Related papers: Teaching LLMs Program Semantics via Symbolic Execu…
Formal verification of large C programs is impeded by state-space explosion: Bounded Model Checking (BMC) tools must encode the entire state space up to the predetermined bound by unrolling all nested constructs. We present ConVer, a…
Chain-of-thought (CoT) reasoning improves large language models (LLMs) on difficult tasks, but it also makes inference expensive because every intermediate step must be generated as a discrete token. Latent reasoning reduces visible token…
Security vulnerabilities often arise unintentionally during development due to a lack of security expertise and code complexity. Traditional tools, such as static and dynamic analysis, detect vulnerabilities only after they are introduced…
With the rapid growth of large language models for code generation, distinguishing between human-written and AI-generated code has become increasingly critical for academic integrity, hiring evaluations, and software security. We present…
The aim of SemEval-2024 Task 1, "Semantic Textual Relatedness for African and Asian Languages" is to develop models for identifying semantic textual relatedness (STR) between two sentences using multiple languages (14 African and Asian…
Large Reasoning Models (LRMs) demonstrate strong performance on complex tasks but often suffer from excessive verbosity, known as "overthinking." Existing solutions via reinforcement learning (RL) typically penalize generated tokens to…
Large language models (LLMs) have achieved state-of-the-art performance in various software engineering tasks, including error detection, clone detection, and code translation, primarily leveraging high-resource programming languages like…
Recent advances in reasoning-focused Large Language Models (LLMs) have introduced Chain-of-Thought (CoT) traces - intermediate reasoning steps generated before a final answer. These traces, as in DeepSeek R1, guide inference and train…
Large language models (LLMs) have recently demonstrated excellent performance in text embedding tasks. Previous work usually use LoRA to fine-tune existing LLMs, which are limited by the data and training gap between LLMs and embedding…
Many privacy-type properties of security protocols can be modelled using trace equivalence properties in suitable process algebras. It has been shown that such properties can be decided for interesting classes of finite processes (i.e.,…
The automated program repair field has attracted substantial interest over the years, but despite significant research efforts, creating a system that works well for complex semantic bugs such as security vulnerabilities has proven…
Ensuring the correctness of smart contracts is critical, as even subtle flaws can lead to severe financial losses. While bug detection tools able to spot common vulnerability patterns can serve as a first line of defense, most real-world…
Trace analysis can be a useful way to discover problems in a program under test. Rather than writing a special purpose trace analysis tool, this paper proposes that traces can usefully be analysed by checking them against a formal model…
Language models can be used to provide interactive, personalized student feedback in educational settings. However, real-world deployment faces three key challenges: privacy concerns, limited computational resources, and the need for…
Equipping Large Language Model (LLM) agents with domain-specific skills is critical for tackling complex tasks. Yet, manual authoring creates a severe scalability bottleneck. Conversely, automated skill generation often yields fragile or…
In the digital age, ensuring the correctness, safety, and reliability of software through formal verification is paramount, particularly as software increasingly underpins critical infrastructure. Formal verification, split into theorem…
Scientific hypothesis generation is a critical bottleneck in accelerating research, yet existing datasets for training and evaluating hypothesis-generating models are limited to single domains and lack explicit reasoning traces connecting…
As large language models (LLMs) become integral to code-related tasks, a central question emerges: Do LLMs truly understand program semantics? We introduce EquiBench, a new benchmark for evaluating LLMs through equivalence checking, i.e.,…
We describe a technique for systematic testing of multi-threaded programs. We combine Quasi-Optimal Partial-Order Reduction, a state-of-the-art technique that tackles path explosion due to interleaving non-determinism, with symbolic…
With the increasing use of large language models (LLMs) in medical decision-support, it is essential to evaluate not only their final answers but also the reliability of their reasoning. Two key risks are Chain-of-Thought (CoT) faithfulness…