Decalage: Uncovering the Gap Between Model-Generated Reasoning and Actual Code Implementation in Small Language Models
cs.SE
Submitted: 2026-11-09
Updated: 2026-11-09
Terminology
Sources
- Measuring Faithfulness in Chain-of-Thought Reasoning
- How Secure is Code Generated by ChatGPT?
- Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models
- The Illusion of Safety: Multi-Tier Verification of AI vs. Human C++ Code
- ReAct: Synergizing Reasoning and Acting in Language Models
- Small Language Models are the Future of Agentic AI
- Qwen2.5-Coder Technical Report
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