose MedChain-Agent, an AI system that integrates a feedback mechanism and a MCase-RAG module to learn from previous cases and adapt its responses. MedChain-Agent demonstrates remarkable adaptability in gathering information dynamically and handling sequential clinical tasks, significantly outperforming existing approaches.

cs.CL↗

arXiv2024

PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback

Large Language Models (LLMs) are widely adopted for assisting in software development tasks, yet their performance evaluations have narrowly focused on the functional correctness of generated code. Human programmers, however, require LLM-generated code to be not only correct but also optimally efficient. We propose PerfCodeGen, a training-free framework that enhances the performance of LLM-generated code by incorporating feedback based on runtime during test case execution into the self-refinement iterations. With PerfCodeGen, we achieve speedups for a significantly higher proportion of problems compared to using the base LLM with sophisticated prompting techniques. Applied to open language models like Phi-3-mini, PerfCodeGen achieves runtime efficiency comparable to prompting powerful closed models like GPT-4. We achieve state-of-the-art runtime efficiency on benchmarks such as HumanEval, MBPP, and APPS, frequently surpassing the ground truth reference solutions with PerfCodeGen using GPT-3.5 and GPT-4. Additionally, we demonstrate the effectiveness of our approach in enhancing code quality across a range of open LLMs of varying sizes including Phi-3-mini, Llama 3 8B, Mixtral 8x7B, Command R, and Llama 3 70B.

cs.SE↗

arXiv2024

Search-Based LLMs for Code Optimization

The code written by developers usually suffers from efficiency problems and contain various performance bugs. These inefficiencies necessitate the research of automated refactoring methods for code optimization. Early research in code optimization employs rule-based methods and focuses on specific inefficiency issues, which are labor-intensive and suffer from the low coverage issue. Recent work regards the task as a sequence generation problem, and resorts to deep learning (DL) techniques such as large language models (LLMs). These methods typically prompt LLMs to directly generate optimized code. Although these methods show state-of-the-art performance, such one-step generation paradigm is hard to achieve an optimal solution. First, complex optimization methods such as combinatorial ones are hard to be captured by LLMs. Second, the one-step generation paradigm poses challenge in precisely infusing the knowledge required for effective code optimization within LLMs, resulting in under-optimized code.To address these problems, we propose to model this task from the search perspective, and propose a search-based LLMs framework named SBLLM that enables iterative refinement and discovery of improved optimization methods. SBLLM synergistically integrate LLMs with evolutionary search and consists of three key components: 1) an execution-based representative sample selection part that evaluates the fitness of each existing optimized code and prioritizes promising ones to pilot the generation of improved code; 2) an adaptive optimization pattern retrieval part that infuses targeted optimization patterns into the model for guiding LLMs towards rectifying and progressively enhancing their optimization methods; and 3) a genetic operator-inspired chain-of-thought prompting part that aids LLMs in combining different optimization methods and generating improved optimization methods.

cs.SE↗

arXiv2023

Identifying Performance Issues in Cloud Service Systems Based on Relational-Temporal Features

Cloud systems are susceptible to performance issues, which may cause service-level agreement violations and financial losses. In current practice, crucial metrics are monitored periodically to provide insight into the operational status of components. Identifying performance issues is often formulated as an anomaly detection problem, which is tackled by analyzing each metric independently. However, this approach overlooks the complex dependencies existing among cloud components. Some graph neural network-based methods take both temporal and relational information into account, however, the correlation violations in the metrics that serve as indicators of underlying performance issues are difficult for them to identify. Furthermore, a large volume of components in a cloud system results in a vast array of noisy metrics. This complexity renders it impractical for engineers to fully comprehend the correlations, making it challenging to identify performance issues accurately. To address these limitations, we propose Identifying Performance Issues based on Relational-Temporal Features (ISOLATE ), a learning-based approach that leverages both the relational and temporal features of metrics to identify performance issues. In particular, it adopts a graph neural network with attention to characterizing the relations among metrics and extracts long-term and multi-scale temporal patterns using a GRU and a convolution network, respectively. The learned graph attention weights can be further used to localize the correlation-violated metrics. Moreover, to relieve the impact of noisy data, ISOLATE utilizes a positive unlabeled learning strategy that tags pseudo-labels based on a small portion of confirmed negative examples. Extensive evaluation on both public and industrial datasets shows that ISOLATE outperforms all baseline models with 0.945 F1-score and 0.920 Hit rate@3.

cs.LG↗

arXiv2023

Validating Multimedia Content Moderation Software via Semantic Fusion

The exponential growth of social media platforms, such as Facebook and TikTok, has revolutionized communication and content publication in human society. Users on these platforms can publish multimedia content that delivers information via the combination of text, audio, images, and video. Meanwhile, the multimedia content release facility has been increasingly exploited to propagate toxic content, such as hate speech, malicious advertisements, and pornography. To this end, content moderation software has been widely deployed on these platforms to detect and blocks toxic content. However, due to the complexity of content moderation models and the difficulty of understanding information across multiple modalities, existing content moderation software can fail to detect toxic content, which often leads to extremely negative impacts. We introduce Semantic Fusion, a general, effective methodology for validating multimedia content moderation software. Our key idea is to fuse two or more existing single-modal inputs (e.g., a textual sentence and an image) into a new input that combines the semantics of its ancestors in a novel manner and has toxic nature by construction. This fused input is then used for validating multimedia content moderation software. We realized Semantic Fusion as DUO, a practical content moderation software testing tool. In our evaluation, we employ DUO to test five commercial content moderation software and two state-of-the-art models against three kinds of toxic content. The results show that DUO achieves up to 100% error finding rate (EFR) when testing moderation software. In addition, we leverage the test cases generated by DUO to retrain the two models we explored, which largely improves model robustness while maintaining the accuracy on the original test set.

cs.SE↗

arXiv2023

BiasAsker: Measuring the Bias in Conversational AI System

Powered by advanced Artificial Intelligence (AI) techniques, conversational AI systems, such as ChatGPT and digital assistants like Siri, have been widely deployed in daily life. However, such systems may still produce content containing biases and stereotypes, causing potential social problems. Due to the data-driven, black-box nature of modern AI techniques, comprehensively identifying and measuring biases in conversational systems remains a challenging task. Particularly, it is hard to generate inputs that can comprehensively trigger potential bias due to the lack of data containing both social groups as well as biased properties. In addition, modern conversational systems can produce diverse responses (e.g., chatting and explanation), which makes existing bias detection methods simply based on the sentiment and the toxicity hardly being adopted. In this paper, we propose BiasAsker, an automated framework to identify and measure social bias in conversational AI systems. To obtain social groups and biased properties, we construct a comprehensive social bias dataset, containing a total of 841 groups and 8,110 biased properties. Given the dataset, BiasAsker automatically generates questions and adopts a novel method based on existence measurement to identify two types of biases (i.e., absolute bias and related bias) in conversational systems. Extensive experiments on 8 commercial systems and 2 famous research models, such as ChatGPT and GPT-3, show that 32.83% of the questions generated by BiasAsker can trigger biased behaviors in these widely deployed conversational systems. All the code, data, and experimental results have been released to facilitate future research.

cs.CL↗

arXiv2023

ChatGPT or Grammarly? Evaluating ChatGPT on Grammatical Error Correction Benchmark

ChatGPT is a cutting-edge artificial intelligence language model developed by OpenAI, which has attracted a lot of attention due to its surprisingly strong ability in answering follow-up questions. In this report, we aim to evaluate ChatGPT on the Grammatical Error Correction(GEC) task, and compare it with commercial GEC product (e.g., Grammarly) and state-of-the-art models (e.g., GECToR). By testing on the CoNLL2014 benchmark dataset, we find that ChatGPT performs not as well as those baselines in terms of the automatic evaluation metrics (e.g., $F_{0.5}$ score), particularly on long sentences. We inspect the outputs and find that ChatGPT goes beyond one-by-one corrections. Specifically, it prefers to change the surface expression of certain phrases or sentence structure while maintaining grammatical correctness. Human evaluation quantitatively confirms this and suggests that ChatGPT produces less under-correction or mis-correction issues but more over-corrections. These results demonstrate that ChatGPT is severely under-estimated by the automatic evaluation metrics and could be a promising tool for GEC.

cs.CL↗

arXiv2023

Deep Learning Based Code Generation Methods: Literature Review

This paper focuses on Code Generation task that aims at generating relevant code fragments according to given natural language descriptions. In the process of software development, developers often encounter two scenarios. One is requested to write a large amount of repetitive and low-technical code for implementing common functionalities. The other is writing code that depends on specific task requirements, which may necessitate the use of external resources such as documentation or other tools. Therefore, code generation has received a lot of attention among academia and industry for assisting developers in coding. In fact, it has also been one of the key concerns in the field of software engineering to make machines understand users' requirements and write programs on their own. The recent development of deep learning techniques especially pre-training models make the code generation task achieve promising performance. In this paper, we systematically review the current work on deep learning-based code generation and classify the current deep learning-based code generation methods into three categories: methods based on code features, methods incorporated with retrieval, and methods incorporated with post-processing. The first category refers to the methods that use deep learning algorithms for code generation based on code features, and the second and third categories of methods improve the performance of the methods in the first category. In this paper, the existing research results of each category of methods are systematically reviewed, summarized and commented. Besides, the paper summarizes and analyzes the corpus and the popular evaluation metrics used in the existing code generation work. Finally, the paper summarizes the overall literature review and provides a prospect on future research directions worthy of attention.

cs.SE↗

arXiv2023

MTTM: Metamorphic Testing for Textual Content Moderation Software

The exponential growth of social media platforms such as Twitter and Facebook has revolutionized textual communication and textual content publication in human society. However, they have been increasingly exploited to propagate toxic content, such as hate speech, malicious advertisement, and pornography, which can lead to highly negative impacts (e.g., harmful effects on teen mental health). Researchers and practitioners have been enthusiastically developing and extensively deploying textual content moderation software to address this problem. However, we find that malicious users can evade moderation by changing only a few words in the toxic content. Moreover, modern content moderation software performance against malicious inputs remains underexplored. To this end, we propose MTTM, a Metamorphic Testing framework for Textual content Moderation software. Specifically, we conduct a pilot study on 2,000 text messages collected from real users and summarize eleven metamorphic relations across three perturbation levels: character, word, and sentence. MTTM employs these metamorphic relations on toxic textual contents to generate test cases, which are still toxic yet likely to evade moderation. In our evaluation, we employ MTTM to test three commercial textual content moderation software and two state-of-the-art moderation algorithms against three kinds of toxic content. The results show that MTTM achieves up to 83.9%, 51%, and 82.5% error finding rates (EFR) when testing commercial moderation software provided by Google, Baidu, and Huawei, respectively, and it obtains up to 91.2% EFR when testing the state-of-the-art algorithms from the academy. In addition, we leverage the test cases generated by MTTM to retrain the model we explored, which largely improves model robustness (0% to 5.9% EFR) while maintaining the accuracy on the original test set.

cs.CL↗

arXiv2022

Understanding and Improving Sequence-to-Sequence Pretraining for Neural Machine Translation

In this paper, we present a substantial step in better understanding the SOTA sequence-to-sequence (Seq2Seq) pretraining for neural machine translation~(NMT). We focus on studying the impact of the jointly pretrained decoder, which is the main difference between Seq2Seq pretraining and previous encoder-based pretraining approaches for NMT. By carefully designing experiments on three language pairs, we find that Seq2Seq pretraining is a double-edged sword: On one hand, it helps NMT models to produce more diverse translations and reduce adequacy-related translation errors. On the other hand, the discrepancies between Seq2Seq pretraining and NMT finetuning limit the translation quality (i.e., domain discrepancy) and induce the over-estimation issue (i.e., objective discrepancy). Based on these observations, we further propose simple and effective strategies, named in-domain pretraining and input adaptation to remedy the domain and objective discrepancies, respectively. Experimental results on several language pairs show that our approach can consistently improve both translation performance and model robustness upon Seq2Seq pretraining.

cs.CL↗

arXiv2021

Revisiting, Benchmarking and Exploring API Recommendation: How Far Are We?

Application Programming Interfaces (APIs), which encapsulate the implementation of specific functions as interfaces, greatly improve the efficiency of modern software development. As numbers of APIs spring up nowadays, developers can hardly be familiar with all the APIs, and usually need to search for appropriate APIs for usage. So lots of efforts have been devoted to improving the API recommendation task. However, it has been increasingly difficult to gauge the performance of new models due to the lack of a uniform definition of the task and a standardized benchmark. For example, some studies regard the task as a code completion problem; while others recommend relative APIs given natural language queries. To reduce the challenges and better facilitate future research, in this paper, we revisit the API recommendation task and aim at benchmarking the approaches. Specifically, the paper groups the approaches into two categories according to the task definition, i.e., query-based API recommendation and code-based API recommendation. We study 11 recently-proposed approaches along with 4 widely-used IDEs. One benchmark named as APIBench is then built for the two respective categories of approaches. Based on APIBench, we distill some actionable insights and challenges for API recommendation. We also achieve some implications and directions for improving the performance of recommending APIs, including data source selection, appropriate query reformulation, low resource setting, and cross-domain adaptation.

cs.SE↗

arXiv2021

Discrete Auto-regressive Variational Attention Models for Text Modeling

Variational autoencoders (VAEs) have been widely applied for text modeling. In practice, however, they are troubled by two challenges: information underrepresentation and posterior collapse. The former arises as only the last hidden state of LSTM encoder is transformed into the latent space, which is generally insufficient to summarize the data. The latter is a long-standing problem during the training of VAEs as the optimization is trapped to a disastrous local optimum. In this paper, we propose Discrete Auto-regressive Variational Attention Model (DAVAM) to address the challenges. Specifically, we introduce an auto-regressive variational attention approach to enrich the latent space by effectively capturing the semantic dependency from the input. We further design discrete latent space for the variational attention and mathematically show that our model is free from posterior collapse. Extensive experiments on language modeling tasks demonstrate the superiority of DAVAM against several VAE counterparts.

cs.LG↗

arXiv2021

Static Inference Meets Deep Learning: A Hybrid Type Inference Approach for Python

Type inference for dynamic programming languages such as Python is an important yet challenging task. Static type inference techniques can precisely infer variables with enough static constraints but are unable to handle variables with dynamic features. Deep learning (DL) based approaches are feature-agnostic, but they cannot guarantee the correctness of the predicted types. Their performance significantly depends on the quality of the training data (i.e., DL models perform poorly on some common types that rarely appear in the training dataset). It is interesting to note that the static and DL-based approaches offer complementary benefits. Unfortunately, to our knowledge, precise type inference based on both static inference and neural predictions has not been exploited and remains an open challenge. In particular, it is hard to integrate DL models into the framework of rule-based static approaches. This paper fills the gap and proposes a hybrid type inference approach named HiTyper based on both static inference and deep learning. Specifically, our key insight is to record type dependencies among variables in each function and encode the dependency information in type dependency graphs (TDGs). Based on TDGs, we can easily integrate type inference rules in the nodes to conduct static inference and type rejection rules to inspect the correctness of neural predictions. HiTyper iteratively conducts static inference and DL-based prediction until the TDG is fully inferred. Experiments on two benchmark datasets show that HiTyper outperforms state-of-the-art DL models by exactly matching 10% more human annotations. HiTyper also achieves an increase of more than 30% on inferring rare types. Considering only the static part of HiTyper, it infers 2x ~ 3x more types than existing static type inference tools.

cs.SE↗

arXiv2020

BinaryBERT: Pushing the Limit of BERT Quantization

The rapid development of large pre-trained language models has greatly increased the demand for model compression techniques, among which quantization is a popular solution. In this paper, we propose BinaryBERT, which pushes BERT quantization to the limit by weight binarization. We find that a binary BERT is hard to be trained directly than a ternary counterpart due to its complex and irregular loss landscape. Therefore, we propose ternary weight splitting, which initializes BinaryBERT by equivalently splitting from a half-sized ternary network. The binary model thus inherits the good performance of the ternary one, and can be further enhanced by fine-tuning the new architecture after splitting. Empirical results show that our BinaryBERT has only a slight performance drop compared with the full-precision model while being 24x smaller, achieving the state-of-the-art compression results on the GLUE and SQuAD benchmarks.

cs.CL↗