Related papers: CodeCircuit: Toward Inferring LLM-Generated Code C…

Large language models (LLMs) have demonstrated impressive capabilities in various reasoning tasks, aided by techniques like chain-of-thought prompting that elicits verbalized reasoning. However, LLMs often generate text with obvious…

Recently, techniques such as explicit structured reasoning have demonstrated strong test-time scaling behavior by enforcing a separation between the model's internal "thinking" process and the final response. A key factor influencing answer…

Mechanistic interpretability identifies internal circuits responsible for model behaviors, yet translating these findings into human-understandable explanations remains an open problem. We present a pipeline that bridges circuit-level…

Large language models are increasingly deployed in settings where reliability matters, yet output-level uncertainty signals such as token probabilities, entropy, and self-consistency can become brittle under calibration--deployment…

In large language models (LLMs), code and reasoning reinforce each other: code offers an abstract, modular, and logic-driven structure that supports reasoning, while reasoning translates high-level goals into smaller, executable steps that…

This article describes a fully automated, credible autocoding chain for control systems. The framework generates code, along with guarantees of high level functional properties which can be independently verified. It relies on domain…

Recent advancements in the field of natural language generation have facilitated the use of large language models to assess the quality of generated text. Although these models have shown promising results in tasks such as machine…

This paper proposes CES, a task to evaluate the abilities of LLMs in simulating program execution and using that reasoning in programming tasks. Besides measuring the correctness of variable predictions during execution simulation, CES…

Mechanistic interpretability produces circuit-level causal analyses of neural network behaviour, but discovered circuits often remain isolated experimental artefacts: there is no shared formal representation for what circuits compute, how…

Code generation problems differ from common natural language problems - they require matching the exact syntax of the target language, identifying happy paths and edge cases, paying attention to numerous small details in the problem spec,…

Mechanism design has long been a cornerstone of economic theory, with traditional approaches relying on mathematical derivations. Recently, automated approaches, including differentiable economics with neural networks, have emerged for…

This paper investigates code LLMs' capability of static analysis during code intelligence tasks such as code summarization and generation. Code LLMs are now household names for their abilities to do some programming tasks that have…

Vibe coding inherently assumes iterative refinement of LLM-generated code through feedback loops. While effective for conventional software tasks, its reliability in runtime-adaptive systems is unclear -- especially when generated code is…

Large language models (LLMs) have recently achieved notable success in code-generation benchmarks such as HumanEval and LiveCodeBench. However, a detailed examination reveals that these evaluation suites often comprise only a limited number…

While LLM-based agents are able to tackle a wide variety of code reasoning questions, the answers are not always correct. This prevents the agent from being useful in situations where high precision is desired: (1) helping a software…

Medical large language models (LLMs) research often makes bold claims, from encoding clinical knowledge to reasoning like a physician. These claims are usually backed by evaluation on competitive benchmarks; a tradition inherited from…

Intelligent coding systems are transforming software development by enabling users to specify code behavior in natural language. However, the opaque decision-making of AI-driven coders raises trust and usability concerns, particularly for…

Vision-Language Models (VLMs) have demonstrated impressive capabilities in code generation across various domains. However, their ability to replicate complex, multi-panel visualizations from real-world data remains largely unassessed. To…

The rise of Large Language Models (LLMs) has significantly advanced various applications on software engineering tasks, particularly in code generation. Despite the promising performance, LLMs are prone to generate hallucinations, which…

Assessing the stability of code generation from large language models (LLMs) is essential for judging their reliability in real-world development. We extend prior "structural-entropy concepts" to the program domain by pairing entropy with…