The success of language models in code assistance has spurred the proposal of repository-level code completion as a means to enhance prediction accuracy, utilizing the context from the entire codebase. However, this amplified context can inadvertently increase inference latency, potentially undermining the developer experience and deterring tool adoption - a challenge we termed the Context-Latency Conundrum. This paper introduces REPOFUSE, a pioneering solution designed to enhance repository-level code completion without the latency trade-off. REPOFUSE uniquely fuses two types of context: the analogy context, rooted in code analogies, and the rationale context, which encompasses in-depth semantic relationships. We propose a novel rank truncated generation (RTG) technique that efficiently condenses these contexts into prompts with restricted size. This enables REPOFUSE to deliver precise code completions while maintaining inference efficiency. Through testing with the CrossCodeEval suite, REPOFUSE has demonstrated a significant leap over existing models, achieving a 40.90% to 59.75% increase in exact match (EM) accuracy for code completions and a 26.8% enhancement in inference speed. Beyond experimental validation, REPOFUSE has been integrated into the workflow of a large enterprise, where it actively supports various coding tasks.
Machine learning models trained on code and related artifacts offer valuable support for software maintenance but suffer from interpretability issues due to their complex internal variables. These concerns are particularly significant in safety-critical applications where the models' decision-making processes must be reliable. The specific features and representations learned by these models remain unclear, adding to the hesitancy in adopting them widely. To address these challenges, we introduce DeepCodeProbe, a probing approach that examines the syntax and representation learning abilities of ML models designed for software maintenance tasks. Our study applies DeepCodeProbe to state-of-the-art models for code clone detection, code summarization, and comment generation. Findings reveal that while small models capture abstract syntactic representations, their ability to fully grasp programming language syntax is limited. Increasing model capacity improves syntax learning but introduces trade-offs such as increased training time and overfitting. DeepCodeProbe also identifies specific code patterns the models learn from their training data. Additionally, we provide best practices for training models on code to enhance performance and interpretability, supported by an open-source replication package for broader application of DeepCodeProbe in interpreting other code-related models.
One of the successful early implementation of deep learning AI technology was on letter recognition. With the recent breakthrough of artificial intelligence (AI) brings more solid technology for complex problems like handwritten letter recognition and even automatic generation of them. In this research, we proposed deep learning framework called Ludwig AI Framework(LAIF) for Germany Suetterlin letter recognition and generation. To recognize Suetterlin letter, we proposed deep convolutional neural network. Since lack of big amount of data to train for the deep models and huge cost to label existing hard copy of handwritten letters, we also introduce the methodology with deep generative adversarial network to generate handwritten letters as synthetic data. Main source code is in https://github.com/enkhtogtokh/LAIF repository.
Making neural visual generative models controllable by logical reasoning systems is promising for improving faithfulness, transparency, and generalizability. We propose the Abductive visual Generation (AbdGen) approach to build such logic-integrated models. A vector-quantized symbol grounding mechanism and the corresponding disentanglement training method are introduced to enhance the controllability of logical symbols over generation. Furthermore, we propose two logical abduction methods to make our approach require few labeled training data and support the induction of latent logical generative rules from data. We experimentally show that our approach can be utilized to integrate various neural generative models with logical reasoning systems, by both learning from scratch or utilizing pre-trained models directly. The code is released at https://github.com/future-item/AbdGen.
The development of generative artificial intelligence for human motion generation has expanded rapidly, necessitating a unified evaluation framework. This paper presents a detailed review of eight evaluation metrics for human motion generation, highlighting their unique features and shortcomings. We propose standardized practices through a unified evaluation setup to facilitate consistent model comparisons. Additionally, we introduce a novel metric that assesses diversity in temporal distortion by analyzing warping diversity, thereby enhancing the evaluation of temporal data. We also conduct experimental analyses of three generative models using a publicly available dataset, offering insights into the interpretation of each metric in specific case scenarios. Our goal is to offer a clear, user-friendly evaluation framework for newcomers, complemented by publicly accessible code.
Tailoring outputs from large language models, like ChatGPT, to implicit user preferences remains a challenge despite their impressive generative capabilities. In this paper, we propose a tri-agent generation pipeline comprising a generator, an instructor, and an editor to enhance output personalization. The generator produces an initial output, the instructor automatically generates editing instructions based on user preferences, and the editor refines the output to align with those preferences. The inference-only large language model (ChatGPT) serves as both the generator and editor, with a smaller model acting as the instructor to guide output generation. We train the instructor using editor-steered reinforcement learning, leveraging feedback from a large-scale editor model to optimize instruction generation. Experimental results on two abstractive summarization datasets demonstrate the effectiveness of our approach in generating outputs that better meet user expectations. Code is available at \url{https://github.com/Wendy-Xiao/chatgpt_editing_summ}
We consider the problem of generating periodic materials with deep models. While symmetry-aware molecule generation has been studied extensively, periodic materials possess different symmetries, which have not been completely captured by existing methods. In this work, we propose SyMat, a novel material generation approach that can capture physical symmetries of periodic material structures. SyMat generates atom types and lattices of materials through generating atom type sets, lattice lengths and lattice angles with a variational auto-encoder model. In addition, SyMat employs a score-based diffusion model to generate atom coordinates of materials, in which a novel symmetry-aware probabilistic model is used in the coordinate diffusion process. We show that SyMat is theoretically invariant to all symmetry transformations on materials and demonstrate that SyMat achieves promising performance on random generation and property optimization tasks. Our code is publicly available as part of the AIRS library (https://github.com/divelab/AIRS).
Code-switching (CSW) is the act of alternating between two or more languages within a single discourse. This phenomenon is widespread in multilingual communities, and increasingly prevalent in online content, where users naturally mix languages in everyday communication. As a result, Large Language Models (LLMs), now central to content processing and generation, are frequently exposed to code-switched inputs. Given their widespread use, it is crucial to understand how LLMs process and reason about such mixed-language text. This paper presents a systematic evaluation of LLM comprehension under code-switching by generating CSW variants of established reasoning and comprehension benchmarks. While degradation is evident when foreign tokens disrupt English text$\unicode{x2013}$even under linguistic constraints$\unicode{x2013}$embedding English into other languages often improves comprehension. Though prompting yields mixed results, fine-tuning offers a more stable path to degradation mitigation.
Pre-trained large language models (LLMs) have significantly improved code generation. As these models scale up, there is an increasing need for the output to handle more intricate tasks and to be appropriately specialized to particular domains. Here, we target bioinformatics due to the amount of domain knowledge, algorithms, and data operations this discipline requires. We present BioCoder, a benchmark developed to evaluate LLMs in generating bioinformatics-specific code. BioCoder spans much of the field, covering cross-file dependencies, class declarations, and global variables. It incorporates 1,026 Python functions and 1,243 Java methods extracted from GitHub, along with 253 examples from the Rosalind Project, all pertaining to bioinformatics. Using topic modeling, we show that the overall coverage of the included code is representative of the full spectrum of bioinformatics calculations. BioCoder incorporates a fuzz-testing framework for evaluation. We have applied it to evaluate various models including InCoder, CodeGen, CodeGen2, SantaCoder, StarCoder, StarCoder+, InstructCodeT5+, GPT-3.5, and GPT- 4. Furthermore, we fine-tuned one model (StarCoder), demonstrating that our training dataset can enhance the performance on our testing benchmark (by >15% in terms of Pass@K under certain prompt configurations and always >3%). The results highlight two key aspects of successful models: (1) Successful models accommodate a long prompt (> 2,600 tokens) with full context, including functional dependencies. (2) They contain domain-specific knowledge of bioinformatics, beyond just general coding capability. This is evident from the performance gain of GPT-3.5/4 compared to the smaller models on our benchmark (50% vs. up to 25%). Availability and implementation: Code is available at: https://github.com/gersteinlab/biocoder and https://biocoder-benchmark. github.io/.
Most business process automation is still developed using traditional automation technologies such as workflow engines. These systems provide domain specific languages that require both business knowledge and programming skills to effectively use. As such, business users often lack adequate programming skills to fully leverage these code oriented environments. We propose a paradigm for the construction of business automations using natural language. The approach applies a large language model to translate business rules and automations described in natural language, into a domain specific language interpretable by a business rule engine. We compare the performance of various language model configurations, across various target domains, and explore the use of constrained decoding to ensure syntactically correct generation of output.
Code review is a vital but demanding aspect of software development, generating significant interest in automating review comments. Traditional evaluation methods for these comments, primarily based on text similarity, face two major challenges: inconsistent reliability of human-authored comments in open-source projects and the weak correlation of text similarity with objectives like enhancing code quality and detecting defects. This study empirically analyzes benchmark comments using a novel set of criteria informed by prior research and developer interviews. We then similarly revisit the evaluation of existing methodologies. Our evaluation framework, DeepCRCEval, integrates human evaluators and Large Language Models (LLMs) for a comprehensive reassessment of current techniques based on the criteria set. Besides, we also introduce an innovative and efficient baseline, LLM-Reviewer, leveraging the few-shot learning capabilities of LLMs for a target-oriented comparison. Our research highlights the limitations of text similarity metrics, finding that less than 10% of benchmark comments are high quality for automation. In contrast, DeepCRCEval effectively distinguishes between high and low-quality comments, proving to be a more reliable evaluation mechanism. Incorporating LLM evaluators into DeepCRCEval significantly boosts efficiency, reducing time and cost by 88.78% and 90.32%, respectively. Furthermore, LLM-Reviewer demonstrates significant potential of focusing task real targets in comment generation.
Generating music with coherent structure, harmonious instrumental and vocal elements remains a significant challenge in song generation. Existing language models and diffusion-based methods often struggle to balance global coherence with local fidelity, resulting in outputs that lack musicality or suffer from incoherent progression and mismatched lyrics. This paper introduces $\textbf{SongBloom}$, a novel framework for full-length song generation that leverages an interleaved paradigm of autoregressive sketching and diffusion-based refinement. SongBloom employs an autoregressive diffusion model that combines the high fidelity of diffusion models with the scalability of language models. Specifically, it gradually extends a musical sketch from short to long and refines the details from coarse to fine-grained. The interleaved generation paradigm effectively integrates prior semantic and acoustic context to guide the generation process. Experimental results demonstrate that SongBloom outperforms existing methods across both subjective and objective metrics and achieves performance comparable to the state-of-the-art commercial music generation platforms. Audio samples are available on our demo page: https://cypress-yang.github.io/SongBloom_demo. The code and model weights have been released on https://github.com/Cypress-Yang/SongBloom .
Multiple business scenarios require an automated generation of descriptive human-readable text from structured input data. Hence, fact-to-text generation systems have been developed for various downstream tasks like generating soccer reports, weather and financial reports, medical reports, person biographies, etc. Unfortunately, previous work on fact-to-text (F2T) generation has focused primarily on English mainly due to the high availability of relevant datasets. Only recently, the problem of cross-lingual fact-to-text (XF2T) was proposed for generation across multiple languages alongwith a dataset, XALIGN for eight languages. However, there has been no rigorous work on the actual XF2T generation problem. We extend XALIGN dataset with annotated data for four more languages: Punjabi, Malayalam, Assamese and Oriya. We conduct an extensive study using popular Transformer-based text generation models on our extended multi-lingual dataset, which we call XALIGNV2. Further, we investigate the performance of different text generation strategies: multiple variations of pretraining, fact-aware embeddings and structure-aware input encoding. Our extensive experiments show that a multi-lingual mT5 model which uses fact-aware embeddings with structure-aware input encoding leads to best results on average across the twelve languages. We make our code, dataset and model publicly available, and hope that this will help advance further research in this critical area.
Diffusion language models offer unique benefits over autoregressive models due to their potential for parallelized generation and controllability, yet they lag in likelihood modeling and are limited to fixed-length generation. In this work, we introduce a class of block diffusion language models that interpolate between discrete denoising diffusion and autoregressive models. Block diffusion overcomes key limitations of both approaches by supporting flexible-length generation and improving inference efficiency with KV caching and parallel token sampling. We propose a recipe for building effective block diffusion models that includes an efficient training algorithm, estimators of gradient variance, and data-driven noise schedules to minimize the variance. Block diffusion sets a new state-of-the-art performance among diffusion models on language modeling benchmarks and enables generation of arbitrary-length sequences. We provide the code, along with the model weights and blog post on the project page: https://m-arriola.com/bd3lms
We describe a novel approach to automating unit test generation for Java methods using large language models (LLMs). Existing LLM-based approaches rely on sample usage(s) of the method to test (focal method) and/or provide the entire class of the focal method as input prompt and context. The former approach is often not viable due to the lack of sample usages, especially for newly written focal methods. The latter approach does not scale well enough; the bigger the complexity of the focal method and larger associated class, the harder it is to produce adequate test code (due to factors such as exceeding the prompt and context lengths of the underlying LLM). We show that augmenting prompts with \emph{concise} and \emph{precise} context information obtained by program analysis %of the focal method increases the effectiveness of generating unit test code through LLMs. We validate our approach on a large commercial Java project and a popular open-source Java project.
The future work section of a scientific article outlines potential research directions by identifying gaps and limitations of a current study. This section serves as a valuable resource for early-career researchers seeking unexplored areas and experienced researchers looking for new projects or collaborations. In this study, we generate future work suggestions from key sections of a scientific article alongside related papers and analyze how the trends have evolved. We experimented with various Large Language Models (LLMs) and integrated Retrieval-Augmented Generation (RAG) to enhance the generation process. We incorporate a LLM feedback mechanism to improve the quality of the generated content and propose an LLM-as-a-judge approach for evaluation. Our results demonstrated that the RAG-based approach with LLM feedback outperforms other methods evaluated through qualitative and quantitative metrics. Moreover, we conduct a human evaluation to assess the LLM as an extractor and judge. The code and dataset for this project are here, code: HuggingFace
Text-to-image generation has recently emerged as a viable alternative to text-to-image retrieval, due to the visually impressive results of generative diffusion models. Although query performance prediction is an active research topic in information retrieval, to the best of our knowledge, there is no prior study that analyzes the difficulty of queries (prompts) in text-to-image generation, based on human judgments. To this end, we introduce the first dataset of prompts which are manually annotated in terms of image generation performance. In order to determine the difficulty of the same prompts in image retrieval, we also collect manual annotations that represent retrieval performance. We thus propose the first benchmark for joint text-to-image prompt and query performance prediction, comprising 10K queries. Our benchmark enables: (i) the comparative assessment of the difficulty of prompts/queries in image generation and image retrieval, and (ii) the evaluation of prompt/query performance predictors addressing both generation and retrieval. We present results with several pre-generation/retrieval and post-generation/retrieval performance predictors, thus providing competitive baselines for future research. Our benchmark and code is publicly available under the CC BY 4.0 license at https://github.com/Eduard6421/PQPP.
Rerunning a metric-based evaluation should be more straightforward, and results should be closer, than in a human-based evaluation, especially where code and model checkpoints are made available by the original authors. As this report of our efforts to rerun a metric-based evaluation of a set of single-attribute and multiple-attribute controllable text generation (CTG) techniques shows however, such reruns of evaluations do not always produce results that are the same as the original results, and can reveal errors in the reporting of the original work.
Recently, diffusion models have emerged as a new paradigm for generative models. Despite the success in domains using continuous signals such as vision and audio, adapting diffusion models to natural language is under-explored due to the discrete nature of texts, especially for conditional generation. We tackle this challenge by proposing DiffuSeq: a diffusion model designed for sequence-to-sequence (Seq2Seq) text generation tasks. Upon extensive evaluation over a wide range of Seq2Seq tasks, we find DiffuSeq achieving comparable or even better performance than six established baselines, including a state-of-the-art model that is based on pre-trained language models. Apart from quality, an intriguing property of DiffuSeq is its high diversity during generation, which is desired in many Seq2Seq tasks. We further include a theoretical analysis revealing the connection between DiffuSeq and autoregressive/non-autoregressive models. Bringing together theoretical analysis and empirical evidence, we demonstrate the great potential of diffusion models in complex conditional language generation tasks. Code is available at \url{https://github.com/Shark-NLP/DiffuSeq}
Despite their impressive performance, large language models (LMs) still struggle with reliably generating complex output structures when not finetuned to follow the required output format exactly. To address this issue, grammar-constrained decoding (GCD) can be used to control the generation of LMs, guaranteeing that the output follows a given structure. Most existing GCD methods are, however, limited to specific tasks, such as parsing or code generation. In this work, we demonstrate that formal grammars can describe the output space for a much wider range of tasks and argue that GCD can serve as a unified framework for structured NLP tasks in general. For increased flexibility, we introduce input-dependent grammars, which allow the grammar to depend on the input and thus enable the generation of different output structures for different inputs. We then empirically demonstrate the power and flexibility of GCD-enhanced LMs on (1) information extraction, (2) entity disambiguation, and (3) constituency parsing. Our results indicate that grammar-constrained LMs substantially outperform unconstrained LMs or even beat task-specific finetuned models. Grammar constraints thus hold great promise for harnessing off-the-shelf LMs for a wide range of structured NLP tasks, especially where training data is scarce or finetuning is expensive. Code and data: https://github.com/epfl-dlab/GCD.