相关论文: PassionNet: An Innovative Framework for Duplicate …

This work presents a custom approach to developing a domain specific knowledge assistant for sustainability reporting using the International Financial Reporting Standards (IFRS). In this domain, there is no publicly available…

While large language models (LLMs) such as ChatGPT and PaLM have demonstrated remarkable performance in various language understanding and generation tasks, their capabilities in complex reasoning and intricate knowledge utilization still…

Large language models (LLMs) have achieved impressive advancements across numerous disciplines, yet the critical issue of knowledge conflicts, a major source of hallucinations, has rarely been studied. Only a few research explored the…

The rapid evolution of Large Language Model (LLM) inference systems has yielded significant efficiency improvements. However, our systematic analysis reveals that current evaluation methodologies frequently exhibit fundamental flaws, often…

Anti-money laundering (AML) actions and measurements are among the priorities of financial institutions, for which machine learning (ML) has shown to have a high potential. In this paper, we propose a comprehensive and systematic approach…

Recent advances in reasoning with large language models (LLMs) have demonstrated strong performance on complex mathematical tasks, including combinatorial optimization. Techniques such as Chain-of-Thought and In-Context Learning have…

Finding the relationships between sentences in a document is crucial for tasks like fact-checking, argument mining, and text summarization. A key challenge is to identify which sentences act as premises or contradictions for a specific…

Language Model (LM) pipelines can dynamically refine their outputs against programmatic constraints. However, their effectiveness collapses when faced with competing soft constraints, leading to inefficient backtracking loops where…

Designing neural network architectures is a challenging task and knowing which specific layers of a model must be adapted to improve the performance is almost a mystery. In this paper, we introduce a novel theory and metric to identify…

Large Language Models (LLMs) have recently achieved impressive performance in math and reasoning benchmarks. However, they often struggle with logic problems and puzzles that are relatively easy for humans. To further investigate this, we…

Context: Conflicts between software requirements bring uncertainties to product development. Some great approaches have been proposed to identify these conflicts. However, they usually require the software requirements represented with…

Large language models (LLMs) have demonstrated remarkable capabilities in various software engineering tasks, such as code generation and debugging, because of their ability to translate between programming languages and natural languages.…

Machine learning models are often used to inform real world risk assessment tasks: predicting consumer default risk, predicting whether a person suffers from a serious illness, or predicting a person's risk to appear in court. Given…

Pattern matching is a powerful tool which is part of many functional programming languages as well as computer algebra systems such as Mathematica. Among the existing systems, Mathematica offers the most expressive pattern matching.…

Retrieval-Augmented Generation (RAG) systems implicitly assume mutual consistency among retrieved documents -- an assumption that frequently fails in practice. We present ConflictRAG, a conflict-aware RAG framework that detects, classifies,…

Machine learning models are often implemented in cohort with humans in the pipeline, with the model having an option to defer to a domain expert in cases where it has low confidence in its inference. Our goal is to design mechanisms for…

The issue of clone code has persisted in software engineering, primarily because developers often copy and paste code segments. This common practice has elevated the importance of clone code detection, garnering attention from both software…

Context: Due to the demand for strong algorithmic reasoning, complex logic implementation, and strict adherence to input/output formats and resource constraints, competitive programming generation by large language models (LLMs) is…

The usage of Large Language Models (LLMs) for software and test development has continued to increase since LLMs were first introduced, but only recently have the expectations of LLMs become more realistic. Verifying the correctness of code…

We propose methods to infer properties of the execution environment of machine learning pipelines by tracing characteristic numerical deviations in observable outputs. Results from a series of proof-of-concept experiments obtained on local…