By adopting a Human-Computer Interaction (HCI) lens, in this article we present a systematic literature review of 83 papers that focus on how users interact with text-based chatbots. We map the relevant themes that are recurrent in the last ten years of research, describing how people ...
Using AI-based tools to help with writing tasks has become the new norm. However, apart from correcting grammar and style mistakes, many members of academia are apparently using ChatGPT, a chatbot based on a large language model, to lay down their entire scientific findings. Paradoxically, in ...
7. Leveraging large language models in chatbots. Recent progress on large open-domain language models, in particular Open AI GPT-3 but also Facebook Blender and Google Meena, opens new chatbot application areas. We particularly welcome papers addressing chatbot applications using such large language ...
通过以上研究，Anthropic不仅揭示了现有AI系统的脆弱性，更推动从"黑箱"到"白箱"的模型可控性革命，为下一代安全AI的构建提供理论和技术基础。● Claude chat robot launched by ●Anthropic.Background: Claude Chatbot launched by Anthropic is a direct competitor of ChatGPT launched by Microsoft-supported OpenAI...
Building safer chatbots for public health Relying on AI chatbots for health information is uniquely risky. We’re building an AI benchmark to make it safer. → Leveraging generative AI for linguistically diverse classification Meedan is using emerging technology to design new tools that promote effi...
- FULL PAPERS: Empirical studies, theoretical contributions, design research, or presentations of chatbot systems and applications that advance the state-of-the-art (12-16 pages, Springer LNCS format). To be presented at the workshop and published in the Springer LNCS workshop proceedings. ...
We conducted a literature search on databases Scopus and Google Scholar, using keyword combinations including: “ChatGPT AND responsible research and innovation”; “artificial intelligence AND responsible research and innovation”; “chatbot AND responsible research and innovation”; ChatGPT AND responsible...
ChatGPT listed as author on research papers: many scientists disapprove. Nature. Strubell E, Ganesh A, and McCallum A (2019). Energy and policy considerations for deep learning in NLP. arXiv preprint arXiv:1906.02243. Thorp HH (2023) ChatGPT is fun, but not an author. Science 379(6630)...
First-Person Fairness in Chatbots pdf MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering pdf code Rule Based Rewards for Language Model Safety pdf code Prover-Verifier Games improve legibility of LLM outputs pdf A Holistic Approach to Undesired Content Detection in the Real...
Explore the future of AI with over 100 groundbreaking papers, including oral and spotlight sessions, on reinforcement learning, advanced language model training, and multilingual, culturally inclusive benchmarks. 微软研究院博客 Orca-AgentInstruct: Agentic flows can be effective synthetic-data generators ...