Leveraging Large Language Models to Power Chatbots for Collecting User Self-Reported Data

Abstract

Large Language Model How's your day so far? Prefix 📄 Information format 🤖 Persona modifier A Ongoing Dialogue History Insert as prompt Generate chatbot response B Work & Productivity ✅ Work done ✅ Rate productivity ✅ Other concerns at work ✅ What went well a C Going splendid so far. How is yours? I'm doing well, thanks for asking. Let's talk about your work and productivity yesterday. What work did you get done?Figure 1: An overview of our chatbot running on a large language model through zero-shot response generation, with only a prefix A○ consisting of persona modifier and information format and the ongoing dialogue history B ○. The example conversation is carried on about work a ○. GPT-3 was used for an underlying large language model C ○. Refer to the online demo at https://naver-ai.github.io/llm-chatbot.

Evaluating large-language-model chatbots to engage communities in large-scale design projects

“…Several previous applications demonstrated that this model can be meaningfully used for grammar correction, summarizing, answering questions, parsing unstructured data, classification, and translation (Radford et al, 2019;Brown et al, 2020), among other tasks. LLMs have also been used to build chatbots to capture self-reported user data chatting (Wei et al, 2023). However, since the model cannot reason, solve mathematical and ethical questions, or pass the Turing test (Floridi and Chiriatti, 2020), it is regarded as a human-like text generator rather than a general AI in the strict sense.…”

“…A reason that could underlie this finding is that there is evidence suggesting that people are more willing to share information through chatbots (Lee et al, 2020), which are generally believed to be useful for collaboration (Kim et al, 2021). Together with LLMs such as GPT-3, recent research has explored the usability of these models in operating chatbots (Wei et al, 2023). In line with this novel technology, in the present study, we empirically test a chatbot framework that may be more effective than survey methods for eliciting meaningful responses from participants in the context of urban design.…”

“…In conclusion, our proposed framework provides an essential foundation for designing effective human and chatbot prompts, addressing the challenges posed by the unpredictable nature of both. Our chatbot design framework distinguishes itself from Perceived ease of use: The interaction with the software is clear and understandable (g) Perceived ease of use previous studies by extending the prompt design to the human, which is essential for fostering clear communication and effectively framing the conversation (Wei et al, 2023). However, the design of chatbot prompts is still very challenging.…”

Ain't Misbehavin' - Using LLMs to Generate Expressive Robot Behavior in Conversations with the Tabletop Robot Haru

“…Recent advancements in LLMs [25] offer great possibilities for social robotics [20,26,27]. These models excel in conducting natural, human-like dialog, as evident in applications like chatbots and virtual agents [24]. However, unlike virtual agents, social robots possess physical embodiment and distinct personalities.…”

Multilingual Framework for Risk Assessment and Symptom Tracking (MRAST)

“…In fact, with closed-ended questions (which PROMs essentially are), the chatbots collect the same quality, if not higher, compared with digital surveys [ 33 , 82 ]. The solutions conducting interviews with open-ended questions generate more noise (less precise data); however, compared with the closed-ended solutions, their participants showed higher engagement and provided higher-quality responses when engaged with the chatbot [ 83 , 84 , 85 ]. With the recent breakthrough in large language models (LLMs), e.g., OpenAI’s GPT3, Google’s PALM, Gopher, Bing Chat, and Azure Health Bot, etc.…”