https://www.kuki.ai/home daily 1.0 2025-11-16 https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/faf6c787-e423-4771-92da-9649c8da3962/02_Horizontal.webp https://www.kuki.ai/policies daily 0.75 2022-11-15 https://www.kuki.ai/research daily 0.75 2021-09-07 https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/1610423073405-AP7PH37HTUW3MR1DW06X/association_for_computing_machinery.png Research - Conceptual Metaphors Impact Perceptions of Human-AI Collaboration Authors - Pranav Khadpe, Ranjay Krishna, Li Fei-Fei, Jeffrey Hancock, Michael Bernstein Abstract - With the emergence of conversational artificial intelligence (AI) agents, it is important to understand the mechanisms that influence users' experiences of these agents. We study a common tool in the designer's toolkit: conceptual metaphors. Metaphors can present an agent as akin to a wry teenager, a toddler, or an experienced butler. How might a choice of metaphor influence our experience of the AI agent? Sampling metaphors along the dimensions of warmth and competence---defined by psychological theories as the primary axes of variation for human social perception---we perform a study (N=260) where we manipulate the metaphor, but not the behavior, of a Wizard-of-Oz conversational agent. Following the experience, participants are surveyed about their intention to use the agent, their desire to cooperate with the agent, and the agent's usability. Contrary to the current tendency of designers to use high competence metaphors to describe AI products, we find that metaphors that signal low competence lead to better evaluations of the agent than metaphors that signal high competence. This effect persists despite both high and low competence agents featuring human-level performance and the wizards being blind to condition. A second study confirms that intention to adopt decreases rapidly as competence projected by the metaphor increases. In a third study, we assess effects of metaphor choices on potential users' desire to try out the system and find that users are drawn to systems that project higher competence and warmth. These results suggest that projecting competence may help attract new users, but those users may discard the agent unless it can quickly correct with a lower competence metaphor. We close with a retrospective analysis that finds similar patterns between metaphors and user attitudes towards past conversational agents such as Xiaoice, Replika, Woebot, Mitsuku, and Tay. https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/1631042180398-AHUW9JDAZJZ06OUT3YJJ/arxive-org.png Research - Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling Authors - Emily Dinan, Gavin Abercrombie, A. Stevie Bergman, Shannon Spruit, Dirk Hovy, Y-Lan Boureau, Verena Rieser Abstract - Over the last several years, end-to-end neural conversational agents have vastly improved in their ability to carry a chit-chat conversation with humans. However, these models are often trained on large datasets from the internet, and as a result, may learn undesirable behaviors from this data, such as toxic or otherwise harmful language. Researchers must thus wrestle with the issue of how and when to release these models. In this paper, we survey the problem landscape for safety for end-to-end conversational AI and discuss recent and related work. We highlight tensions between values, potential positive impact and potential harms, and provide a framework for making decisions about whether and how to release these models, following the tenets of value-sensitive design. We additionally provide a suite of tools to enable researchers to make better-informed decisions about training and releasing end-to-end conversational AI models. https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/1610418237519-VNITA798RM1OTM0O02XE/Google_AI.png Research - Towards a Human-like Open-Domain Chatbot Authors - Daniel Adiwardana, Minh-Thang Luong, David R. So, Jamie Hall, Noah Fiedel, Romal Thoppilan, Zi Yang, Apoorv Kulshreshtha, Gaurav Nemade, Yifeng Lu, Quoc V. Le Abstract - We present Meena, a multi-turn open-domain chatbot trained end-to-end on data mined and filtered from public domain social media conversations. This 2.6B parameter neural network is simply trained to minimize perplexity of the next token. We also propose a human evaluation metric called Sensibleness and Specificity Average (SSA), which captures key elements of a human-like multi-turn conversation. Our experiments show strong correlation between perplexity and SSA. The fact that the best perplexity end-to-end trained Meena scores high on SSA (72% on multi-turn evaluation) suggests that a human-level SSA of 86% is potentially within reach if we can better optimize perplexity. Additionally, the full version of Meena (with a filtering mechanism and tuned decoding) scores 79% SSA, 23% higher in absolute SSA than the existing chatbots we evaluated. https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/1610419065280-4N9KM5T8HDFKC8968K6A/tsu.png Research - Evaluating the Knowledge of Conversational Agents Authors - Mina Park, Milam Aiken, Mahesh Vanjani Abstract - Several studies have tested chatbots for their abilities to emulate human conversation, but few have evaluated the systems’ general knowledge. In this study, we asked two chatbots (Mitsuku and Tutor) and a digital assistant (Cortana) several questions and compared their answers to 67 humans’ answers. Results showed that while Tutor and Cortana performed poorly, the accuracies of Mitsuku and the humans were not significantly different. As expected, the chatbots and Cortana answered factual questions more accurately than abstract questions. https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/1610419800321-ZMQXEVWNKXV2UCBAQFR4/iojet.png Research - English as a Foreign Language Learner Interactions with Chatbots: Negotiation for Meaning Authors - Yin, Qinghua; Satar, Müge Abstract - Chatbots, whose potential for language learning have caused controversy among Second Language Acquisition (SLA) researchers (Atwell, 1999; Fryer & Carpenter, 2006; Fryer & Nakao, 2009; Parker, 2005, Coniam, 2014; Jia, 2004; Chantarotwong, 2005) are intelligent conversational systems stimulating human interlocutors with voice or text. In this paper, two different types of chatbots (pedagogical chatbot Tutor Mike and conversational chatbot Mitsuku) were selected to investigate their potential for foreign language learning by exploring the frequency and patterns of Negotiation for Meaning (NfM) in CMC interactions. 8 Chinese EFL learners were randomly divided into two groups (lower and higher-level learners), and all learners interacted with both the pedagogical and conversational chatbot in a switching replications research design. Data were analysed through content analysis to identify the number of NfM instances observed, the different stages of NfM, trigger types, modified output and learners' perceptions. The findings of this study indicate that while learners with low language levels would benefit most from interactions with pedagogical agents, high language level learners expressed dissatisfaction with chatbots and a low level of engagement was observed in their interactions with the pedagogical chatbot. https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/1610418752542-73HJCEW358RVVVBLKNL4/icicci.png Research - Comparative Analysis of Chatbots Authors - Shivang Verma, Lakshay Sahni, Moolchand Sharma Abstract - A chatbot is computer software that employs Natural Language Processing and Pattern Recognition techniques to provide appropriate answers to questions posed by humans. In this paper, we are analyzing and comparing the total accuracy score of the following chatbots: Rose, Google Assistant, Siri, Machine Comprehension Chatbot, Mitsuku, Jabberwacky, ALICE and Eliza based on the answers provided by them to a set of predefined questions. The chatbots were broadly analyzed on three focal parameters: 1. Assessment of Factual Questions, 2. Assessment of Conversational Attributes, and 3. Evaluation of Exceptional queries. The paper produces conclusive comparisons and conclusions and then ranks these chatbots according to their performance in the above-mentioned focal points. These focal points help in assessing the chatbots according to their responses by assigning a rank to each chatbot concerning others. The final level is evaluated by averaging grades attained in the three parameters above. https://www.kuki.ai/partnership-request daily 0.75 2021-10-06 https://www.kuki.ai/collaboration-request daily 0.75 2021-12-15 https://www.kuki.ai/account-deleted daily 0.75 2021-07-06 https://www.kuki.ai/research-request daily 0.75 2021-07-21 https://www.kuki.ai/iconiq-ethics daily 0.75 2021-10-06 https://www.kuki.ai/policies-september-24-archive daily 0.75 2021-10-05 https://www.kuki.ai/faqs daily 0.75 2021-11-17 https://www.kuki.ai/about daily 0.75 2025-11-16 https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/cdb7deaf-01d4-4bcb-b6c9-80eddb3031f0/Kuki+Vogue.png https://www.kuki.ai/dev-feedback daily 0.75 2022-09-07 https://www.kuki.ai/api-feedback daily 0.75 2022-10-13 https://www.kuki.ai/voice-chat-feedback daily 0.75 2022-10-14 https://www.kuki.ai/press daily 0.75 2022-11-18 https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/117aa1c1-818d-4d80-804e-2afd839fc0fe/5Marco+1+%281%29.png https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/8147e70f-c062-4f3a-a90c-218d46cad66d/Federico+Cina+1.png https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/1503c3a4-501f-41e2-a3a8-49dc5238e2a3/4Cormio.1+%281%29.jpg https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/548f1dbe-b9e7-4885-a25d-d3fa27fa3b8a/1Vivetta.1+%282%29.jpg https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/4527f77b-906a-44ad-a2f6-44f650007dde/NYT-Headers-F-NYTMagazine%402x.jpg Press https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/a46f63e0-4e11-4677-bffe-cf50a12035ad/CNN-Logo-1980.jpg Press https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/eb87d7de-e167-4ee4-9f63-d988b7068028/vice-logo.jpg Press https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/8ce9b0c5-2f55-4f93-a587-b9e8eab36527/Wired_logo.svg.png Press https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/1dd9ffe2-40cb-4dc6-88e7-1337da92bd59/NYLON_Logo.jpg Press https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/1609958813681-QNBLVH9QVXCN24GZCKKZ/wall_street_journal.png Press https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/1610127722284-UDXY09HV8FFA83XD06Q6/the_guardian.jpeg Press https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/3883c9ce-f3a7-4f7b-81d0-bcbc2f34d999/WNYC_Radiolab_logo.svg.jpg Press https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/d7c9c757-dd3f-4538-a6f7-c338733b2e55/BBC-Logo-1.png Press https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/bee6eb2d-749f-4b37-98be-626470112b59/Variety_%28magazine%29-Logo.wine.jpg Press https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/92a906f4-813e-4e61-b082-7833fa2fd3e1/MHC_LightingPreset_RedLantern_RT.0000_%287%29+%281%29.png Press Kuki in Balenciaga https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/e8651e54-0ddd-4119-8f2d-d1a97ddb3073/Kukix5_.0000_%283%29+%281%29.png Press Kuki for Vogue Talents https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/55605d7f-0ae8-419a-a976-0839c2082709/Kuki_BlackRoom_v001.0000+%282%29.png Press Kuki in Balenciaga https://images.squarespace-cdn.com/content/v1/5fd110ee514f2770efc95c70/6ecf4d1a-4463-478f-a19c-e5e0d3347410/KukixRm+%282%29.png Press Kuki in NFT Wearables