Measuring LLM Trust Allocation Across Conflicting Software Artifacts

LLM-based software engineering assistants fail not only by producing incorrect outputs, but also by allocating trust to the wrong artifact when code, documentation, and tests disagree. Existing evaluations focus mainly on downstream outcomes and therefore cannot reveal whether a model recognized degraded evidence, identified the unreliable source, or calibrated its trust across artifacts. We present TRACE (Trust Reasoning over Artifacts for Calibrated Evaluation), a framework that elicits structured artifact-level trust traces over Javadoc, method signatures, implementations, and test prefixes under blind perturbations. Using 22,339 valid traces from seven models on 456 curated Java method bundles, we evaluate per-artifact quality assessment, inconsistency detection, affected artifact attribution, and source prioritization. Across all models, quality penalties are largely localized to the perturbed artifact and increase with severity, but sensitivity is asymmetric across artifact types: documentation bugs induce a substantially larger heavy-to-subtle gap than implementation faults (0.152-0.253 vs. 0.049-0.123). Models detect explicit documentation bugs well (67-94%) and Javadoc and implementation contradictions at 50-91%, yet show a systematic blind spot when only the implementation drifts while the documentation remains plausible, with detection dropping by 7-42 percentage points. Confidence is poorly calibrated for six of seven models. These findings suggest that current LLMs are better at auditing natural-language specifications than at detecting subtle code-level drift, motivating explicit artifact-level trust reasoning before correctness-critical downstream use.

Exploring the Effectiveness of Large Language Models in Generating Unit Tests

A code generation model generates code by taking a prompt from a code comment, existing code, or a combination of both. Although code generation models (e.g., GitHub Copilot) are increasingly being adopted in practice, it is unclear whether they can successfully be used for unit test generation without fine-tuning. To fill this gap, we investigated how well three generative models (CodeGen, Codex, and GPT-3.5) can generate test cases. We used two benchmarks (HumanEval and Evosuite SF110) to investigate the context generation's effect in the unit test generation process. We evaluated the models based on compilation rates, test correctness, coverage, and test smells. We found that the Codex model achieved above 80% coverage for the HumanEval dataset, but no model had more than 2% coverage for the EvoSuite SF110 benchmark. The generated tests also suffered from test smells, such as Duplicated Asserts and Empty Tests.