Related papers: Instruction Adherence in Coding Agent Configuratio…
In code comprehension experiments, participants are usually told at the beginning what kind of code comprehension task to expect. Describing experiment scenarios and experimental tasks will influence participants in ways that are sometimes…
In active learning, the user sequentially chooses values for feature $X$ and an oracle returns the corresponding label $Y$. In this paper, we consider the effect of feature noise in active learning, which could arise either because $X$…
Large Language Models (LLMs) have recently demonstrated remarkable coding capabilities. However, assessing code generation based on well-formed properties and aligning it with developer preferences remains challenging. In this paper, we…
As large language models are deployed as autonomous agents with tool execution privileges, a critical assumption underpins their security architecture: that model errors are detectable at runtime. We present empirical evidence that this…
An essential and challenging problem in causal inference is causal effect estimation from observational data. The problem becomes more difficult with the presence of unobserved confounding variables. The front-door adjustment is a practical…
Users often make security- and privacy-relevant decisions without a clear understanding of the rules that govern safe behavior. We introduce pedagogical friction, a design approach that inserts brief, instructional interactions at the…
Important insights towards the explainability of neural networks reside in the characteristics of their decision boundaries. In this work, we borrow tools from the field of adversarial robustness, and propose a new perspective that relates…
Searching for clues, gathering evidence, and reviewing case files are all techniques used by criminal investigators to draw sound conclusions and avoid wrongful convictions. Similarly, in software engineering (SE) research, we can develop…
Multimodal creative assistants decompose user goals and route tasks to subagents for layout, styling, retrieval, and generation. Retrieval quality is pivotal, yet failures can arise at several stages: understanding user intent, choosing…
Version control relies on commit messages to convey the rationale for code changes, but these messages are often low quality and, more critically, inconsistent with their diffs-known as message-code inconsistency (MCI). MCIs mislead…
Programming courses can be challenging for first year university students, especially for those without prior coding experience. Students initially struggle with code syntax, but as more advanced topics are introduced across a semester, the…
The effectiveness and validity of applying variation partitioning methods in community ecology has been questioned. Here, using mathematical deduction and numerical simulation, we made an attempt to uncover the underlying mechanisms…
Users often interpret and select agent skills through their SKILL markdown specifications. To protect users, existing audits mainly focus on malicious or unsafe skills. We study the complementary question of whether specifications help…
Growing privacy regulations and internal governance mandates are driving demand for fine-grained, context-sensitive access control in data management systems. Among competing approaches, content-based access control -- where access…
Context: Software systems are in continuous evolution through source code changes to fixing bugs, adding new functionalities and improving the internal architecture. All these practices are recorded in the version history, which can be…
Current AI safety relies on behavioral monitoring and post-training alignment, yet empirical measurement shows these approaches produce no detectable pre-commitment signal in a majority of instruction-tuned models tested. We present an…
Real-world instructions with multiple constraints pose a significant challenge to existing large language models (LLMs). An observation is that the LLMs exhibit dramatic performance fluctuation when disturbing the order of the incorporated…
Instructors and students alike are often focused on the grade in programming assignments as a key measure of how well a student is mastering the material and whether a student is struggling. This can be, however, misleading. Especially when…
Mixed-effects models fit to observational practice data are widely used in learning analytics to estimate student-level variation in initial knowledge and learning rate, and the resulting estimates increasingly inform substantive claims…
An auditor instructs an AI assistant: "open each file individually using the Read tool -- no scripts, no agents." The AI replies "Yes" -- then issues a single batched call summarizing all fifty files at once. We call this the Compliance…