Search Results for author:
Found 40 papers, 20 papers with code
SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks
Constructing large-scale datasets for the GitHub issue resolution task is crucial for both training and evaluating the software engineering capabilities of Large Language Models (LLMs).
Large Language Models are Qualified Benchmark Builders: Rebuilding Pre-Training Datasets for Advancing Code Intelligence Tasks
Pre-trained code models rely heavily on high-quality pre-training data, particularly human-written reference comments that bridge code and natural language.
Towards an Understanding of Context Utilization in Code Intelligence
(1) A quantitative analysis of the research landscape, including publication trends, venues, and the explored domains; (2) A novel taxonomy of context types used in code intelligence; (3) A task-oriented analysis investigating context integration strategies across diverse code intelligence tasks; (4) A critical evaluation of evaluation methodologies for context-aware methods.
RustEvo^2: An Evolving Benchmark for API Evolution in LLM-based Rust Code Generation
To address this gap, we present RustEvo, a novel framework for constructing dynamic benchmarks that evaluate the ability of LLMs to adapt to evolving Rust APIs.
Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmark
With the rapid advancement of large language models (LLMs), extensive research has been conducted to investigate the code generation capabilities of LLMs.
RepoTransBench: A Real-World Benchmark for Repository-Level Code Translation
However, even with this improvement, the Success@1 score of the best-performing LLM is only 21%, which may not meet the need for reliable automatic repository-level code translation.
LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation
In this paper, we conduct an empirical study to study the phenomena, mechanism, and mitigation of LLM hallucinations within more practical and complex development contexts in repository-level generation scenario.
RMCBench: Benchmarking Large Language Models' Resistance to Malicious Code
Despite their benefits, LLMs also pose notable risks, including the potential to generate harmful content and being abused by malicious developers to create malicious code.
Agents in Software Engineering: Survey, Landscape, and Vision
In recent years, Large Language Models (LLMs) have achieved remarkable success and have been widely used in various downstream tasks, especially in the tasks of the software engineering (SE) field.
Knowledge Probing for Graph Representation Learning
Based on the intrinsic properties of graphs, we design three probes to systematically investigate the graph representation learning process from different perspectives, respectively the node-wise level, the path-wise level, and the structural level.
Beyond Functional Correctness: Investigating Coding Style Inconsistencies in Large Language Models
In this paper, we empirically analyze the differences in coding style between the code generated by mainstream Code LLMs and the code written by human developers, and summarize coding style inconsistency taxonomy.
CoSQA+: Pioneering the Multi-Choice Code Search Benchmark with Test-Driven Agents
Semantic code search, retrieving code that matches a given natural language query, is an important task to improve productivity in software engineering.
MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution
To overcome this challenge, we empirically study the reason why LLMs fail to resolve GitHub issues and analyze the major factors.
YODA: Teacher-Student Progressive Learning for Language Models
With the teacher's guidance, the student learns to iteratively refine its answer with feedback, and forms a robust and comprehensive understanding of the posed questions.
KADEL: Knowledge-Aware Denoising Learning for Commit Message Generation
However, previous methods are trained on the entire dataset without considering the fact that a portion of commit messages adhere to good practice (i. e., good-practice commits), while the rest do not.
Code Search Debiasing:Improve Search Results beyond Overall Ranking Performance
To mitigate biases, we develop a general debiasing framework that employs reranking to calibrate search results.
Adaptive-Solver Framework for Dynamic Strategy Selection in Large Language Model Reasoning
These methods employ consistent models, sample sizes, prompting methods and levels of problem decomposition, regardless of the problem complexity.
SoTaNa: The Open-Source Software Development Assistant
To meet the demands of this dynamic field, there is a growing need for an effective software development assistant.
Modeling Orders of User Behaviors via Differentiable Sorting: A Multi-task Framework to Predicting User Post-click Conversion
Inspired by recent advances on differentiable sorting, in this paper, we propose a novel multi-task framework that leverages orders of user behaviors to predict user post-click conversion in an end-to-end approach.
Autism Spectrum Disorder Classification in Children based on Structural MRI Features Extracted using Contrastive Variational Autoencoder
Few studies conduct machine classification of ASD for participants below 5-year-old, but, with mediocre predictive accuracy.
MemoryBank: Enhancing Large Language Models with Long-Term Memory
To mimic anthropomorphic behaviors and selectively preserve memory, MemoryBank incorporates a memory updating mechanism, inspired by the Ebbinghaus Forgetting Curve theory, which permits the AI to forget and reinforce memory based on time elapsed and the relative significance of the memory, thereby offering a human-like memory mechanism.
AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models
Impressively, GPT-4 surpasses average human performance on SAT, LSAT, and math competitions, attaining a 95% accuracy rate on the SAT Math test and a 92. 5% accuracy on the English test of the Chinese national college entrance exam.
Towards Efficient Fine-tuning of Pre-trained Code Models: An Experimental Study and Beyond
Our experimental study shows that (1) lexical, syntactic and structural properties of source code are encoded in the lower, intermediate, and higher layers, respectively, while the semantic property spans across the entire model.
Exploring Representation-Level Augmentation for Code Search
In this paper, we explore augmentation methods that augment data (both code and query) at representation level which does not require additional data processing and training, and based on this we propose a general format of representation-level augmentation that unifies existing methods.
Unveiling the Black Box of PLMs with Semantic Anchors: Towards Interpretable Neural Semantic Parsing
The recent prevalence of pretrained language models (PLMs) has dramatically shifted the paradigm of semantic parsing, where the mapping from natural language utterances to structured logical forms is now formulated as a Seq2Seq task.
Make Heterophily Graphs Better Fit GNN: A Graph Rewiring Approach
Graph Neural Networks (GNNs) are popular machine learning methods for modeling graph data.
Ranked #7 on
Node Classification
on Squirrel
MM-GNN: Mix-Moment Graph Neural Network towards Modeling Neighborhood Feature Distribution
Graph Neural Networks (GNNs) have shown expressive performance on graph representation learning by aggregating information from neighbors.
Meta-data Study in Autism Spectrum Disorder Classification Based on Structural MRI
Accurate diagnosis of autism spectrum disorder (ASD) based on neuroimaging data has significant implications, as extracting useful information from neuroimaging data for ASD detection is challenging.
PrivateRec: Differentially Private Training and Serving for Federated News Recommendation
Collecting and training over sensitive personal data raise severe privacy concerns in personalized recommendation systems, and federated learning can potentially alleviate the problem by training models over decentralized user data. However, a theoretically private solution in both the training and serving stages of federated recommendation is essential but still lacking. Furthermore, naively applying differential privacy (DP) to the two stages in federated recommendation would fail to achieve a satisfactory trade-off between privacy and utility due to the high-dimensional characteristics of model gradients and hidden representations. In this work, we propose a federated news recommendation method for achieving a better utility in model training and online serving under a DP guarantee. We first clarify the DP definition over behavior data for each round in the life-circle of federated recommendation systems. Next, we propose a privacy-preserving online serving mechanism under this definition based on the idea of decomposing user embeddings with public basic vectors and perturbing the lower-dimensional combination coefficients.
Identification of Autism spectrum disorder based on a novel feature selection method and Variational Autoencoder
This paper introduces a classification framework to aid ASD diagnosis based on rs-fMRI.
CoCoSoDa: Effective Contrastive Learning for Code Search
However, there is still a lot of room for improvement in using contrastive learning for code search.
Accelerating Code Search with Deep Hashing and Code Classification
Code search is to search reusable code snippets from source code corpus based on natural languages queries.
UniXcoder: Unified Cross-Modal Pre-training for Code Representation
Furthermore, we propose to utilize multi-modal contents to learn representation of code fragment with contrastive learning, and then align representations among programming languages using a cross-modal generation task.
RACE: Retrieval-Augmented Commit Message Generation
Furthermore, RACE can boost the performance of existing Seq2Seq models in commit message generation.
No One Left Behind: Inclusive Federated Learning over Heterogeneous Devices
In this way, all the clients can participate in the model learning in FL, and the final model can be big and powerful enough.
Game of Privacy: Towards Better Federated Platform Collaboration under Privacy Restriction
To solve the game, we propose a platform negotiation method that simulates the bargaining among platforms and locally optimizes their policies via gradient descent.
On the Evaluation of Neural Code Summarization
To achieve a profound understanding of how far we are from solving this problem and provide suggestions to future research, in this paper, we conduct a systematic and in-depth analysis of 5 state-of-the-art neural code summarization models on 6 widely used BLEU variants, 4 pre-processing operations and their combinations, and 3 widely used datasets.
On the Evaluation of Commit Message Generation Models: An Experimental Study
We find that: (1) Different variants of the BLEU metric are used in previous works, which affects the evaluation and understanding of existing methods.
Is a Single Model Enough? MuCoS: A Multi-Model Ensemble Learning for Semantic Code Search
On the other hand, as a specific query may focus on one or several perspectives, it is difficult for a single query representation module to represent different user intents.
Code Completion by Modeling Flattened Abstract Syntax Trees as Graphs
Code completion has become an essential component of integrated development environments.
