Fires cause a lot of casualties and economic losses. In order to prevent fire accidents in advance, it is necessary to find out the cause of the fire. Existing fire alarm systems detected fires with temperature, smoke...
详细信息
This paper presents our experience developing a Llama-based chatbot for question answering about continuous integration and continuous delivery (CI/CD) at Ericsson, a multinational telecommunications company. Our chat...
详细信息
ISBN:
(纸本)9798350395693;9798350395686
This paper presents our experience developing a Llama-based chatbot for question answering about continuous integration and continuous delivery (CI/CD) at Ericsson, a multinational telecommunications company. Our chatbot is designed to handle the specificities of CI/CD documents at Ericsson, employing a retrieval-augmented generation (RAG) model to enhance accuracy and relevance. Our empirical evaluation of the chatbot on industrial CI/CD-related questions indicates that an ensemble retriever, combining BM25 and embedding retrievers, yields the best performance. When evaluated against a ground truth of 72 CI/CD questions and answers at Ericsson, our most accurate chatbot configuration provides fully correct answers for 61.11% of the questions, partially correct answers for 26.39%, and incorrect answers for 12.50%. Through an error analysis of the partially correct and incorrect answers, we discuss the underlying causes of inaccuracies and provide insights for further refinement. We also reflect on lessons learned and suggest future directions for further improving our chatbot's accuracy.
All machine learning procedures consume a mathematical foundation. The aforementioned is applicable to Deep Learning, Optimization, and any additional Statistics science processes since Deep Knowledge is a subset of M...
详细信息
software Maintenance and Evolution (SME) is moving fast with the assistance of artificial intelligence (AI), especially Large Language Models (LLM). Researchers have already started automating various activities of th...
详细信息
ISBN:
(纸本)9798350395693;9798350395686
software Maintenance and Evolution (SME) is moving fast with the assistance of artificial intelligence (AI), especially Large Language Models (LLM). Researchers have already started automating various activities of the SME workflow. Understanding the requirements for maintenance and development work i.e. Requirements engineering (RE) is a crucial phase that kicks off the SME workflow through multiple discussions on a proposed scope of work documented in different forms. The RE phase ends with a list of user stories for each unit task and usually created and tracked on a project management tool such as GitHub, Jira, AzurDev, etc. In this research, we collaborated with Bell Mobility to develop a tool "Geneus" (Generate UserSory) using GPT-4-turbo to automatically create user stories from software requirements documents. Requirements documents are usually long and contain complex information. Since LLMs typically suffer from hallucination when the input is too complex, this paper proposes a new prompting strategy, "Refine and Thought" (RaT), to mitigate that issue and improve the performance of the LLM in prompts with large and noisy contexts. Along with manual evaluation using RUST (Readability, Understandability, Specificity, Technical-aspects) survey questionnaire, automatic evaluation with BERTScore, and AlignScore evaluation metrics are used to evaluate the results of the "Geneus" tool. Results show that our method with RaT performs consistently better in most of the cases of interactions compared to the single-shot baseline method. However, the BERTScore and AlignScore test results are not consistent. In the median case, Geneus performs significantly better in all three interactions (requirements specification, user story details, and test case specifications) according to AlignScorebut it shows slightly low performance in requirements specifications according to BERTScore. Distilling RE documents requires significant time & effort from the senior members of the
The news ticker is a common feature of many different news networks that display headlines and other *** ticker recognition applications are highly valuable in e-business and news surveillance for media regulatory ***...
详细信息
The news ticker is a common feature of many different news networks that display headlines and other *** ticker recognition applications are highly valuable in e-business and news surveillance for media regulatory *** this paper,we focus on the automatic Arabic Ticker Recognition system for the Al-Ekhbariya news *** primary emphasis of this research is on ticker recognition methods and storage *** that end,the research is aimed at character-wise explicit segmentation using a semantic segmentation technique and words identification *** proposed learning architecture considers the grouping of homogeneousshaped *** incorporates linguistic taxonomy in a unified manner to address the imbalance in data distribution which leads to individual ***,experiments with a novel ArabicNews Ticker(Al-ENT)dataset that provides accurate character-level and character components-level labeling to evaluate the effectiveness of the suggested *** proposed method attains 96.5%,outperforming the current state-of-the-art technique by 8.5%.The study reveals that our strategy improves the performance of lowrepresentation correlated character classes.
Most frequently, we decide to play a song or piece of music that best suits our current state of mind. Despite this significant link, the majority of the music software programmes available today do not yet offer the ...
详细信息
Detecting conflicting requirements early in the software development lifecycle is crucial to mitigating risks of system failures and enhancing overall reliability. While Large Language Models (LLMs) have demonstrated ...
详细信息
ISBN:
(数字)9798400712487
ISBN:
(纸本)9798400712487
Detecting conflicting requirements early in the software development lifecycle is crucial to mitigating risks of system failures and enhancing overall reliability. While Large Language Models (LLMs) have demonstrated proficiency in natural language understanding tasks, they often struggle with the nuanced reasoning required for identifying complex requirement conflicts. This paper introduces a novel framework, SAT-LLM, which integrates Satisfiability Modulo Theories (SMT) solvers with LLMs to enhance the detection of conflicting software requirements. SMT solvers provide rigorous formal reasoning capabilities, complementing LLMs' proficiency in natural language understanding. By synergizing these strengths, SAT-LLM aims to overcome the limitations of standalone LLMs in handling intricate requirement interactions. The early experiments provide empirical evidence supporting the effectiveness of our SAT-LLM over pure LLM-based methods like ChatGPT in identifying and resolving conflicting requirements. These findings lay a foundation for further exploration and refinement of hybrid approaches that integrate NLP techniques with formal reasoning methodologies to address complex challenges in software development.
Understanding software systems is a vital task, often undertaken by teams of engineers, for the development and maintenance of systems. Collaborative software visualization tools are essential in this context, yet the...
详细信息
ISBN:
(纸本)9798400705861
Understanding software systems is a vital task, often undertaken by teams of engineers, for the development and maintenance of systems. Collaborative software visualization tools are essential in this context, yet they are limited. Existing tools, particularly in virtual reality, allow exploration but lack the crucial feature of note-taking, which is a significant limitation. We present Immersive software Archaeology (ISA), a virtual reality tool that enables engineering teams to collaboratively explore and comprehend software systems. Unique to ISA, it facilitates note-taking during exploration with virtual multimedia whiteboards that support freehand diagramming, audio recordings, and VR screenshots. Notes taken on these whiteboards are synchronized with an Integrated Development Environment (IDE), providing easy access to the results of a VR exploration while performing changes to the system's source code.
Cryptographic APIs provided by Ethereum are widely adopted in decentralized applications (DApps) for cryptographic operations. However, developers who lack expertise in cryptography frequently encounter difficulties w...
详细信息
暂无评论