Srikanth Tamilselvam

Debeshee Das, Noble Saji Mathews, Alex Mathai et al.

Learning effective representations of source code is critical for any Machine Learning for Software Engineering (ML4SE) system. Inspired by natural language processing, large language models (LLMs) like Codex and CodeGen treat code as generic sequences of text and are trained on huge corpora of code data, achieving state of the art performance on several software engineering (SE) tasks. However, valid source code, unlike natural language, follows a strict structure and pattern governed by the underlying grammar of the programming language. Current LLMs do not exploit this property of the source code as they treat code like a sequence of tokens and overlook key structural and semantic properties of code that can be extracted from code-views like the Control Flow Graph (CFG), Data Flow Graph (DFG), Abstract Syntax Tree (AST), etc. Unfortunately, the process of generating and integrating code-views for every programming language is cumbersome and time consuming. To overcome this barrier, we propose our tool COMEX - a framework that allows researchers and developers to create and combine multiple code-views which can be used by machine learning (ML) models for various SE tasks. Some salient features of our tool are: (i) it works directly on source code (which need not be compilable), (ii) it currently supports Java and C#, (iii) it can analyze both method-level snippets and program-level snippets by using both intra-procedural and inter-procedural analysis, and (iv) it is easily extendable to other languages as it is built on tree-sitter - a widely used incremental parser that supports over 40 languages. We believe this easy-to-use code-view generation and customization tool will give impetus to research in source code representation learning methods and ML4SE. Tool: https://pypi.org/project/comex - GitHub: https://github.com/IBM/tree-sitter-codeviews - Demo: https://youtu.be/GER6U87FVbU

Mehant Kammakomati, Sameer Pimparkhede, Srikanth Tamilselvam et al.

Recent work shows Large Language Models (LLMs) struggle to understand natural language constraints for various text generation tasks in zero- and few-shot settings. While, in the code domain, there is wide usage of constraints in code format to maintain the integrity of code written in Domain-Specific Languages (DSLs) like JSON and YAML which are widely used for system-level programming tasks in enterprises. Given that LLMs are increasingly used for system-level code tasks, evaluating if they can comprehend these code constraints is crucial. However, no work has been done to evaluate their controllability over code constraints. Hence, we introduce ConCodeEval, a first-of-its-kind benchmark having two novel tasks for code constraints across five representations. Our findings suggest that language models struggle with code constraints. Code languages that perform excellently for normal code tasks do not perform well when the same languages represent fine-grained constraints.

Sameer Pimparkhede, Mehant Kammakomati, Srikanth Tamilselvam et al.

Recent developments show that Large Language Models (LLMs) produce state-of-the-art performance on natural language (NL) to code generation for resource-rich general-purpose languages like C++, Java, and Python. However, their practical usage for structured domain-specific languages (DSLs) such as YAML, JSON is limited due to domain-specific schema, grammar, and customizations generally unseen by LLMs during pre-training. Efforts have been made to mitigate this challenge via in-context learning through relevant examples or by fine-tuning. However, it suffers from problems, such as limited DSL samples and prompt sensitivity but enterprises maintain good documentation of the DSLs. Therefore, we propose DocCGen, a framework that can leverage such rich knowledge by breaking the NL-to-Code generation task for structured code languages into a two-step process. First, it detects the correct libraries using the library documentation that best matches the NL query. Then, it utilizes schema rules extracted from the documentation of these libraries to constrain the decoding. We evaluate our framework for two complex structured languages, Ansible YAML and Bash command, consisting of two settings: Out-of-domain (OOD) and In-domain (ID). Our extensive experiments show that DocCGen consistently improves different-sized language models across all six evaluation metrics, reducing syntactic and semantic errors in structured code. We plan to open-source the datasets and code to motivate research in constrained code generation.

Advait Pavuluri, Bridget McGinn, Ashita Saxena et al.

Java remains central to enterprise software, and many applications outlive their original architecture. Migrating them across frameworks is a behavior-preserving refactoring spanning build configuration, dependency injection, persistence, request handling, and deployment. Existing software-engineering benchmarks cover bug fixing, feature implementation, and language or version modernization, but leave cross-framework refactoring largely unmeasured. We introduce ScarfBench, a benchmark for behavior-preserving cross-framework refactoring of enterprise Java applications. It is built from expert-written implementation triples across Spring, Jakarta EE, and Quarkus: 34 applications (29 focused single-layer, 5 whole) yielding 102 variants (~151K lines across 1946 source and test files) and 204 directed refactoring tasks. Each task gives an agent a working source application and a target framework; the agent must synthesize a target implementation preserving the source behavior. Correctness is evaluated by an application-specific executable oracle: the candidate must compile, deploy in a containerized target runtime, and pass behavioral tests over the application's observable interface. We evaluate five state-of-the-art coding agents on ScarfBench. The strongest achieves only 15.3% aggregate test pass on focused-layer migrations and 12.2% on whole applications, and only one of the 204 tasks yields a fully behaviorally equivalent target. Difficulty is asymmetric across framework directions and architectural layers: Spring<->Quarkus is the most tractable pair, and Jakarta-targeted migrations are hardest. From LLM-as-a-judge and expert adjudication of failed-task traces, we derive a taxonomy of recurring failure categories spanning build, deploy, and test stages. We release the benchmark, harness, and agent traces at https://scarfbench.info.

Kishan Maharaj, Nandakishore Menon, Ashita Saxena et al.

Large language models (LLMs) increasingly assist software engineering tasks that require reasoning over long code contexts, yet their robustness under varying input conditions remains unclear. We conduct a systematic study of long-context code question answering using controlled ablations that test sensitivity to answer format, distractors, and context scale. Extending LongCodeBench Python dataset with new COBOL and Java question-answer sets, we evaluate state-of-the-art models under three settings: (i) shuffled multiple-choice options, (ii) open-ended questions and (iii) needle-in-a-haystack contexts containing relevant and adversarially irrelevant information. Results show substantial performance drops in both shuffled multiple-choice options and open-ended questions, and brittle behavior in the presence of irrelevant cues. Our findings highlight limitations of current long-context evaluations and provide a broader benchmark for assessing code reasoning in both legacy and modern systems.

Alex Mathai, Kranthi Sedamaki, Debeshee Das et al.

Machine Learning (ML) for software engineering (SE) has gained prominence due to its ability to significantly enhance the performance of various SE applications. This progress is largely attributed to the development of generalizable source code representations that effectively capture the syntactic and semantic characteristics of code. In recent years, pre-trained transformer-based models, inspired by natural language processing (NLP), have shown remarkable success in SE tasks. However, source code contains structural and semantic properties embedded within its grammar, which can be extracted from structured code-views like the Abstract Syntax Tree (AST), Data-Flow Graph (DFG), and Control-Flow Graph (CFG). These code-views can complement NLP techniques, further improving SE tasks. Unfortunately, there are no flexible frameworks to infuse arbitrary code-views into existing transformer-based models effectively. Therefore, in this work, we propose CodeSAM, a novel scalable framework to infuse multiple code-views into transformer-based models by creating self-attention masks. We use CodeSAM to fine-tune a small language model (SLM) like CodeBERT on the downstream SE tasks of semantic code search, code clone detection, and program classification. Experimental results show that by using this technique, we improve downstream performance when compared to SLMs like GraphCodeBERT and CodeBERT on all three tasks by utilizing individual code-views or a combination of code-views during fine-tuning. We believe that these results are indicative that techniques like CodeSAM can help create compact yet performant code SLMs that fit in resource constrained settings.

Jayant Havare, Saurav Chaudhary, Ganesh Ramakrishnan et al.

Large Language Models have shown impressive capabilities in coding tasks like code generation and code completion, as they have been trained on a large amount of code data. Also, since one of the core pretraining objectives is Next Token Prediction, these models tends to learn surface-level syntactic patterns in code. However, this does not guarantee code comprehension ability i.e. the ability to capture the semantics of the code. In our opinion, this is the reason why these models often underperform on tasks that require deeper semantic understanding, such as code debugging and code optimization. To address this, we propose fine-tuning these models specifically for code comprehension tasks using large-scale datasets, enabling them to develop a more robust understanding of code semantics. We evaluate three code models of varying sizes on a suite of code comprehension tasks designed to assess semantic understanding beyond surface-level syntactic pattern matching. In particular, we analyze performance on the Subjectivity Grading Task and observe that model performance improves after fine-tuning on relevant downstream tasks. The most significant improvement is seen in the QWQ-32B model, where accuracy increases from 70% to 83.47%. A similar or explainable trend is observed across other models, clearly indicating an enhancement in code comprehension ability. Among the models studied, the DPO-fine-tuned Codestral-22B achieves the highest micro-accuracy of 87.66% on the Subjectivity Grading Task.

Prince Kumar, Srikanth Tamilselvam, Dinesh Garg

While text summarization is a well-known NLP task, in this paper, we introduce a novel and useful variant of it called functionality extraction from Git README files. Though this task is a text2text generation at an abstract level, it involves its own peculiarities and challenges making existing text2text generation systems not very useful. The motivation behind this task stems from a recent surge in research and development activities around the use of large language models for code-related tasks, such as code refactoring, code summarization, etc. We also release a human-annotated dataset called FuncRead, and develop a battery of models for the task. Our exhaustive experimentation shows that small size fine-tuned models beat any baseline models that can be designed using popular black-box or white-box large language models (LLMs) such as ChatGPT and Bard. Our best fine-tuned 7 Billion CodeLlama model exhibit 70% and 20% gain on the F1 score against ChatGPT and Bard respectively.

Mayank Mishra, Prince Kumar, Riyaz Bhat et al.

Prompting with natural language instructions has recently emerged as a popular method of harnessing the capabilities of large language models. Given the inherent ambiguity present in natural language, it is intuitive to consider the possible advantages of prompting with less ambiguous prompt styles, such as the use of pseudo-code. In this paper we explore if prompting via pseudo-code instructions helps improve the performance of pre-trained language models. We manually create a dataset of pseudo-code prompts for 132 different tasks spanning classification, QA and generative language tasks, sourced from the Super-NaturalInstructions dataset. Using these prompts along with their counterparts in natural language, we study their performance on two LLM families - BLOOM and CodeGen. Our experiments show that using pseudo-code instructions leads to better results, with an average increase (absolute) of 7-16 points in F1 scores for classification tasks and an improvement (relative) of 12-38% in aggregate ROUGE-L scores across all tasks. We include detailed ablation studies which indicate that code comments, docstrings, and the structural clues encoded in pseudo-code all contribute towards the improvement in performance. To the best of our knowledge our work is the first to demonstrate how pseudo-code prompts can be helpful in improving the performance of pre-trained LMs.

Alex Mathai, Sambaran Bandyopadhyay, Utkarsh Desai et al.

Monolithic software encapsulates all functional capabilities into a single deployable unit. But managing it becomes harder as the demand for new functionalities grow. Microservice architecture is seen as an alternate as it advocates building an application through a set of loosely coupled small services wherein each service owns a single functional responsibility. But the challenges associated with the separation of functional modules, slows down the migration of a monolithic code into microservices. In this work, we propose a representation learning based solution to tackle this problem. We use a heterogeneous graph to jointly represent software artifacts (like programs and resources) and the different relationships they share (function calls, inheritance, etc.), and perform a constraint-based clustering through a novel heterogeneous graph neural network. Experimental studies show that our approach is effective on monoliths of different types.

Utkarsh Desai, Sambaran Bandyopadhyay, Srikanth Tamilselvam

Microservices are becoming the defacto design choice for software architecture. It involves partitioning the software components into finer modules such that the development can happen independently. It also provides natural benefits when deployed on the cloud since resources can be allocated dynamically to necessary components based on demand. Therefore, enterprises as part of their journey to cloud, are increasingly looking to refactor their monolith application into one or more candidate microservices; wherein each service contains a group of software entities (e.g., classes) that are responsible for a common functionality. Graphs are a natural choice to represent a software system. Each software entity can be represented as nodes and its dependencies with other entities as links. Therefore, this problem of refactoring can be viewed as a graph based clustering task. In this work, we propose a novel method to adapt the recent advancements in graph neural networks in the context of code to better understand the software and apply them in the clustering task. In that process, we also identify the outliers in the graph which can be directly mapped to top refactor candidates in the software. Our solution is able to improve state-of-the-art performance compared to works from both software engineering and existing graph representation based techniques.

Alex Mathai, Shreya Khare, Srikanth Tamilselvam et al.

We propose a novel genetic-algorithm technique that generates black-box adversarial examples which successfully fool neural network based text classifiers. We perform a genetic search with multi-objective optimization guided by deep learning based inferences and Seq2Seq mutation to generate semantically similar but imperceptible adversaries. We compare our approach with DeepWordBug (DWB) on SST and IMDB sentiment datasets by attacking three trained models viz. char-LSTM, word-LSTM and elmo-LSTM. On an average, we achieve an attack success rate of 65.67% for SST and 36.45% for IMDB across the three models showing an improvement of 49.48% and 101% respectively. Furthermore, our qualitative study indicates that 94% of the time, the users were not able to distinguish between an original and adversarial sample.

Raunak Sinha, Utkarsh Desai, Srikanth Tamilselvam et al.

With the increase in the number of open repositories and discussion forums, the use of natural language for semantic code search has become increasingly common. The accuracy of the results returned by such systems, however, can be low due to 1) limited shared vocabulary between code and user query and 2) inadequate semantic understanding of user query and its relation to code syntax. Siamese networks are well suited to learning such joint relations between data, but have not been explored in the context of code search. In this work, we evaluate Siamese networks for this task by exploring multiple extraction network architectures. These networks independently process code and text descriptions before passing them to a Siamese network to learn embeddings in a common space. We experiment on two different datasets and discover that Siamese networks can act as strong regularizers on networks that extract rich information from code and text, which in turn helps achieve impressive performance on code search beating previous baselines on $2$ programming languages. We also analyze the embedding space of these networks and provide directions to fully leverage the power of Siamese networks for semantic code search.

Utkarsh Desai, Srikanth Tamilselvam, Jassimran Kaur et al.

Text classification models, especially neural networks based models, have reached very high accuracy on many popular benchmark datasets. Yet, such models when deployed in real world applications, tend to perform badly. The primary reason is that these models are not tested against sufficient real world natural data. Based on the application users, the vocabulary and the style of the model's input may greatly vary. This emphasizes the need for a model agnostic test dataset, which consists of various corruptions that are natural to appear in the wild. Models trained and tested on such benchmark datasets, will be more robust against real world data. However, such data sets are not easily available. In this work, we address this problem, by extending the benchmark datasets along naturally occurring corruptions such as Spelling Errors, Text Noise and Synonyms and making them publicly available. Through extensive experiments, we compare random and targeted corruption strategies using Local Interpretable Model-Agnostic Explanations(LIME). We report the vulnerabilities in two popular text classification models along these corruptions and also find that targeted corruptions can expose vulnerabilities of a model better than random choices in most cases.

Ameya Prabhu, Riddhiman Dasgupta, Anush Sankaran et al.

For an unknown (new) classification dataset, choosing an appropriate deep learning architecture is often a recursive, time-taking, and laborious process. In this research, we propose a novel technique to recommend a suitable architecture from a repository of known models. Further, we predict the performance accuracy of the recommended architecture on the given unknown dataset, without the need for training the model. We propose a model encoder approach to learn a fixed length representation of deep learning architectures along with its hyperparameters, in an unsupervised fashion. We manually curate a repository of image datasets with corresponding known deep learning models and show that the predicted accuracy is a good estimator of the actual accuracy. We discuss the implications of the proposed approach for three benchmark images datasets and also the challenges in using the approach for text modality. To further increase the reproducibility of the proposed approach, the entire implementation is made publicly available along with the trained models.

Senthil Mani, Anush Sankaran, Srikanth Tamilselvam et al.

Deep Neural Networks (DNNs), with its promising performance, are being increasingly used in safety critical applications such as autonomous driving, cancer detection, and secure authentication. With growing importance in deep learning, there is a requirement for a more standardized framework to evaluate and test deep learning models. The primary challenge involved in automated generation of extensive test cases are: (i) neural networks are difficult to interpret and debug and (ii) availability of human annotators to generate specialized test points. In this research, we explain the necessity to measure the quality of a dataset and propose a test case generation system guided by the dataset properties. From a testing perspective, four different dataset quality dimensions are proposed: (i) equivalence partitioning, (ii) centroid positioning, (iii) boundary conditioning, and (iv) pair-wise boundary conditioning. The proposed system is evaluated on well known image classification datasets such as MNIST, Fashion-MNIST, CIFAR10, CIFAR100, and SVHN against popular deep learning models such as LeNet, ResNet-20, VGG-19. Further, we conduct various experiments to demonstrate the effectiveness of systematic test case generation system for evaluating deep learning models.

Srikanth Tamilselvam, Naveen Panwar, Shreya Khare et al.

Deep learning is one of the fastest growing technologies in computer science with a plethora of applications. But this unprecedented growth has so far been limited to the consumption of deep learning experts. The primary challenge being a steep learning curve for learning the programming libraries and the lack of intuitive systems enabling non-experts to consume deep learning. Towards this goal, we study the effectiveness of a no-code paradigm for designing deep learning models. Particularly, a visual drag-and-drop interface is found more efficient when compared with the traditional programming and alternative visual programming paradigms. We conduct user studies of different expertise levels to measure the entry level barrier and the developer load across different programming paradigms. We obtain a System Usability Scale (SUS) of 90 and a NASA Task Load index (TLX) score of 21 for the proposed visual programming compared to 68 and 52, respectively, for the traditional programming methods.

Vitobha Munigala, Srikanth Tamilselvam, Anush Sankaran

Persuasivenes is a creative art aimed at making people believe in certain set of beliefs. Many a times, such creativity is about adapting richness of one domain into another to strike a chord with the target audience. In this research, we present PersuAIDE! - A persuasive system based on linguistic creativity to transform given sentence to generate various forms of persuading sentences. These various forms cover multiple focus of persuasion such as memorability and sentiment. For a given simple product line, the algorithm is composed of several steps including: (i) select an appropriate well-known expression for the target domain to add memorability, (ii) identify keywords and entities in the given sentence and expression and transform it to produce creative persuading sentence, and (iii) adding positive or negative sentiment for further persuasion. The persuasive conversion were manually verified using qualitative results and the effectiveness of the proposed approach is empirically discussed.