Which Signals of Code Correctness Survive Distribution Shift? Hidden-State and Causal Predictors of Program and Verdict Correctness
cs.SE, cs.LG
Submitted: 2026-11-05
Updated: 2026-11-05
Terminology
Sources
- Functional Entropy: Predicting Functional Correctness in LLM-Generated Code with Uncertainty Quantification
- Using Semantic Distance to Estimate Uncertainty in LLM-Based Code Generation
- Language Models (Mostly) Know What They Know
- Assessing Correctness in LLM-Based Code Generation via Uncertainty Estimation
- Code Is More Than Text: Uncertainty Estimation for Code Generation
- Representation Engineering: A Top-Down Approach to AI Transparency
Related papers
- ArkEval: Benchmarking and Evaluating Automated CodeRepair for ArkTS
- TestPrism: Rethinking Test Evaluation Beyond a Single Reference
- Mining Workflow Graphs for Black-Box Boundary Testing of Conversational LLM Agents
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- For Coding Agents, the Repository Matters