Large Language Models (LLMs) have gained considerable traction within the Software Engineering (SE) community, impacting various SE tasks from code completion to test generation, from program repair to code summarization. Despite their promise, researchers must still be careful as numerous intricate factors can influence the outcomes of experiments involving LLMs. This paper initiates an open discussion on potential threats to the validity of LLM-based research including issues such as closed-source models, possible data leakage between LLM training data and research evaluation, and the reproducibility of LLM-based findings. In response, this paper proposes a set of guidelines tailored for SE researchers and Language Model (LM) providers to mitigate these concerns. The implications of the guidelines are illustrated using existing good practices followed by LLM providers and a practical example for SE researchers in the context of test case generation.
We present RepoST, a scalable method to construct environments that provide execution feedback for repository-level code generation for both training and evaluation. Unlike existing works that aim to build entire repositories for execution, which is challenging for both human and LLMs, we provide execution feedback with sandbox testing, which isolates a given target function and its dependencies to a separate script for testing. Sandbox testing reduces the complexity of external dependencies and enables constructing environments at a large scale. We use our method to construct RepoST-Train, a large-scale train set with 7,415 functions from 832 repositories. Training with the execution feedback provided by RepoST-Train leads to a performance gain of 5.5% Pass@1 on HumanEval and 3.5% Pass@1 on RepoEval. We also build an evaluation dataset, RepoST-Eval, and benchmark 12 code generation models.
This paper presents a system developed for SemEval 2025 Task 8: Question Answering (QA) over tabular data. Our approach integrates several key components: text-to-SQL and text-to-code generation modules, a self-correction mechanism, and a retrieval-augmented generation (RAG). Additionally, it includes an end-to-end (E2E) module, all orchestrated by a large language model (LLM). Through ablation studies, we analyzed the effects of different parts of our pipeline and identified the challenges that are still present in this field. During the evaluation phase of the competition, our solution achieved an accuracy of 80%, resulting in a top-13 ranking among the 38 participating teams. Our pipeline demonstrates a significant improvement in accuracy for open-source models and achieves a performance comparable to proprietary LLMs in QA tasks over tables. The code is available at GitHub repository.
We introduce a method for the generation of images from an input scene graph. The method separates between a layout embedding and an appearance embedding. The dual embedding leads to generated images that better match the scene graph, have higher visual quality, and support more complex scene graphs. In addition, the embedding scheme supports multiple and diverse output images per scene graph, which can be further controlled by the user. We demonstrate two modes of per-object control: (i) importing elements from other images, and (ii) navigation in the object space, by selecting an appearance archetype. Our code is publicly available at https://www.github.com/ashual/scene_generation
Generating ultra-long sequences with large language models (LLMs) has become increasingly crucial but remains a highly time-intensive task, particularly for sequences up to 100K tokens. While traditional speculative decoding methods exist, simply extending their generation limits fails to accelerate the process and can be detrimental. Through an in-depth analysis, we identify three major challenges hindering efficient generation: frequent model reloading, dynamic key-value (KV) management and repetitive generation. To address these issues, we introduce TOKENSWIFT, a novel framework designed to substantially accelerate the generation process of ultra-long sequences while maintaining the target model's inherent quality. Experimental results demonstrate that TOKENSWIFT achieves over 3 times speedup across models of varying scales (1.5B, 7B, 8B, 14B) and architectures (MHA, GQA). This acceleration translates to hours of time savings for ultra-long sequence generation, establishing TOKENSWIFT as a scalable and effective solution at unprecedented lengths. Code can be found at https://github.com/bigai-nlco/TokenSwift.
We present CodeBERT, a bimodal pre-trained model for programming language (PL) and nat-ural language (NL). CodeBERT learns general-purpose representations that support downstream NL-PL applications such as natural language codesearch, code documentation generation, etc. We develop CodeBERT with Transformer-based neural architecture, and train it with a hybrid objective function that incorporates the pre-training task of replaced token detection, which is to detect plausible alternatives sampled from generators. This enables us to utilize both bimodal data of NL-PL pairs and unimodal data, where the former provides input tokens for model training while the latter helps to learn better generators. We evaluate CodeBERT on two NL-PL applications by fine-tuning model parameters. Results show that CodeBERT achieves state-of-the-art performance on both natural language code search and code documentation generation tasks. Furthermore, to investigate what type of knowledge is learned in CodeBERT, we construct a dataset for NL-PL probing, and evaluate in a zero-shot setting where parameters of pre-trained models are fixed. Results show that CodeBERT performs better than previous pre-trained models on NL-PL probing.
Large language models (LLMs) have demonstrated remarkable capabilities in code-related tasks, such as code understanding and code generation. However, an equally important yet underexplored question is whether LLMs can serve as general-purpose surrogate code executors, to predict the output and behavior of a program without actually running it. To systematically investigate this capability, we introduce SURGE, a comprehensive benchmark covering eight key aspects: multi-language programming tasks, competition-level programming problems, repository-level code analysis, high-cost scientific computing, time-complexity-intensive algorithms, buggy code analysis, programs dependent on specific compilers or execution environments, and formal mathematical proof verification. We evaluate multiple open-source and proprietary LLMs on SURGE and conduct a scaling study to analyze the impact of model size and training data scale on surrogate execution accuracy. Additionally, we categorize model prediction errors and explore potential areas for improvement. Our findings indicate that while LLMs can predict code execution results in certain cases, they exhibit limitations in general-purpose surrogate execution. This study provides empirical insights into the feasibility of using LLMs as surrogate code executors. Code and dataset are released at https://github.com/Imbernoulli/SURGE.
Code-mixing and script-mixing are prevalent across online social networks and multilingual societies. However, a user's preference toward code-mixing depends on the socioeconomic status, demographics of the user, and the local context, which existing generative models mostly ignore while generating code-mixed texts. In this work, we make a pioneering attempt to develop a persona-aware generative model to generate texts resembling real-life code-mixed texts of individuals. We propose a Persona-aware Generative Model for Code-mixed Generation, PARADOX, a novel Transformer-based encoder-decoder model that encodes an utterance conditioned on a user's persona and generates code-mixed texts without monolingual reference data. We propose an alignment module that re-calibrates the generated sequence to resemble real-life code-mixed texts. PARADOX generates code-mixed texts that are semantically more meaningful and linguistically more valid. To evaluate the personification capabilities of PARADOX, we propose four new metrics -- CM BLEU, CM Rouge-1, CM Rouge-L and CM KS. On average, PARADOX achieves 1.6 points better CM BLEU, 47% better perplexity and 32% better semantic coherence than the non-persona-based counterparts.
A number of researchers have recently questioned the necessity of increasingly complex neural network (NN) architectures. In particular, several recent papers have shown that simpler, properly tuned models are at least competitive across several NLP tasks. In this work, we show that this is also the case for text generation from structured and unstructured data. We consider neural table-to-text generation and neural question generation (NQG) tasks for text generation from structured and unstructured data, respectively. Table-to-text generation aims to generate a description based on a given table, and NQG is the task of generating a question from a given passage where the generated question can be answered by a certain sub-span of the passage using NN models. Experimental results demonstrate that a basic attention-based seq2seq model trained with the exponential moving average technique achieves the state of the art in both tasks. Code is available at https://github.com/h-shahidi/2birds-gen.
Large language models (LLMs) bring unprecedented flexibility in defining and executing complex, creative natural language generation (NLG) tasks. Yet, this flexibility brings new challenges, as it introduces new degrees of freedom in formulating the task inputs and instructions and in evaluating model performance. To facilitate the exploration of creative NLG tasks, we propose a three-component research framework that consists of systematic input manipulation, reference data, and output measurement. We use this framework to explore citation text generation -- a popular scholarly NLP task that lacks consensus on the task definition and evaluation metric and has not yet been tackled within the LLM paradigm. Our results highlight the importance of systematically investigating both task instruction and input configuration when prompting LLMs, and reveal non-trivial relationships between different evaluation metrics used for citation text generation. Additional human generation and human evaluation experiments provide new qualitative insights into the task to guide future research in citation text generation. We make our code and data publicly available.
Tokenization is an understudied and often neglected component of modern LLMs. Most published works use a single tokenizer for all experiments, often borrowed from another model, without performing ablations or analysis to optimize tokenization. Moreover, the tokenizer is generally kept unchanged when fine-tuning a base model. In this paper, we show that the size, pre-tokenization regular expression, and training data of a tokenizer can significantly impact the model's generation speed, effective context size, memory usage, and downstream performance. We train specialized Byte-Pair Encoding code tokenizers, and conduct extensive ablations on the impact of tokenizer design on the performance of LLMs for code generation tasks such as HumanEval and MBPP, and provide recommendations for tokenizer hyper-parameters selection and switching the tokenizer in a pre-trained LLM. We perform our experiments on models trained from scratch and from pre-trained models, verifying their applicability to a wide range of use-cases. We find that when fine-tuning on more than 50 billion tokens, we can specialize the tokenizer of a pre-trained LLM to obtain large gains in generation speed and effective context size.
Language models (LMs) have become a staple of the code-writing toolbox. Their pre-training recipe has, however, remained stagnant over recent years, barring the occasional changes in data sourcing and filtering strategies. In particular, research exploring modifications to Code-LMs' pre-training objectives, geared towards improving data efficiency and better disentangling between syntax and semantics, has been noticeably sparse, especially compared with corresponding efforts in natural language LMs. In this work, we examine grounding on obfuscated code as a means of helping Code-LMs look beyond the surface-form syntax and enhance their pre-training sample efficiency. To this end, we compile ObscuraX, a dataset of approximately 55M source and obfuscated code pairs in seven languages. Subsequently, we pre-train ObscuraCoder models, ranging in size from 255M to 2.8B parameters, on a 272B-token corpus that includes ObscuraX and demonstrate that our obfuscation-based pre-training recipe leads to consistent improvements in Code-LMs' abilities compared to both vanilla autoregressive pre-training as well as existing de-obfuscation (DOBF) objectives. ObscuraCoder demonstrates sizeable gains across multiple tests of syntactic and semantic code understanding, along with improved capabilities in multilingual code completion, multilingual code commit summarization, and multi-purpose library-oriented code generation.
Code data in large language model (LLM) pretraining is recognized crucial not only for code-related tasks but also for enhancing general intelligence of LLMs. Current open-source LLMs often heavily rely on human effort to produce their code pretraining data, such as employing hand-crafted filtering rules tailored to individual programming languages, or using human-annotated data to train quality filters. However, these approaches are inherently limited in scalability, prone to subjective biases, and costly to extend and maintain across diverse programming languages. To address these challenges, we introduce Seed-Coder, a series of open-source LLMs comprising base, instruct and reasoning models of 8B size, minimizing human involvement in data construction. Our code pretraining data is produced by a model-centric data pipeline, which predominantly leverages LLMs for scoring and filtering code data. The instruct model is further trained via supervised fine-tuning and preference optimization, and the reasoning model leverages Long-Chain-of-Thought (LongCoT) reinforcement learning to improve multi-step code reasoning. Seed-Coder achieves state-of-the-art results among open-source models of similar size and even surpasses some much larger models, demonstrating superior performance in code generation, code completion, code editing, code reasoning, and software engineering tasks.
Feature generation aims to generate new and meaningful features to create a discriminative representation space.A generated feature is meaningful when the generated feature is from a feature pair with inherent feature interaction. In the real world, experienced data scientists can identify potentially useful feature-feature interactions, and generate meaningful dimensions from an exponentially large search space, in an optimal crossing form over an optimal generation path. But, machines have limited human-like abilities.We generalize such learning tasks as self-optimizing feature generation. Self-optimizing feature generation imposes several under-addressed challenges on existing systems: meaningful, robust, and efficient generation. To tackle these challenges, we propose a principled and generic representation-crossing framework to solve self-optimizing feature generation.To achieve hashing representation, we propose a three-step approach: feature discretization, feature hashing, and descriptive summarization. To achieve reinforcement crossing, we develop a hierarchical reinforcement feature crossing approach.We present extensive experimental results to demonstrate the effectiveness and efficiency of the proposed method. The code is available at https://github.com/yingwangyang/HRC_feature_cross.git.
Recent advances in 3D generation have been remarkable, with methods such as DreamFusion leveraging large-scale text-to-image diffusion-based models to guide 3D object generation. These methods enable the synthesis of detailed and photorealistic textured objects. However, the appearance of 3D objects produced by such text-to-3D models is often unpredictable, and it is hard for single-image-to-3D methods to deal with images lacking a clear subject, complicating the generation of appearance-controllable 3D objects from complex images. To address these challenges, we present IPDreamer, a novel method that captures intricate appearance features from complex $\textbf{I}$mage $\textbf{P}$rompts and aligns the synthesized 3D object with these extracted features, enabling high-fidelity, appearance-controllable 3D object generation. Our experiments demonstrate that IPDreamer consistently generates high-quality 3D objects that align with both the textual and complex image prompts, highlighting its promising capability in appearance-controlled, complex 3D object generation. Our code is available at https://github.com/zengbohan0217/IPDreamer.
We propose a novel Generative Adversarial Network (XingGAN or CrossingGAN) for person image generation tasks, i.e., translating the pose of a given person to a desired one. The proposed Xing generator consists of two generation branches that model the person's appearance and shape information, respectively. Moreover, we propose two novel blocks to effectively transfer and update the person's shape and appearance embeddings in a crossing way to mutually improve each other, which has not been considered by any other existing GAN-based image generation work. Extensive experiments on two challenging datasets, i.e., Market-1501 and DeepFashion, demonstrate that the proposed XingGAN advances the state-of-the-art performance both in terms of objective quantitative scores and subjective visual realness. The source code and trained models are available at https://github.com/Ha0Tang/XingGAN.
Personalized models have demonstrated remarkable success in understanding and generating concepts provided by users. However, existing methods use separate concept tokens for understanding and generation, treating these tasks in isolation. This may result in limitations for generating images with complex prompts. For example, given the concept $\langle bo\rangle$, generating "$\langle bo\rangle$ wearing its hat" without additional textual descriptions of its hat. We call this kind of generation personalized knowledge-driven generation. To address the limitation, we present UniCTokens, a novel framework that effectively integrates personalized information into a unified vision language model (VLM) for understanding and generation. UniCTokens trains a set of unified concept tokens to leverage complementary semantics, boosting two personalized tasks. Moreover, we propose a progressive training strategy with three stages: understanding warm-up, bootstrapping generation from understanding, and deepening understanding from generation to enhance mutual benefits between both tasks. To quantitatively evaluate the unified VLM personalization, we present UnifyBench, the first benchmark for assessing concept understanding, concept generation, and knowledge-driven generation. Experimental results on UnifyBench indicate that UniCTokens shows competitive performance compared to leading methods in concept understanding, concept generation, and achieving state-of-the-art results in personalized knowledge-driven generation. Our research demonstrates that enhanced understanding improves generation, and the generation process can yield valuable insights into understanding. Our code and dataset will be released at: \href{https://github.com/arctanxarc/UniCTokens}{https://github.com/arctanxarc/UniCTokens}.
Source code representation with deep learning techniques is an important research field. There have been many studies that learn sequential or structural information for code representation. But sequence-based models and non-sequence-models both have their limitations. Researchers attempt to incorporate structural information to sequence-based models, but they only mine part of token-level hierarchical structure information. In this paper, we analyze how the complete hierarchical structure influences the tokens in code sequences and abstract this influence as a property of code tokens called hierarchical embedding. The hierarchical embedding is further divided into statement-level global hierarchy and token-level local hierarchy. Furthermore, we propose the Hierarchy Transformer (HiT), a simple but effective sequence model to incorporate the complete hierarchical embeddings of source code into a Transformer model. We demonstrate the effectiveness of hierarchical embedding on learning code structure with an experiment on variable scope detection task. Further evaluation shows that HiT outperforms SOTA baseline models and show stable training efficiency on three source code-related tasks involving classification and generation tasks across 8 different datasets.
Generative modeling has evolved to a notable field of machine learning. Deep polynomial neural networks (PNNs) have demonstrated impressive results in unsupervised image generation, where the task is to map an input vector (i.e., noise) to a synthesized image. However, the success of PNNs has not been replicated in conditional generation tasks, such as super-resolution. Existing PNNs focus on single-variable polynomial expansions which do not fare well to two-variable inputs, i.e., the noise variable and the conditional variable. In this work, we introduce a general framework, called CoPE, that enables a polynomial expansion of two input variables and captures their auto- and cross-correlations. We exhibit how CoPE can be trivially augmented to accept an arbitrary number of input variables. CoPE is evaluated in five tasks (class-conditional generation, inverse problems, edges-to-image translation, image-to-image translation, attribute-guided generation) involving eight datasets. The thorough evaluation suggests that CoPE can be useful for tackling diverse conditional generation tasks. The source code of CoPE is available at \url{https://github.com/grigorisg9gr/polynomial_nets_for_conditional_generation}.
The automatic generation of visualizations is an old task that, through the years, has shown more and more interest from the research and practitioner communities. Recently, large language models (LLM) have become an interesting option for supporting generative tasks related to visualization, demonstrating initial promising results. At the same time, several pitfalls, like the multiple ways of instructing an LLM to generate the desired result, the different perspectives leading the generation (code-based, image-based, grammar-based), and the presence of hallucinations even for the visualization generation task, make their usage less affordable than expected. Following similar initiatives for benchmarking LLMs, this paper copes with the problem of modeling the evaluation of a generated visualization through an LLM. We propose a theoretical evaluation stack, EvaLLM, that decomposes the evaluation effort in its atomic components, characterizes their nature, and provides an overview of how to implement and interpret them. We also designed and implemented an evaluation platform that provides a benchmarking resource for the visualization generation task. The platform supports automatic and manual scoring conducted by multiple assessors to support a fine-grained and semantic evaluation based on the EvaLLM stack. Two case studies on GPT3.5-turbo with Code Interpreter and Llama2-70-b models show the benefits of EvaLLM and illustrate interesting results on the current state-of-the-art LLM-generated visualizations.