Recent Advances towards Safe, Responsible, and Moral Dialogue Systems: A Survey

Deng, Jiawen; Sun, Han‐Dong; Zhang, Zhexin; Cheng, Jiale; Huang, Minlie

doi:10.48550/arxiv.2302.09270

Cited by 6 publications

(6 citation statements)

References 130 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…to identify the truthfulness of statements. However, with the rising enforcement of LLM safety policies [130], specific prompts are not necessary to help judge the credibility of statements. While explicit prompting helps in obtaining higher-quality LLM responses, LLMs can provide factual evidence refuting such claims without the need to supply prompts.…”

Section: Llms In Tackling Disinformation and Misinformationmentioning

confidence: 99%

Navigating the Web of Disinformation and Misinformation: Large Language Models as Double-Edged Swords

Shah,

Thapa,

Acharya

et al. 2024

IEEE Access

View full text Add to dashboard Cite

This paper explores the dual role of Large Language Models (LLMs) in the context of online misinformation and disinformation. In today's digital landscape, where the internet and social media facilitate the rapid dissemination of information, discerning between accurate content and falsified information presents a formidable challenge. Misinformation, often arising unintentionally, and disinformation, crafted deliberately, are at the forefront of this challenge. LLMs such as OpenAI's GPT-4, equipped with advanced language generation abilities, present a double-edged sword in this scenario. While they hold promise in combating misinformation by fact-checking and detecting LLM-generated text, their ability to generate realistic, contextually relevant text also poses risks for creating and propagating misinformation. Further, LLMs are plagued with many problems such as biases, knowledge cutoffs, and hallucinations, which may further perpetuate misinformation and disinformation. The paper outlines historical developments in misinformation detection and how it affects social media consumption, especially among youth, and introduces LLMs and their applications in various domains. It then critically analyzes the potential of LLMs to generate and counter misinformation and disinformation in sensitive topics such as healthcare, COVID-19, and political agendas. Further, it discusses mitigation strategies, ethical considerations, and regulatory measures, summarizing previous methods and proposing future research direction toward leveraging the benefits of LLMs while minimizing misuse risks. The paper concludes by acknowledging LLMs as powerful tools with significant implications in both spreading and combating misinformation in the digital age.

show abstract

Section: Llms In Tackling Disinformation and Misinformationmentioning

confidence: 99%

Navigating the Web of Disinformation and Misinformation: Large Language Models as Double-Edged Swords

Shah,

Thapa,

Acharya

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…These models possess the ability to generate informative, interesting, and harmless responses, making conversational agents much more usable. The application of LLMs in dialog systems has the potential to transform the way users interact with technology, creating more engaging and effective conversational experiences [303]. Further research in this area can lead to improvements in the quality and effectiveness of dialog systems, making them even more valuable for a range of applications and industries.…”

Section: H Dialog Systemsmentioning

confidence: 99%

Large Language Models: A Comprehensive Survey of its Applications, Challenges, Limitations, and Future Prospects

Hadi,

tashi,

Qureshi

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>Within the vast expanse of computerized language processing, a revolutionary entity known as Large Language Models (LLMs) has emerged, wielding immense power in its capacity to comprehend intricate linguistic patterns and conjure coherent and contextually fitting responses. Large language models (LLMs) are a type of artificial intelligence (AI) that have emerged as powerful tools for a wide range of tasks, including natural language processing (NLP), machine translation, and question-answering. This survey paper provides a comprehensive overview of LLMs, including their history, architecture, training methods, applications, and challenges. The paper begins by discussing the fundamental concepts of generative AI and the architecture of generative pre- trained transformers (GPT). It then provides an overview of the history of LLMs, their evolution over time, and the different training methods that have been used to train them. The paper then discusses the wide range of applications of LLMs, including medical, education, finance, and engineering. It also discusses how LLMs are shaping the future of AI and how they can be used to solve real-world problems. The paper then discusses the challenges associated with deploying LLMs in real-world scenarios, including ethical considerations, model biases, interpretability, and computational resource requirements. It also highlights techniques for enhancing the robustness and controllability of LLMs, and addressing bias, fairness, and generation quality issues. Finally, the paper concludes by highlighting the future of LLM research and the challenges that need to be addressed in order to make LLMs more reliable and useful. This survey paper is intended to provide researchers, practitioners, and enthusiasts with a comprehensive understanding of LLMs, their evolution, applications, and challenges. By consolidating the state-of-the-art knowledge in the field, this survey serves as a valuable resource for further advancements in the development and utilization of LLMs for a wide range of real-world applications. The GitHub repo for this project is available at https://github.com/anas-zafar/LLM-Survey</p>

show abstract

“…According to Deng et al (2023), main safety issues can be divided into 4 categories: (1) abusive and toxic contents (Poletto et al, 2021;Schmidt and Wiegand, 2017;Davidson et al, 2017), (2) unfairness and discrimination (Barikeri et al, 2021;Nangia et al, 2020;Sap et al, 2020;Dhamala et al, 2021), (3) ethics and morality issues (Lourie et al, 2021;Hendrycks et al, 2021;Forbes et al, 2020;Jiang et al, 2021), ( 4) risk of misleading and privacy information (Carlini et al, 2021;Pan et al, 2020;Carlini et al, 2019;Bang et al, 2021a;Zhang et al, 2023b). In recent years, many datasets have been created to help detect these safety issues (Levy et al, 2022;Sun et al, 2022;Zampieri et al, 2019;Zhang et al, 2022bZhang et al, , 2023a.…”

Section: Safety Detectionmentioning

confidence: 99%

InstructSafety: A Unified Framework for Building Multidimensional and Explainable Safety Detector through Instruction Tuning

Zhang,

Cheng,

Sun

et al. 2023

Findings of the Association for Computational Linguistics: EMNLP 2023

View full text Add to dashboard Cite

Safety detection has been an increasingly important topic in recent years and it has become even more necessary to develop reliable safety detection systems with the rapid development of large language models. However, currently available safety detection systems have limitations in terms of their versatility and interpretability. In this paper, we first introduce INSTRUCTSAFETY, a safety detection framework that unifies 7 common sub-tasks for safety detection. These tasks are unified into a similar form through different instructions. We then conduct a comprehensive survey of existing safety detection datasets and process 39 human-annotated datasets for instruction tuning. We also construct adversarial samples to enhance the model's robustness. After fine-tuning Flan-T5 on the collected data, we have developed Safety-Flan-T5, a multidimensional and explainable safety detector. We conduct comprehensive experiments on a variety of datasets and tasks, and demonstrate the strong performance of Safety-Flan-T5 in comparison to supervised baselines and served APIs (Perspective API, ChatGPT and In-structGPT). Our Github repository is at https: //github.com/thu-coai/InstructSafety.

show abstract

Recent Advances towards Safe, Responsible, and Moral Dialogue Systems: A Survey

Cited by 6 publications

References 130 publications

Navigating the Web of Disinformation and Misinformation: Large Language Models as Double-Edged Swords

Navigating the Web of Disinformation and Misinformation: Large Language Models as Double-Edged Swords

Large Language Models: A Comprehensive Survey of its Applications, Challenges, Limitations, and Future Prospects

InstructSafety: A Unified Framework for Building Multidimensional and Explainable Safety Detector through Instruction Tuning

Contact Info

Product

Resources

About