Related papers: Faver: Boosting LLM-based RTL Generation with Func…

Language models (LMs) can solve tasks such as answering questions about tables or images by writing programs. However, using primitive functions often leads to verbose and error-prone programs, and higher-level functions require expert…

Large Language Models (LLMs) show remarkable capabilities, yet their stochastic next-token prediction creates logical inconsistencies and reward hacking that formal symbolic systems avoid. To bridge this gap, we introduce a formal logic…

The ability of large language models (LLMs) to validate their output and identify potential errors is crucial for ensuring robustness and reliability. However, current research indicates that LLMs struggle with self-correction, encountering…

Assertion-based verification (ABV) serves as a crucial technique for ensuring that register-transfer level (RTL) designs adhere to their specifications. While Large Language Model (LLM) aided assertion generation approaches have recently…

Program repair techniques offer cost-saving benefits for debugging within software development and programming education scenarios. With the proven effectiveness of Large Language Models (LLMs) in code-related tasks, researchers have…

As the Large Language Model (LLM) becomes increasingly important in various domains. However, the following challenges still remain unsolved in accelerating LLM inference: (1) Synchronized partial softmax update. The softmax operation…

Large language models (LLMs) exhibit remarkable capabilities but often produce inaccurate responses, as they rely solely on their embedded knowledge. Retrieval-Augmented Generation (RAG) enhances LLMs by incorporating an external…

Large Language Models (LLMs) have demonstrated significant performance improvements across various cognitive tasks. An emerging application is using LLMs to enhance retrieval-augmented generation (RAG) capabilities. These systems require…

This paper presents a framework that integrates Large Language Models (LLMs) into translation validation, targeting LLVM compiler transformations where formal verification tools fall short. Our framework first utilizes existing formal…

Large Language Model (LLM) agents can increasingly automate complex reasoning through Test-Time Scaling (TTS), iterative refinement guided by reward signals. However, many real-world tasks involve multi-stage pipeline whose final outcomes…

Recent large language models (LLMs) achieve strong performance in generating promising reasoning paths for complex tasks. However, despite powerful generation ability, LLMs remain weak at verifying their own answers, revealing a persistent…

Program verifiers such as Dafny automate proofs by outsourcing them to an SMT solver. This automation is not perfect, however, and the solver often requires hints in the form of assertions, creating a burden for the proof engineer. In this…

Reinforcement Learning with Verifiable Rewards (RLVR) has markedly improved the performance of Large Language Models (LLMs) on tasks requiring multi-step reasoning. However, most RLVR pipelines rely on sparse outcome-based rewards,…

Alignment is a standard procedure to fine-tune pre-trained large language models (LLMs) to follow natural language instructions and serve as helpful AI assistants. We have observed, however, that the conventional alignment process fails to…

Despite the syntactic fluency of Large Language Models (LLMs), ensuring their logical correctness in high-stakes domains remains a fundamental challenge. We present a neurosymbolic framework that combines LLMs with SMT solvers to produce…

Large language models are increasingly used to produce runnable software. In practice, security is often addressed through a Detect--Repair--Verify (DRV) loop that detects issues, applies fixes, and verifies the result. This work studies…

Boundary value analysis and testing (BVT) is fundamental in software quality assurance because faults tend to cluster at input extremes, yet testers often struggle to understand and justify why certain input-output pairs represent…

The rise of automated code generation tools, such as large language models (LLMs), has introduced new challenges in ensuring the correctness and efficiency of scientific software, particularly in complex kernels, where numerical stability,…

Recent advances in large language models (LLMs) have enabled near-human performance on software coding benchmarks, but their effectiveness in RTL code generation remains limited due to the scarcity of high-quality training data. While prior…

Code generation with large language models (LLMs), often termed vibe coding, is increasingly adopted in production but fails to ensure code quality, particularly in security (e.g., SQL injection vulnerabilities) and maintainability (e.g.,…