Implementing new features in repository-level codebases is a crucial application of code generation models. However, current benchmarks lack a dedicated evaluation framework for this capability. To fill this gap, we introduce FEA-Bench, a benchmark designed to assess the ability of large language models (LLMs) to perform incremental development within code repositories. We collect pull requests from 83 GitHub repositories and use rule-based and intent-based filtering to construct task instances focused on new feature development. Each task instance containing code changes is paired with relevant unit test files to ensure that the solution can be verified. The feature implementation requires LLMs to simultaneously possess code completion capabilities for new components and code editing abilities for other relevant parts in the code repository, providing a more comprehensive evaluation method of LLMs' automated software engineering capabilities. Experimental results show that LLMs perform significantly worse in the FEA-Bench, highlighting considerable challenges in such repository-level incremental code development.
Generative AI (GenAI) has demonstrated remarkable capabilities in code generation, and its integration into complex product modeling and simulation code generation can significantly enhance the efficiency of the system design phase in Model-Based Systems Engineering (MBSE). In this study, we introduce a generative system design methodology framework for MBSE, offering a practical approach for the intelligent generation of simulation models for system physical properties. First, we employ inference techniques, generative models, and integrated modeling and simulation languages to construct simulation models for system physical properties based on product design documents. Subsequently, we fine-tune the language model used for simulation model generation on an existing library of simulation models and additional datasets generated through generative modeling. Finally, we introduce evaluation metrics for the generated simulation models for system physical properties. Our proposed approach to simulation model generation presents the innovative concept of scalable templates for simulation models. Using these templates, GenAI generates simulation models for system physical properties through code completion. The experimental results demonstrate that, for mainstream open-source Transformer-based models, the quality of the simulation model is significantly improved using the simulation model generation method proposed in this paper.
Continual learning has become a promising solution to refine large language models incrementally by leveraging user feedback. In particular, online continual learning - iteratively training the model with small batches of user feedback - has demonstrated notable performance improvements. However, the existing practice of separating training and serving processes forces the online trainer to recompute the intermediate results already done during serving. Such redundant computations can account for 30%-42% of total training time. In this paper, we propose Alchemist, to the best of our knowledge, the first online continual learning system that efficiently reuses serving activations to increase training throughput. Alchemist introduces two key techniques: (1) recording and storing activations and KV cache only during the prefill phase to minimize latency and memory overhead; and (2) smart activation offloading and hedging. Evaluations with inputs of varied token length sampled from ShareGPT dataset show that compared with a separate training cluster, Alchemist significantly increases training throughput by up to 1.72x, reduces up to 47% memory usage during training, and supports up to 2x more training tokens - all while maintaining negligible impact on serving latency.
Smart contracts are crucial programs on blockchains, and their immutability post-deployment makes functional correctness vital. Despite progress in code completion models, benchmarks for Solidity, the primary smart contract language, are lacking. Existing metrics like BLEU do not adequately assess the functional correctness of generated smart contracts. To fill this gap, we introduce SolBench, a benchmark for evaluating the functional correctness of Solidity smart contracts generated by code completion models. SolBench includes 4,178 functions from 1,155 Ethereum-deployed contracts. Testing advanced models revealed challenges in generating correct code without context, as Solidity functions rely on context-defined variables and interfaces. To address this, we propose a Retrieval-Augmented Code Repair framework. In this framework, an executor verifies functional correctness, and if necessary, an LLM repairs the code using retrieved snippets informed by executor traces. We conduct a comprehensive evaluation of both closed-source and open-source LLMs across various model sizes and series to assess their performance in smart contract completion. The results show that code repair and retrieval techniques effectively enhance the correctness of smart contract completion while reducing computational costs.
This paper proposes a method for generating software components for embedded systems, integrating seamlessly into existing implementations without developer intervention. We demonstrate this by automatically generating hardware abstraction layer (HAL) code for GPIO operations on the STM32F407 microcontroller. Using Abstract Syntax Trees (AST) for code analysis and Retrieval-Augmented Generation (RAG) for component generation, our approach enables autonomous code completion for embedded applications.
Recently, language models (LMs) have shown impressive proficiency in code generation tasks, especially when fine-tuned on code-specific datasets, commonly known as Code LMs. However, our understanding of the internal decision-making processes of Code LMs, such as how they use their (syntactic or semantic) knowledge, remains limited, which could lead to unintended harm as they are increasingly used in real life. This motivates us to conduct one of the first Mechanistic Interpretability works to understand how Code LMs perform a syntactic completion task, specifically the closing parenthesis task, on the CodeLlama-7b model (Roziere et al. 2023). Our findings reveal that the model requires middle-later layers until it can confidently predict the correct label for the closing parenthesis task. Additionally, we identify that while both multi-head attention (MHA) and feed-forward (FF) sub-layers play essential roles, MHA is particularly crucial. Furthermore, we also discover attention heads that keep track of the number of already closed parentheses precisely but may or may not promote a correct number of closing parentheses that are still missing, leading to a positive or negative impact on the model's performance.
Speculative decoding has become a promising technique to mitigate the high inference latency of autoregressive decoding in Large Language Models (LLMs). Despite its promise, the effective application of speculative decoding in LLMs still confronts three key challenges: the increasing memory demands of the draft model, the distribution shift between the short-training corpora and long-context inference, and inefficiencies in attention implementation. In this work, we enhance the performance of speculative decoding in long-context settings by addressing these challenges. First, we propose a memory-efficient draft model with a constant-sized Key-Value (KV) cache. Second, we introduce novel position indices for short-training data, enabling seamless adaptation from short-context training to long-context inference. Finally, we present an innovative attention aggregation method that combines fast implementations for prefix computation with standard attention for tree mask handling, effectively resolving the latency and memory inefficiencies of tree decoding. Our approach achieves strong results on various long-context tasks, including repository-level code completion, long-context summarization, and o1-like long reasoning tasks, demonstrating significant improvements in latency reduction. The code is available at https://github.com/sail-sg/LongSpec.
The advent of Large Language Models (LLMs) has revolutionized code completion, transforming it into a more intelligent and context-aware feature in modern integrated development environments. These advancements have significantly enhanced developers' ability to write efficient and error-free code. This study evaluates the performance of several chat-based LLMs, including Gemini 1.5 Flash, Gemini 1.5 Pro, GPT-4o, GPT-4o-mini, and GPT-4 Turbo, using the Syntax-Aware Fill-in-the-Middle (SAFIM) dataset. This benchmark is specifically designed to assess models' capabilities in syntax-sensitive code generation. Performance metrics, such as cosine similarity with ground-truth completions and latency, were employed to measure both accuracy and efficiency. The findings reveal substantial differences in the models' code completion abilities, offering valuable insights into their respective strengths and weaknesses. This work provides a comparative analysis that underscores the trade-offs between accuracy and speed, establishing a benchmark for future advancements in LLM-based code completion.
The pace of evolution of Large Language Models (LLMs) necessitates new approaches for rigorous and comprehensive evaluation. Traditional human annotation is increasingly impracticable due to the complexities and costs involved in generating high-quality, challenging problems. In this work, we introduce CHASE, a unified framework to synthetically generate challenging problems using LLMs without human involvement. For a given task, our approach builds a hard problem in a bottom-up manner from simpler components. Moreover, our framework decomposes the generation process into independently verifiable sub-tasks, thereby ensuring a high level of quality and correctness. We implement CHASE to create evaluation benchmarks across three diverse domains: (1) document-based question answering, (2) repository-level code completion, and (3) math reasoning. The performance of state-of-the-art LLMs on these synthetic benchmarks lies in the range of 40-60% accuracy, thereby demonstrating the effectiveness of our framework at generating challenging problems. We publicly release our benchmarks and code.
Mathematical reasoning represents a critical frontier in advancing large language models (LLMs). While step-by-step approaches have emerged as the dominant paradigm for mathematical problem-solving in LLMs, the quality of reasoning steps in training data fundamentally constrains the performance of the models. Recent studies has demonstrated that more detailed intermediate steps can enhance model performance, yet existing methods for step expansion either require more powerful external models or incur substantial computational costs. In this paper, we introduce MathFimer, a novel framework for mathematical reasoning step expansion inspired by the "Fill-in-the-middle" task from code completion. By decomposing solution chains into prefix-suffix pairs and training models to reconstruct missing intermediate steps, we develop a specialized model, MathFimer-7B, on our carefully curated NuminaMath-FIM dataset. We then apply these models to enhance existing mathematical reasoning datasets by inserting detailed intermediate steps into their solution chains, creating MathFimer-expanded versions. Through comprehensive experiments on multiple mathematical reasoning datasets, including MathInstruct, MetaMathQA and etc., we demonstrate that models trained on MathFimer-expanded data consistently outperform their counterparts trained on original data across various benchmarks such as GSM8K and MATH. Our approach offers a practical, scalable solution for enhancing mathematical reasoning capabilities in LLMs without relying on powerful external models or expensive inference procedures.
Large Language Models (LLMs) are becoming integral to daily life, showcasing their vast potential across various Natural Language Processing (NLP) tasks. Beyond NLP, LLMs are increasingly used in software development tasks, such as code completion, modification, bug fixing, and code translation. Software engineers widely use tools like GitHub Copilot and Amazon Q, streamlining workflows and automating tasks with high accuracy. While the resource and energy intensity of LLM training is often highlighted, inference can be even more resource-intensive over time, as it's a continuous process with a high number of invocations. Therefore, developing resource-efficient alternatives for LLM inference is crucial for sustainability. This work proposes GREEN-CODE, a framework for energy-aware code generation in LLMs. GREEN-CODE performs dynamic early exit during LLM inference. We train a Reinforcement Learning (RL) agent that learns to balance the trade-offs between accuracy, latency, and energy consumption. Our approach is evaluated on two open-source LLMs, Llama 3.2 3B and OPT 2.7B, using the JavaCorpus and PY150 datasets. Results show that our method reduces the energy consumption between 23-50 % on average for code generation tasks without significantly affecting accuracy.
Fill-in-the-Middle (FIM) models play a vital role in code completion tasks, leveraging both prefix and suffix context to provide more accurate and contextually relevant suggestions. This paper presents approaches to improve FIM code completion while addressing the challenge of maintaining low latency for real-time coding assistance. We enhance FIM code completion by incorporating context and curriculum examples in the training process. We identify patterns where completion suggestions fail more frequently, revealing complexities that smaller language models struggle with. To address these challenges, we develop a curriculum dataset by extracting hard-to-complete patterns from code repositories and generate context examples using semantic and static analysis tools (e.g. TSC compiler). We fine-tune various sized models, including StarCoder and DeepSeek, on this enhanced dataset. Our evaluation encompasses three key dimensions: the Santa Coder FIM task, the Amazon CCEval benchmark, and a new Multi-Line Infilling evaluation benchmark derived from SWE-bench. Comprehensive ablation studies across multiple model sizes reveal that while all fine-tuned models show improvements, the performance gains are more pronounced for smaller parameter models and incorporating difficult-to-complete examples, as part of curriculum learning, improves the code completion performance. This finding is particularly significant given the latency constraints of code completion tasks. While larger models like GPT and Claude perform well in multi-line completions but are prohibitively challenging to use given high latency, and our fine-tuned models achieve a balance between performance and latency. Finally, we validate our approach through online A/B testing, demonstrating tangible improvements in Completion Acceptance Rate (CAR) and Completion Persistence Rate (CPR), with zero latency impact.
Code completion has become an essential tool for daily software development. Existing evaluation benchmarks often employ static methods that do not fully capture the dynamic nature of real-world coding environments and face significant challenges, including limited context length, reliance on superficial evaluation metrics, and potential overfitting to training datasets. In this work, we introduce a novel framework for enhancing code completion in software development through the creation of a repository-level benchmark ExecRepoBench and the instruction corpora Repo-Instruct, aim at improving the functionality of open-source large language models (LLMs) in real-world coding scenarios that involve complex interdependencies across multiple files. ExecRepoBench includes 1.2K samples from active Python repositories. Plus, we present a multi-level grammar-based completion methodology conditioned on the abstract syntax tree to mask code fragments at various logical units (e.g. statements, expressions, and functions). Then, we fine-tune the open-source LLM with 7B parameters on Repo-Instruct to produce a strong code completion baseline model Qwen2.5-Coder-Instruct-C based on the open-source model. Qwen2.5-Coder-Instruct-C is rigorously evaluated against existing benchmarks, including MultiPL-E and ExecRepoBench, which consistently outperforms prior baselines across all programming languages. The deployment of \ourmethod{} can be used as a high-performance, local service for programming development\footnote{\url{https://execrepobench.github.io/}}.
Large Language Models (LLMs) have demonstrated impressive capabilities in code completion tasks, where they assist developers by predicting and generating new code in real-time. However, existing LLM-based code completion systems primarily rely on the immediate context of the file being edited, often missing valuable repository-level information, user behaviour and edit history that could improve suggestion accuracy. Additionally, challenges such as efficiently retrieving relevant code snippets from large repositories, incorporating user behavior, and balancing accuracy with low-latency requirements in production environments remain unresolved. In this paper, we propose ContextModule, a framework designed to enhance LLM-based code completion by retrieving and integrating three types of contextual information from the repository: user behavior-based code, similar code snippets, and critical symbol definitions. By capturing user interactions across files and leveraging repository-wide static analysis, ContextModule improves the relevance and precision of generated code. We implement performance optimizations, such as index caching, to ensure the system meets the latency constraints of real-world coding environments. Experimental results and industrial practise demonstrate that ContextModule significantly improves code completion accuracy and user acceptance rates.
Recent advancements in code completion models have primarily focused on local file contexts. However, these studies do not fully capture the complexity of real-world software development, which often requires the use of rapidly-evolving public libraries. To fill the gap, we introduce LibEvolutionEval, a detailed study requiring an understanding of library evolution to perform in-line code completion accurately. LibEvolutionEval provides a version-specific code-completion task comprised of eight libraries (torch, torchvision, scipy, pil, tqdm, pyyaml, matplotlib, and pandas) as they evolve over the year along with a detailed analysis of the evolution of two popular and well-maintained public libraries: PyTorch and Matplotlib. We evaluate popular public models and find that public library evolution significantly influences model performance. We explored mitigation methods by studying how retrieved version-specific library documentation and prompting can improve the model's capability in handling these fast-evolving packages, paving a promising future path in better handling fast-evolving libraries.
Recent years have witnessed the emerging trend of extensions in modern Integrated Development Environments (IDEs) like Visual Studio Code (VSCode) that significantly enhance developer productivity. Especially, popular AI coding assistants like GitHub Copilot and Tabnine provide conveniences like automated code completion and debugging. While these extensions offer numerous benefits, they may introduce privacy and security concerns to software developers. However, there is no existing work that systematically analyzes the security and privacy concerns, including the risks of data exposure in VSCode extensions. In this paper, we investigate on the security issues of cross-extension interactions in VSCode and shed light on the vulnerabilities caused by data exposure among different extensions. Our study uncovers high-impact security flaws that could allow adversaries to stealthily acquire or manipulate credential-related data (e.g., passwords, API keys, access tokens) from other extensions if not properly handled by extension vendors. To measure their prevalence, we design a novel automated risk detection framework that leverages program analysis and natural language processing techniques to automatically identify potential risks in VSCode extensions. By applying our tool to 27,261 real-world VSCode extensions, we discover that 8.5% of them (i.e., 2,325 extensions) are exposed to credential-related data leakage through various vectors, such as commands, user input, and configurations. Our study sheds light on the security challenges and flaws of the extension-in-IDE paradigm and provides suggestions and recommendations for improving the security of VSCode extensions and mitigating the risks of data exposure.
Speculative Decoding has gained popularity as an effective technique for accelerating the auto-regressive inference process of Large Language Models. However, Speculative Decoding entirely relies on the availability of efficient draft models, which are often lacking for many existing language models due to a stringent constraint of vocabulary compatibility. In this work we introduce FastDraft, a novel and efficient approach for pre-training and aligning a draft model to any large language model by incorporating efficient pre-training, followed by fine-tuning over synthetic datasets generated by the target model. We demonstrate FastDraft by training two highly parameter efficient drafts for the popular Phi-3-mini and Llama-3.1-8B models. Using FastDraft, we were able to produce a draft model with approximately 10 billion tokens on a single server with 8 Intel$^\circledR$ Gaudi$^\circledR$ 2 accelerators in under 24 hours. Our results show that the draft model achieves impressive results in key metrics of acceptance rate, block efficiency and up to 3x memory bound speed up when evaluated on code completion and up to 2x in summarization, text completion and instruction tasks. We validate our theoretical findings through benchmarking on the latest Intel$^\circledR$ Core$^{\tiny \text{TM}}$ Ultra, achieving a wall-clock time speedup of up to 2x, indicating a significant reduction in runtime. Due to its high quality, FastDraft unlocks large language models inference on AI-PC and other edge-devices.
Text classification is a fundamental task in natural language processing (NLP), and large language models (LLMs) have demonstrated their capability to perform this task across various domains. However, the performance of LLMs heavily depends on the quality of their input prompts. Recent studies have also shown that LLMs exhibit remarkable results in code-related tasks. To leverage the capabilities of LLMs in text classification, we propose the Code Completion Prompt (CoCoP) method, which transforms the text classification problem into a code completion task. CoCoP significantly improves text classification performance across diverse datasets by utilizing LLMs' code-completion capability. For instance, CoCoP enhances the accuracy of the SST2 dataset by more than 20%. Moreover, when CoCoP integrated with LLMs specifically designed for code-related tasks (code models), such as CodeLLaMA, this method demonstrates better or comparable performance to few-shot learning techniques while using only one-tenth of the model size. The source code of our proposed method will be available to the public upon the acceptance of the paper.
The rapid evolution of software libraries presents a significant challenge for code generation models, which must adapt to frequent version updates while maintaining compatibility with previous versions. Existing code completion benchmarks often overlook this dynamic aspect, and the one that does consider it relies on static code prediction tasks without execution-based evaluation, offering a limited perspective on a model's practical usability. To address this gap, we introduce \textbf{\GitChameleon{}}, a novel, manually curated dataset comprising 116 Python code completion problems, each conditioned on specific library versions and accompanied by executable unit tests. \GitChameleon{} is designed to rigorously assess the ability of modern large language models (LLMs) to generate version-specific code that is not only syntactically correct but also functionally accurate upon execution. Our comprehensive evaluations reveal that state-of-the-art LLMs struggle with this task; for instance, \textbf{GPT-4o} achieves a pass@10 of only 39.9\% (43.7\% when provided with error feedback), highlighting the complexity of the problem and the limitations of current models. By providing an execution-based benchmark that emphasizes the dynamic nature of code libraries, \GitChameleon{} serves as a critical tool to advance the development of more adaptable and reliable code generation models. For facilitation for further exploration of version-conditioned code generation, we make our code repository publicly accessible at \url{https://github.com/NizarIslah/GitChameleon}.
Accurate document retrieval is crucial for the success of retrieval-augmented generation (RAG) applications, including open-domain question answering and code completion. While large language models (LLMs) have been employed as dense encoders or listwise rerankers in RAG systems, they often struggle with reasoning-intensive tasks because they lack nuanced analysis when judging document relevance. To address this limitation, we introduce JudgeRank, a novel agentic reranker that emulates human cognitive processes when assessing document relevance. Our approach consists of three key steps: (1) query analysis to identify the core problem, (2) document analysis to extract a query-aware summary, and (3) relevance judgment to provide a concise assessment of document relevance. We evaluate JudgeRank on the reasoning-intensive BRIGHT benchmark, demonstrating substantial performance improvements over first-stage retrieval methods and outperforming other popular reranking approaches. In addition, JudgeRank performs on par with fine-tuned state-of-the-art rerankers on the popular BEIR benchmark, validating its zero-shot generalization capability. Through comprehensive ablation studies, we demonstrate that JudgeRank's performance generalizes well across LLMs of various sizes while ensembling them yields even more accurate reranking than individual models.