Related papers: Verify Implementation Equivalence of Large Models

In Earth System Modeling (ESM), meshes of different models usually do not match, requiring data mapping algorithms implemented in coupling software. Valcke et al. recently introduced a benchmark to evaluate such algorithms and compared…

The success of large language models has garnered widespread attention for model merging techniques, especially training-free methods which combine model capabilities within the parameter space. However, two challenges remain: (1) uniform…

Task based parallel programming has shown competitive outcomes in many aspects of parallel programming such as efficiency, performance, productivity and scalability. Different approaches are used by different software development frameworks…

Equivalent Representations (ERs) of code are textual representations that preserve the same semantics as the code itself, e.g., natural language comments and pseudocode. ERs play a critical role in software development and maintenance.…

Large Language Models (LLMs) exhibit strong reasoning capabilities in complex tasks. However, they still struggle with hallucinations and factual errors in knowledge-intensive scenarios like knowledge graph question answering (KGQA). We…

Retrieval-augmented generation (RAG) frameworks enable large language models (LLMs) to retrieve relevant information from a knowledge base and incorporate it into the context for generating responses. This mitigates hallucinations and…

Given two algorithms for the same problem, can we determine whether they are meaningfully different? In full generality, the question is uncomputable, and empirically it is muddied by competing notions of similarity. Yet, in many…

In this paper we promote introducing software verification and control flow graph similarity measurement in automated evaluation of students' programs. We present a new grading framework that merges results obtained by combination of these…

Temporal link prediction in dynamic graphs is a critical task with applications in diverse domains such as social networks, recommendation systems, and e-commerce platforms. While existing Temporal Graph Neural Networks (T-GNNs) have…

This paper introduces several techniques that improve the scalability of the deductive verification of data-level programs working on arrays and matrices. First of all, we introduce a technique to rewrite expressions with (nested)…

Multi-table entity matching (MEM) addresses the limitations of dual-table approaches by enabling simultaneous identification of equivalent entities across multiple data sources without unique identifiers. However, existing methods relying…

Finding bugs is key to the correctness of compilers in wide use today. If the behaviour of a compiled program, as allowed by its architecture memory model, is not a behaviour of the source program under its source model, then there is a…

Neural surrogate models are powerful and efficient tools in data mining. Meanwhile, large language models (LLMs) have demonstrated remarkable capabilities in code-related tasks, such as generation and understanding. However, an equally…

Embedding knowledge graphs (KGs) for multi-hop logical reasoning is a challenging problem due to massive and complicated structures in many KGs. Recently, many promising works projected entities and queries into a geometric space to…

A Large Language Model (LLM) is considered consistent if semantically equivalent prompts produce semantically equivalent responses. Despite recent advancements showcasing the impressive capabilities of LLMs in conversational systems, we…

Graph kernels are widely used for measuring the similarity between graphs. Many existing graph kernels, which focus on local patterns within graphs rather than their global properties, suffer from significant structure information loss when…

Learned knowledge graph representations supporting robots contain a wealth of domain knowledge that drives robot behavior. However, there does not exist an inference reconciliation framework that expresses how a knowledge graph…

A key to knowledge graph embedding (KGE) is to choose a proper representation space, e.g., point-wise Euclidean space and complex vector space. In this paper, we propose a unified perspective of embedding and introduce uncertainty into KGE…

Data quality remains an important challenge in data-driven systems, as errors in tabular data can severely compromise downstream analytics and machine learning performance. Although numerous error detection algorithms have been proposed,…

This paper introduces Auto-modeling of Formal Verification with Real-world Prompting for 5G and NextG protocols (AVRE), a novel system designed for the formal verification of Next Generation (NextG) communication protocols, addressing the…