Large language models (LLMs) have gained widespread adoption in various natural language processing tasks, including question answering and dialogue systems. However, a major drawback of LLMs is the issue of hallucination, where they generate unfaithful or inconsistent content that deviates from the input source, leading to severe consequences. In this paper, we propose a robust discriminator named RelD to effectively detect hallucination in LLMs' generated answers. RelD is trained on the constructed RelQA, a bilingual question-answering dialogue dataset along with answers generated by LLMs and a comprehensive set of metrics. Our experimental results demonstrate that the proposed RelD successfully detects hallucination in the answers generated by diverse LLMs. Moreover, it performs well in distinguishing hallucination in LLMs' generated answers from both in-distribution and out-of-distribution datasets. Additionally, we also conduct a thorough analysis of the types of hallucinations that occur and present valuable insights. This research significantly contributes to the detection of reliable answers generated by LLMs and holds noteworthy implications for mitigating hallucination in the future work.

Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models

Community question answering (CQA) becomes increasingly prevalent in recent years, providing platforms for users with various backgrounds to obtain information and share knowledge. However, the redundancy and lengthiness issues of crowd-sourced answers limit the performance of answer selection, thus leading to difficulties in reading or even misunderstandings for community users. To solve these problems, we propose the dual graph question-answer attention networks (DGQAN) for answer selection task. Aims to fully understand the internal structure of the question and the corresponding answer, firstly, we construct a dual-CQA concept graph with graph convolution networks using the original question and answer text. Specifically, our CQA concept graph exploits the correlation information between question-answer pairs to construct two sub-graphs (QSubject-Answer and QBody-Answer), respectively. Further, a novel dual attention mechanism is incorporated to model both the internal and external semantic relations among questions and answers. More importantly, we conduct experiment to investigate the impact of each layer in the BERT model. The experimental results show that DGQAN model achieves state-of-the-art performance on three datasets (SemEval-2015, 2016, and 2017), outperforming all the baseline models.

/pdf/dgqan-dual-graph-question-answer-attention-networks-for-3n8kvbxq.pdf

DGQAN: Dual Graph Question-Answer Attention Networks for Answer Selection

Abstract The collaboration among different organizations is considered one of the main benefits of moving applications and services to a cloud computing environment. Unfortunately, this collaboration raises many challenges such as the access of sensitive resources by unauthorized people. Usually, Role-Based Access-Control (RBAC) model is deployed in large organizations. This paper addresses the scalability problem of the online stored rules. This problem affects the performance of the access control system due to increasing number of shared resources and/or number of collaborating organizations in the same cloud environment. Therefore, this paper proposes replacing the cross-domain RBAC rules with Role-To-Role (RTR) mapping rules among all organizations. The RTR mapping rules are generated using a newly proposed Role-Mapping algorithm. A comparative study is performed to evaluate the proposed algorithm’s performance with concerning the Rule-Store size and the authorization response time. According to the results, it is found that the proposed algorithm reduces the number of stored rules which minimizes the Rule-Store size and reduces the authorization response time. Additionally, this paper proposes applying a concurrent approach on the RTR mapping model using the proposed Role-Mapping algorithm to achieve more savings in the authorization response time. Therefore, it will be suitable in highly-collaborative cloud environments. 

/pdf/a-novel-role-mapping-algorithm-for-enhancing-highly-2v8ix2dr.pdf

A novel role-mapping algorithm for enhancing highly collaborative access control system

/pdf/a-novel-role-mapping-algorithm-for-enhancing-highly-3c7qogwb.pdf

To solve the access control problem about multi-level multi-domain information system,a method based on security level access control model is proposed after analyzing complex information system.The experimental result has proved that the access control model has achieved the predetermined goal that it can set the security level according to kinds of factors of multi-level multi-domain information system and then control the access by the comparison of security level.And it is easier to deploy on multi-level multi-do-main information system,reacts more rapidly for change of authority,and limits the flow of unsafe information for access control model based on security level comparing with other ordinary ones.

Research of access control method on multi-level & multi-domain information system

Inter-domain access control can guarantee the safety of resources sharing among different domains, role mapping is one of the key technologies which realizing access control. Traditional mapping mechanism, which involves congested traffic, has massive computational complexity and has a big traffic. In this paper, we proposed a cross-domain role mapping model under the circumstance of multi security level, which makes the resources and roles divided into different security levels, and establishes a hierarchy tree according to the different department that containing different roles and resources. With the help of interdomain level service, we achieve the goal of cross-domain access control. Compared with the existing researches, the model in this paper is more practical and secure. KEYWORD: Multi-level; Multi-domain; Access control; Interoperation 4th International Conference on Mechanical Materials and Manufacturing Engineering (MMME 2016) © 2016. The authors Published by Atlantis Press 230

/pdf/a-multi-level-cross-domain-access-control-model-based-on-2uzlf7x041.pdf

A Multi-Level Cross-Domain Access Control Model Based On Role Mapping

Community Question Answering (CQA) provides platforms for users with various background to obtain information and share knowledge. In the recent years, with the rapid development of such online platforms, an enormous amount of archive data has accumulated which makes it more and more difficult for users to identify desirable answers. Therefore, answer selection becomes a very important subtask in Community Question Answering. A posted question often consists of two parts: a question subject with summarization of users’ intention, and a question body clarifying the subject with more details. Most of the existing answer selection techniques often roughly concatenate these two parts, so that they cause excessive noises besides useful information to questions, inevitably reducing the performance of answer selection approaches. In this paper, we propose AMQAN, an adaptive multi-attention question-answer network with embeddings at different levels, which makes comprehensive use of semantic information in questions and answers, and alleviates the noise issue at the same time. To evaluate our proposed approach, we implement experiments on two datasets, SemEval 2015 and SemEval 2017. Experiment results show that AMQAN outperforms all existing models on two standard CQA datasets.

AMQAN: Adaptive Multi-Attention Question-Answer Networks for Answer Selection

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Rui Mao

Author Tools

Chat about Author

Papers

A Multi-Level Cross-Domain Access Control Model Based On Role Mapping

AMQAN: Adaptive Multi-Attention Question-Answer Networks for Answer Selection