Directed Diversity: Leveraging Language Embedding Distances for Collective Creativity in Crowd Ideation

Cox, Samuel Rhys; Wang, Yunlong; Abdul, Ashraf; Weth, Christian von der; Lim, Brian Y.

doi:10.1145/3411764.3445782

Cited by 13 publications

(5 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To rigorously evaluate dialogue diversity, we developed two specialized metrics: intra-remote-clique (intra-RC) and inter-remote-clique (inter-RC). These metrics are adaptations of the remote-clique (RC) metric [71], which is commonly used to measure text embedding diversity. The RC metric is defined as the average pairwise distance between text embeddings [26,44].…”

Section: Diversity Of Dialoguesmentioning

confidence: 99%

CloChat: Understanding How People Customize, Interact, and Experience Personas in Large Language Models

Ha,

Jeon,

Han

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Large language models (LLMs) have facilitated significant strides in generating conversational agents, enabling seamless, contextually relevant dialogues across diverse topics. However, the existing LLM-driven conversational agents have fixed personalities and functionalities, limiting their adaptability to individual user needs. Creating personalized agent personas with distinct expertise or traits can address this issue. Nonetheless, we lack knowledge of how people customize and interact with agent personas. In this

show abstract

Section: Diversity Of Dialoguesmentioning

confidence: 99%

CloChat: Understanding How People Customize, Interact, and Experience Personas in Large Language Models

Ha,

Jeon,

Han

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…One can also consider this metric as a proxy of the "uniqueness" of the writing-a lower level of diversity across multiple writings on the same topic usually implies that each writing in the group is less unique. For our study, given a set of articles submitted by participants on the same topic (i.e., argumentative essays for the same statement or creative stories for the same prompt) using the same writing mode, we used remote clique score and Chamfer distance score to quantify the diversity of these articles following the prior literature [38]. Specifically, the remote clique score is computed as the average mean distance of an article to other articles in the set, while the Chamfer distance score is defined as the average minimum distance of an article to other articles in the set.…”

Section: Content Diversitymentioning

confidence: 99%

The Value, Benefits, and Concerns of Generative AI-Powered Assistance in Writing

Li,

Liang,

Peng

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Recent advances in generative AI technologies like large language models raise both excitement and concerns about the future of human-AI co-creation in writing. To unpack people's attitude towards and experience with generative AI-powered writing assistants, in this paper, we conduct an experiment to understand whether and how much value people attach to AI assistance, and how the incorporation of AI assistance in writing workflows changes people's writing perceptions and performance. Our results suggest that people are willing to forgo financial payments to receive writing assistance from AI, especially if AI can provide direct content generation assistance and the writing task is highly creative. Generative AI-powered assistance is found to offer benefits in increasing people's productivity and confidence in writing. However, direct content generation assistance offered by AI also comes with risks, including decreasing people's sense of accountability and diversity in writing. We conclude by discussing the implications of our findings. CCS CONCEPTS• Human-centered computing → Empirical studies in HCI; • Computing methodologies → Artificial intelligence.

show abstract

“…prompt incorporating physical and human interactions with general background knowledge and using benchmark datasets such as Common-senseQA. [5, 206, 207, 209, 268, 270, 284-286, 293-296, 301, 304-306, 312-314] Creativity -supports ideation and creation process like automated diverse prompting ideas [315][316][317][318]. Logical -improves logical reasoning -e.g.…”

Section: Asking My Question (Prompting)mentioning

confidence: 99%

Complex QA and language models hybrid architectures, Survey

Daull¹,

Bellot²,

Bruno³

et al. 2023

Preprint

View full text Add to dashboard Cite

This paper provides a survey of the state of the art of hybrid language models architectures and strategies for "complex" question-answering (QA, CQA, CPS). Very large language models are good at leveraging public data on standard problems but once you want to tackle more specific complex questions or problems you may need specific architecture, knowledge, skills, tasks, methods, sensitive data, performance, human approval and versatile feedback... This survey extends findings from the robust community edited research papers BIG, BLOOM and HELM which open source, benchmark and analyze limits and challenges of large language models in terms of tasks complexity and strict evaluation on accuracy (e.g. fairness, robustness, toxicity, ...). It identifies the key elements used with Large Language Models (LLM) to solve complex questions or problems. Recent projects like ChatGPT and GALACTICA have allowed non-specialists to grasp the great potential as well as the equally strong limitations of language models in complex QA. Hybridizing these models with different components could allow to overcome these different limits and go much further. We discuss some challenges associated with complex QA, including domain adaptation, decomposition and efficient multi-step QA, long form QA, non-factoid QA, safety and multi-sensitivity data protection, multimodal search, hallucinations, QA explainability and truthfulness, time dimension. Therefore we review current solutions and promising strategies, using elements such as hybrid LLM architectures, human-in-the-loop reinforcement learning, prompting adaptation, neuro-symbolic and structured knowledge grounding, program synthesis, and others. We analyze existing solutions and provide an overview of the current research and trends in the area of complex QA.

show abstract

Directed Diversity: Leveraging Language Embedding Distances for Collective Creativity in Crowd Ideation

Cited by 13 publications

References 84 publications

CloChat: Understanding How People Customize, Interact, and Experience Personas in Large Language Models

CloChat: Understanding How People Customize, Interact, and Experience Personas in Large Language Models

The Value, Benefits, and Concerns of Generative AI-Powered Assistance in Writing

Complex QA and language models hybrid architectures, Survey

Contact Info

Product

Resources

About