Related papers: Finding Cross-rule Optimization Bugs in Datalog En…

Assessing the correctness of distributed and parallel applications is notoriously difficult due to the complexity of the concurrent behaviors and the difficulty to reproduce bugs. In this context, Dynamic Partial Order Reduction (DPOR)…

Fixing static analysis alerts in source code with Large Language Models (LLMs) is becoming increasingly popular. However, LLMs often hallucinate and perform poorly for complex and less common alerts. Retrieval-augmented generation (RAG)…

Deep Learning (DL) library bugs affect downstream DL applications, emphasizing the need for reliable systems. Generating valid input programs for fuzzing DL libraries is challenging due to the need for satisfying both language…

Missing data is an important problem in machine learning practice. Starting from the premise that imputation methods should preserve the causal structure of the data, we develop a regularization scheme that encourages any baseline…

Language models can use verifiable rewards to improve at a wide variety of reasoning tasks. However, both parametric (e.g. RLVR) and non-parametric (e.g. prompt optimization) approaches to doing so typically require hundreds of training…

Chain-of-thought prompting~(CoT) and tool augmentation have been validated in recent work as effective practices for improving large language models~(LLMs) to perform step-by-step reasoning on complex math-related tasks. However, most…

Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs). However, standard RAG pipelines often fail to ensure that model reasoning remains consistent with the…

Careful curation of data sources can significantly improve the performance of LLM pre-training, but predominant approaches rely heavily on intuition or costly trial-and-error, making them difficult to generalize across different data…

The effectiveness of AI debugging follows a predictable exponential decay pattern; most models lose 60-80% of their debugging capability within just 2-3 attempts, despite iterative debugging being a critical capability for practical code…

Dead code introduces several challenges in software development, such as increased binary size and maintenance difficulties. It can also obscure logical errors and be exploited for obfuscation in malware. For LLM-based code-related tasks,…

Retrieval-augmented generation (RAG) has emerged as one of the most prominent applications of vector databases. By integrating documents retrieved from a database into the prompt of a large language model (LLM), RAG enables more reliable…

Significantly simplifying the creation of optimization models for real-world business problems has long been a major goal in applying mathematical optimization more widely to important business and societal decisions. The recent…

While search-augmented large language models (LLMs) exhibit impressive capabilities, their reliability in complex multi-hop reasoning remains limited. This limitation arises from three fundamental challenges: decomposition errors, where…

State-of-the-art Datalog engines include expressive features such as ADTs (structured heap values), stratified aggregation and negation, various primitive operations, and the opportunity for further extension using FFIs. Current…

Deep learning benefits from the growing abundance of available data. Meanwhile, efficiently dealing with the growing data scale has become a challenge. Data publicly available are from different sources with various qualities, and it is…

The performance of multi-objective evolutionary algorithms deteriorates appreciably in solving many-objective optimization problems which encompass more than three objectives. One of the known rationales is the loss of selection pressure…

We typically compute aggregate statistics on held-out test data to assess the generalization of machine learning models. However, statistics on test data often overstate model generalization, and thus, the performance of deployed machine…

Automatically generating bug reproduction tests (BRT) from issue descriptions is crucial for software maintenance. LLM-based approaches have shown great potential for this task. Their effectiveness heavily relies on retrieving high-quality…

Bug localization is a tedious activity in the bug fixing process in which a software developer tries to locate bugs in the source code described in a bug report. Since this process is time-consuming and requires additional knowledge about…

Software systems evolve continuously through frequent code changes, yet such changes often introduce unintended bugs despite extensive testing and code review. Existing testing approaches are largely constrained to predefined execution…