Recent code large language models (LLMs) have shown promising performance in generating standalone functions but face limitations in repository-level code generation due to their lack of awareness of repository-level dependencies (e.g., user-defined attributes), resulting in dependency errors such as undefined-variable and no-member errors. In this work, we introduce ToolGen, an approach that integrates autocompletion tools into the code LLM generation process to address these dependencies. ToolGen comprises two main phases: Data Augmentation and Model Fine-tuning (Offline), and Tool-integrated Code Generation (Online). During the offline phase, ToolGen augments functions within a given code corpus with a special mark token, indicating positions to trigger autocompletion tools. These augmented functions, along with their corresponding docstrings, are then used to fine-tune a selected code LLM. In the online phase, ToolGen iteratively generates functions by predicting tokens step-by-step using the fine-tuned LLM. Whenever a mark token is encountered, ToolGen invokes the autocompletion tool to suggest code completions and selects the most appropriate one. We conduct comprehensive experiments to evaluate ToolGen's effectiveness in repository-level code generation. To facilitate this evaluation, we create a benchmark comprising 680 real-world code repositories and introduce two new repository-level metrics: Dependency Coverage and Success Rate. The results demonstrate that ToolGen significantly improves dependency coverage by 15.2% to 45.8% and success rates by 10.9% to 42.2% across three distinct code LLMs, while maintaining competitive performance in widely-recognized similarity metrics. Furthermore, our generalizability evaluation confirms ToolGen's consistent performance when applied to diverse code LLMs, including various model architectures and scales.
相關內容
這個新版本的工具會議系列恢復了從1989年到2012年的50個會議的傳統。工具最初是“面向對象語言和系統的技術”，后來發展到包括軟件技術的所有創新方面。今天許多最重要的軟件概念都是在這里首次引入的。2019年TOOLS 50+1在俄羅斯喀山附近舉行，以同樣的創新精神、對所有與軟件相關的事物的熱情、科學穩健性和行業適用性的結合以及歡迎該領域所有趨勢和社區的開放態度，延續了該系列。
官網鏈接： ·
大語言模型
·
MoDELS
·
Processing（編程語言）
·
可辨認的
·
Large language models (LLMs) demonstrate remarkable multilingual capabilities without being pre-trained on specially curated multilingual parallel corpora. It remains a challenging problem to explain the underlying mechanisms by which LLMs process multilingual texts. In this paper, we delve into the composition of Transformer architectures in LLMs to pinpoint language-specific regions. Specially, we propose a novel detection method, language activation probability entropy (LAPE), to identify language-specific neurons within LLMs. Based on LAPE, we conduct comprehensive experiments on two representative LLMs, namely LLaMA-2 and BLOOM. Our findings indicate that LLMs' proficiency in processing a particular language is predominantly due to a small subset of neurons, primarily situated in the models' top and bottom layers. Furthermore, we showcase the feasibility to "steer" the output language of LLMs by selectively activating or deactivating language-specific neurons. Our research provides important evidence to the understanding and exploration of the multilingual capabilities of LLMs.
Transformer-based language models for automatic code completion have shown great promise so far, yet the evaluation of these models rarely uses real data. This study provides both quantitative and qualitative assessments of three public code language models when completing real-world code. We first developed an open-source IDE extension, Code4Me, for the online evaluation of the models. We collected real auto-completion usage data for over a year from more than 1200 users, resulting in over 600K valid completions. These models were then evaluated using six standard metrics across twelve programming languages. Next, we conducted a qualitative study of 1690 real-world completion requests to identify the reasons behind the poor model performance. A comparative analysis of the models' performance in online and offline settings was also performed, using benchmark synthetic datasets and two masking strategies. Our findings suggest that while developers utilize code completion across various languages, the best results are achieved for mainstream languages such as Python and Java. InCoder outperformed the other models across all programming languages, highlighting the significance of training data and objectives. Our study also revealed that offline evaluations do not accurately reflect real-world scenarios. Upon qualitative analysis of the model's predictions, we found that 66.3% of failures were due to the models' limitations, 24.4% occurred due to inappropriate model usage in a development context, and 9.3% were valid requests that developers overwrote. Given these findings, we propose several strategies to overcome the current limitations. These include refining training objectives, improving resilience to typographical errors, adopting hybrid approaches, and enhancing implementations and usability.
The recent surge in generative AI technologies, such as large language models and diffusion models, have boosted the development of AI applications in various domains, including science, finance, and education. Concurrently, adaptive learning, a concept that has gained substantial interest in the educational sphere, has proven its efficacy in enhancing students' learning efficiency. In this position paper, we aim to shed light on the intersectional studies of these two methods, which combine generative AI with adaptive learning concepts. By presenting discussions about the benefits, challenges, and potentials in this field, we argue that this union will contribute significantly to the development of the next stage learning format in education.
Large language models (LLMs) have made significant strides in reasoning capabilities, with ongoing efforts to refine their reasoning through self-correction. However, recent studies suggest that self-correction can be limited or even counterproductive without external accurate knowledge, raising questions about the limits and effectiveness of self-correction. In this paper, we aim to enhance LLM's self-checking capabilities by meticulously designing training data, thereby improving the accuracy of self-correction. We conduct a detailed analysis of error types in mathematical reasoning and develop a tailored prompt, termed "Step CoT Check". Then we construct a checking-correction dataset for training models. After integrating the original CoT data and checking-correction data for training, we observe that models could improve their self-checking capabilities, thereby enhancing their self-correction capacity and eliminating the need for external feedback or ground truth labels to ascertain the endpoint of correction. We compare the performance of models fine-tuned with the "Step CoT Check" prompt against those refined using other promps within the context of checking-correction data. The "Step CoT Check" outperforms the other two check formats in model with lager parameters, providing more precise feedback thus achieving a higher rate of correctness. For reproducibility, all the datasets and codes are provided in //github.com/bammt/Learn-to-check.
While enabling large language models to implement function calling (known as APIs) can greatly enhance the performance of Large Language Models (LLMs), function calling is still a challenging task due to the complicated relations between different APIs, especially in a context-learning setting without fine-tuning. This paper introduces ``Reverse Chain'', a controllable, target-driven approach designed to empower LLMs with the capability to operate external APIs only via prompts. Recognizing that most LLMs have limited tool-use capabilities, Reverse Chain limits LLMs to executing simple tasks, e.g., API Selection and Argument Completion. Furthermore, to manage a controllable multi-function calling, Reverse Chain adopts a generic rule based on a backward reasoning process. This rule determines when to do API selection or Argument completion. To evaluate the multi-tool-use capability of LLMs, we have released a compositional multi-tool task dataset, available at \url{//anonymous.4open.science/r/reverse-chain-8681}. Extensive numerical experiments validate the remarkable proficiency of Reverse Chain in managing multiple API calls.
Large language models (LLMs) have shown the ability to produce fluent and cogent content, presenting both productivity opportunities and societal risks. To build trustworthy AI systems, it is imperative to distinguish between machine-generated and human-authored content. The leading zero-shot detector, DetectGPT, showcases commendable performance but is marred by its intensive computational costs. In this paper, we introduce the concept of conditional probability curvature to elucidate discrepancies in word choices between LLMs and humans within a given context. Utilizing this curvature as a foundational metric, we present **Fast-DetectGPT**, an optimized zero-shot detector, which substitutes DetectGPT's perturbation step with a more efficient sampling step. Our evaluations on various datasets, source models, and test conditions indicate that Fast-DetectGPT not only surpasses DetectGPT by a relative around 75% in both the white-box and black-box settings but also accelerates the detection process by a factor of 340, as detailed in Table 1. See \url{//github.com/baoguangsheng/fast-detect-gpt} for code, data, and results.
Recently, large language models (LLMs) have been successful in relational extraction (RE) tasks, especially in the few-shot learning. An important problem in the field of RE is long-tailed data, while not much attention is currently paid to this problem using LLM approaches. Therefore, in this paper, we propose SLCoLM, a model collaboration framework, to mitigate the data long-tail problem. In our framework, We use the ``\textit{Training-Guide-Predict}'' strategy to combine the strengths of pre-trained language models (PLMs) and LLMs, where a task-specific PLM framework acts as a tutor, transfers task knowledge to the LLM, and guides the LLM in performing RE tasks. Our experiments on a RE dataset rich in relation types show that the approach in this paper facilitates RE of long-tail relation types.
Recent diffusion-based generative models show promise in their ability to generate text images, but limitations in specifying the styles of the generated texts render them insufficient in the realm of typographic design. This paper proposes a typographic text generation system to add and modify text on typographic designs while specifying font styles, colors, and text effects. The proposed system is a novel combination of two off-the-shelf methods for diffusion models, ControlNet and Blended Latent Diffusion. The former functions to generate text images under the guidance of edge conditions specifying stroke contours. The latter blends latent noise in Latent Diffusion Models (LDM) to add typographic text naturally onto an existing background. We first show that given appropriate text edges, ControlNet can generate texts in specified fonts while incorporating effects described by prompts. We further introduce text edge manipulation as an intuitive and customizable way to produce texts with complex effects such as ``shadows'' and ``reflections''. Finally, with the proposed system, we successfully add and modify texts on a predefined background while preserving its overall coherence.
The emergence of large language models (LLMs) has substantially influenced natural language processing, demonstrating exceptional results across various tasks. In this study, we employ ``Introspective Tips" to facilitate LLMs in self-optimizing their decision-making. By introspectively examining trajectories, LLM refines its policy by generating succinct and valuable tips. Our method enhances the agent's performance in both few-shot and zero-shot learning situations by considering three essential scenarios: learning from the agent's past experiences, integrating expert demonstrations, and generalizing across diverse games. Importantly, we accomplish these improvements without fine-tuning the LLM parameters; rather, we adjust the prompt to generalize insights from the three aforementioned situations. Our framework not only supports but also emphasizes the advantage of employing LLM in in-contxt decision-making. Experiments involving over 100 games in TextWorld illustrate the superior performance of our approach.
Visual Question Answering (VQA) models have struggled with counting objects in natural images so far. We identify a fundamental problem due to soft attention in these models as a cause. To circumvent this problem, we propose a neural network component that allows robust counting from object proposals. Experiments on a toy task show the effectiveness of this component and we obtain state-of-the-art accuracy on the number category of the VQA v2 dataset without negatively affecting other categories, even outperforming ensemble models with our single model. On a difficult balanced pair metric, the component gives a substantial improvement in counting over a strong baseline by 6.6%.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191