arXiv subjects

Ryan Shar

Publications and source records attributed to Ryan Shar.

4 recordsLinked to original sources

arXiv2026

Comparing Developer and LLM Biases in Code Evaluation

As LLMs are increasingly used as judges in code applications, they should be evaluated in realistic interactive settings that capture partial context and ambiguous intent. We present TRACE (Tool for Rubric Analysis in Code Evaluation), a framework that evaluates LLM judges' ability to predict human preferences and automatically extracts rubric items to reveal systematic biases in how humans and models weigh each item. Across three modalities -- chat-based programming, IDE autocompletion, and instructed code editing -- we use TRACE to measure how well LLM judges align with developer preferences. Among 13 different models, the best judges underperform human annotators by 12-23%. TRACE identifies 35 significant sources of misalignment between humans and judges across interaction modalities, the majority of which correspond to existing software engineering code quality criteria. For example, in chat-based coding, judges are biased towards longer code explanations while humans prefer shorter ones. We find significant misalignment on the majority of existing code quality dimensions, showing alignment gaps between LLM judges and human preference in realistic coding applications.

cs.SE↗

arXiv2025

EDIT-Bench: Evaluating LLM Abilities to Perform Real-World Instructed Code Edits

Instructed code editing, where LLMs directly modify a developer's existing code based on a user instruction, is becoming a widely used interaction mode in AI coding assistants. However, few benchmarks directly evaluate this capability and current datasets often rely on artificial sources. We introduce EDIT-Bench, a benchmark for evaluating LLM code editing capabilities grounded in real-world usage, i.e., user instructions and code contexts collected in the wild. EDIT-Bench comprises of 540 problems, multiple natural and programming languages, and a diverse set of real-world use cases, ranging from resolving errors to adding features. EDIT-Bench introduces context-dependent problems that require the model to understand code context, highlighted code, and cursor position in addition to the user instruction. We evaluate 40 diverse LLMs and observe that EDIT-Bench is a challenging set of problems where only 1 model scores over 60%. We find that model performance varies across different categories of user instructions. Further, we find that varying levels of contextual information greatly affect task success rate, with performance varying up to 11%, indicating the importance of evaluating with realistic context.

cs.SE↗

arXiv2025

CodeAlignBench: Assessing Code Generation Models on Developer-Preferred Code Adjustments

As large language models become increasingly capable of generating code, evaluating their performance remains a complex and evolving challenge. Existing benchmarks primarily focus on functional correctness, overlooking the diversity of real-world coding tasks and developer expectations. To this end, we introduce a multi-language benchmark that evaluates LLM instruction-following capabilities and is extensible to operate on any set of standalone coding problems. Our benchmark evaluates instruction following in two key settings: adherence to pre-defined constraints specified with the initial problem, and the ability to perform refinements based on follow-up instructions. For this paper's analysis, we empirically evaluated our benchmarking pipeline with programming tasks from LiveBench, that are also automatically translated from Python into Java and JavaScript. Our automated benchmark reveals that models exhibit differing levels of performance across multiple dimensions of instruction-following. Our benchmarking pipeline provides a more comprehensive evaluation of code generation models, highlighting their strengths and limitations across languages and generation goals.

cs.SE↗

arXiv2025

When Benchmarks Talk: Re-Evaluating Code LLMs with Interactive Feedback

Programming is a fundamentally interactive process, yet coding assistants are often evaluated using static benchmarks that fail to measure how well models collaborate with users. We introduce an interactive evaluation pipeline to examine how LLMs incorporate different types of feedback in a collaborative setting. Specifically, we perturb static coding benchmarks so that the code model must interact with a simulated user to retrieve key information about the problem. We find that interaction significantly affects model performance, as the relative rankings of 10 models across 3 datasets often vary between static and interactive settings, despite models being fairly robust to feedback that contains errors. We also observe that even when different feedback types are equally effective with respect to performance, they can impact model behaviors such as (1) how models respond to higher- vs. lower-quality feedback and (2) whether models prioritize aesthetic vs. functional edits. Our work aims to "re-evaluate" model coding capabilities through an interactive lens toward bridging the gap between existing evaluations and real-world usage.

cs.HC↗