Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Navigating the Unknown: A Chat-Based Collaborative Interface for Personalized Exploratory Tasks (2410.24032v1)

Published 31 Oct 2024 in cs.HC, cs.AI, and cs.CL

Abstract: The rise of LLMs has revolutionized user interactions with knowledge-based systems, enabling chatbots to synthesize vast amounts of information and assist with complex, exploratory tasks. However, LLM-based chatbots often struggle to provide personalized support, particularly when users start with vague queries or lack sufficient contextual information. This paper introduces the Collaborative Assistant for Personalized Exploration (CARE), a system designed to enhance personalization in exploratory tasks by combining a multi-agent LLM framework with a structured user interface. CARE's interface consists of a Chat Panel, Solution Panel, and Needs Panel, enabling iterative query refinement and dynamic solution generation. The multi-agent framework collaborates to identify both explicit and implicit user needs, delivering tailored, actionable solutions. In a within-subject user study with 22 participants, CARE was consistently preferred over a baseline LLM chatbot, with users praising its ability to reduce cognitive load, inspire creativity, and provide more tailored solutions. Our findings highlight CARE's potential to transform LLM-based systems from passive information retrievers to proactive partners in personalized problem-solving and exploration.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (50)
  1. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023).
  2. Knowledge-Augmented Large Language Models for Personalized Contextual Query Suggestion. In Proceedings of the ACM Web Conference 2024 (Singapore, Singapore) (WWW ’24). Association for Computing Machinery, New York, NY, USA, 3355–3366. https://doi.org/10.1145/3589334.3645404
  3. The HCI Aspects of Public Deployment of Research Chatbots: A User Study, Design Recommendations, and Open Challenges. arXiv preprint arXiv:2306.04765 (2023).
  4. Bing. 2024. Bing. https://www.bing.com/. Accessed: 2024-10-10.
  5. Ali Borji. 2023. A Categorical Archive of ChatGPT Failures. arXiv preprint arXiv:2302.03494 (2023).
  6. Language models are few-shot learners. In Proceedings of the 34th International Conference on Neural Information Processing Systems (Vancouver, BC, Canada) (NIPS ’20). Curran Associates Inc., Red Hook, NY, USA, Article 159, 25 pages.
  7. Edward Y. Chang. 2023. Prompting Large Language Models With the Socratic Method. In 2023 IEEE 13th Annual Computing and Communication Workshop and Conference (CCWC). 0351–0360. https://doi.org/10.1109/CCWC57344.2023.10099179
  8. A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects. In Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI-23, Edith Elkind (Ed.). International Joint Conferences on Artificial Intelligence Organization, 6583–6591. https://doi.org/10.24963/ijcai.2023/738 Survey Track.
  9. Boosting Large Language Models with Socratic Method for Conversational Mathematics Teaching. arXiv preprint arXiv:2407.17349 (2024).
  10. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024).
  11. Luciano Floridi. 2023. AI as Agency Without Intelligence: on ChatGPT, Large Language Models, and Other Generative Models. Philos. Technol. 36 (2023), 15. https://doi.org/10.1007/s13347-023-00621-y
  12. Sparks: Inspiration for Science Writing using Language Models. In Proceedings of the 2022 ACM Designing Interactive Systems Conference (Virtual Event, Australia) (DIS ’22). Association for Computing Machinery, New York, NY, USA, 1002–1019. https://doi.org/10.1145/3532106.3533533
  13. Sukhpal Singh Gill and Rupinder Kaur. 2023. ChatGPT: Vision and challenges. Internet of Things and Cyber-Physical Systems 3 (2023), 262–271. https://doi.org/10.1016/j.iotcps.2023.05.004
  14. Charles Goodwin. 2015. Professional Vision. Springer Fachmedien Wiesbaden, Wiesbaden, 387–425. https://doi.org/10.1007/978-3-531-19381-6_20
  15. Google. 2023. Google Gemini. https://gemini.google.com. Accessed: 2024-10-10.
  16. Google. 2024. Google. https://www.google.com/. Accessed: 2024-10-10.
  17. Myeongjun Jang and Thomas Lukasiewicz. 2023. Consistency Analysis of ChatGPT. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Houda Bouamor, Juan Pino, and Kalika Bali (Eds.). Association for Computational Linguistics, Singapore, 15970–15985. https://doi.org/10.18653/v1/2023.emnlp-main.991
  18. PromptMaker: Prompt-based Prototyping with Large Language Models. In Extended Abstracts of the 2022 CHI Conference on Human Factors in Computing Systems (New Orleans, LA, USA) (CHI EA ’22). Association for Computing Machinery, New York, NY, USA, Article 35, 8 pages. https://doi.org/10.1145/3491101.3503564
  19. Graphologue: Exploring Large Language Model Responses with Interactive Diagrams. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology (San Francisco, CA, USA) (UIST ’23). Association for Computing Machinery, New York, NY, USA, Article 3, 20 pages. https://doi.org/10.1145/3586183.3606737
  20. Challenges and Applications of Large Language Models. arXiv preprint arXiv:2307.10169 (2023).
  21. Why and When LLM-Based Assistants Can Go Wrong: Investigating the Effectiveness of Prompt-Based Interactions for Software Help-Seeking. In Proceedings of the 29th International Conference on Intelligent User Interfaces (Greenville, SC, USA) (IUI ’24). Association for Computing Machinery, New York, NY, USA, 288–303. https://doi.org/10.1145/3640543.3645200
  22. Using LLMs to Investigate Correlations of Conversational Follow-up Queries with User Satisfaction. arXiv preprint arXiv:2407.13166 (2024).
  23. DataDive: Supporting Readers’ Contextualization of Statistical Statements with Data Exploration. In Proceedings of the 29th International Conference on Intelligent User Interfaces (Greenville, SC, USA) (IUI ’24). Association for Computing Machinery, New York, NY, USA, 623–639. https://doi.org/10.1145/3640543.3645155
  24. Understanding Users’ Dissatisfaction with ChatGPT Responses: Types, Resolving Tactics, and the Effect of Knowledge Level. In Proceedings of the 29th International Conference on Intelligent User Interfaces (Greenville, SC, USA) (IUI ’24). Association for Computing Machinery, New York, NY, USA, 385–404. https://doi.org/10.1145/3640543.3645148
  25. Guy Laban and Theo Araujo. 2020. The Effect of Personalization Techniques in Users’ Perceptions of Conversational Recommender Systems. In Proceedings of the 20th ACM International Conference on Intelligent Virtual Agents (Virtual Event, Scotland, UK) (IVA ’20). Association for Computing Machinery, New York, NY, USA, Article 34, 3 pages. https://doi.org/10.1145/3383652.3423890
  26. ChatGPT as Research Scientist: Probing GPT’s capabilities as a Research Librarian, Research Ethicist, Data Generator, and Data Predictor. Proceedings of the National Academy of Sciences 121, 35 (2024), e2404328121. https://doi.org/10.1073/pnas.2404328121 arXiv:https://www.pnas.org/doi/pdf/10.1073/pnas.2404328121
  27. Learning to Rewrite Prompts for Personalized Text Generation. In Proceedings of the ACM Web Conference 2024 (Singapore, Singapore) (WWW ’24). Association for Computing Machinery, New York, NY, USA, 3367–3378. https://doi.org/10.1145/3589334.3645408
  28. Beyond ChatBots: ExploreLLM for Structured Thoughts and Personalized Model Responses. In Extended Abstracts of the 2024 CHI Conference on Human Factors in Computing Systems (CHI EA ’24). Association for Computing Machinery, New York, NY, USA, Article 56, 12 pages. https://doi.org/10.1145/3613905.3651093
  29. Microsoft. 2023. Microsoft Copilot. https://copilot.microsoft.com. Accessed: 2024-10-10.
  30. Personalizing an AR-based Communication System for Nonspeaking Autistic Users. In Proceedings of the 29th International Conference on Intelligent User Interfaces (Greenville, SC, USA) (IUI ’24). Association for Computing Machinery, New York, NY, USA, 731–741. https://doi.org/10.1145/3640543.3645153
  31. OpenAI. 2023. OpenAI ChatGPT. https://chatgpt.com/. Accessed: 2024-10-10.
  32. Training language models to follow instructions with human feedback. Advances in neural information processing systems 35 (2022), 27730–27744.
  33. PromptInfuser: How Tightly Coupling AI and UI Design Impacts Designers’ Workflows. In Proceedings of the 2024 ACM Designing Interactive Systems Conference (Copenhagen, Denmark) (DIS ’24). Association for Computing Machinery, New York, NY, USA, 743–756. https://doi.org/10.1145/3643834.3661613
  34. Conversation space: visualising multi-threaded conversation. In Proceedings of the Working Conference on Advanced Visual Interfaces (Palermo, Italy) (AVI ’00). Association for Computing Machinery, New York, NY, USA, 246–249. https://doi.org/10.1145/345513.345330
  35. Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Lun-Wei Ku, Andre Martins, and Vivek Srikumar (Eds.). Association for Computational Linguistics, Bangkok, Thailand, 1088–1113. https://doi.org/10.18653/v1/2024.acl-long.61
  36. Crystal Qian and James Wexler. 2024. Take It, Leave It, or Fix It: Measuring Productivity and Trust in Human-AI Collaboration. In Proceedings of the 29th International Conference on Intelligent User Interfaces (Greenville, SC, USA) (IUI ’24). Association for Computing Machinery, New York, NY, USA, 370–384. https://doi.org/10.1145/3640543.3645198
  37. Partha Pratim Ray. 2023. ChatGPT: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope. Internet of Things and Cyber-Physical Systems 3 (2023), 121–154. https://doi.org/10.1016/j.iotcps.2023.04.003
  38. Leveraging ChatGPT for Automated Human-centered Explanations in Recommender Systems. In Proceedings of the 29th International Conference on Intelligent User Interfaces (Greenville, SC, USA) (IUI ’24). Association for Computing Machinery, New York, NY, USA, 597–608. https://doi.org/10.1145/3640543.3645171
  39. Streamlit. 2024. Streamlit: A faster way to build and share data apps. https://streamlit.io/. Accessed: 2024-10-10.
  40. Sensecape: Enabling Multilevel Exploration and Sensemaking with Large Language Models. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology (San Francisco, CA, USA) (UIST ’23). Association for Computing Machinery, New York, NY, USA, Article 1, 18 pages. https://doi.org/10.1145/3586183.3606756
  41. PDFChatAnnotator: A Human-LLM Collaborative Multi-Modal Data Annotation Tool for PDF-Format Catalogs. In Proceedings of the 29th International Conference on Intelligent User Interfaces (Greenville, SC, USA) (IUI ’24). Association for Computing Machinery, New York, NY, USA, 419–430. https://doi.org/10.1145/3640543.3645174
  42. The effect of personalizing a psychotherapy conversational agent on therapeutic bond and usage intentions. In Proceedings of the 29th International Conference on Intelligent User Interfaces (Greenville, SC, USA) (IUI ’24). Association for Computing Machinery, New York, NY, USA, 761–771. https://doi.org/10.1145/3640543.3645195
  43. LAVE: LLM-Powered Agent Assistance and Language Augmentation for Video Editing. In Proceedings of the 29th International Conference on Intelligent User Interfaces (Greenville, SC, USA) (IUI ’24). Association for Computing Machinery, New York, NY, USA, 699–714. https://doi.org/10.1145/3640543.3645143
  44. A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT. arXiv preprint arXiv:2302.11382 (2023).
  45. Autogen: Enabling next-gen llm applications via multi-agent conversation framework. arXiv preprint arXiv:2308.08155 (2023).
  46. AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts. In Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems (New Orleans, LA, USA) (CHI ’22). Association for Computing Machinery, New York, NY, USA, Article 385, 22 pages. https://doi.org/10.1145/3491102.3517582
  47. Jamplate: Exploring LLM-Enhanced Templates for Idea Reflection. In Proceedings of the 29th International Conference on Intelligent User Interfaces (Greenville, SC, USA) (IUI ’24). Association for Computing Machinery, New York, NY, USA, 907–921. https://doi.org/10.1145/3640543.3645196
  48. Herding AI Cats: Lessons from Designing a Chatbot by Prompting GPT-3. In Proceedings of the 2023 ACM Designing Interactive Systems Conference (Pittsburgh, PA, USA) (DIS ’23). Association for Computing Machinery, New York, NY, USA, 2206–2220. https://doi.org/10.1145/3563657.3596138
  49. Why Johnny Can’t Prompt: How Non-AI Experts Try (and Fail) to Design LLM Prompts. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (Hamburg, Germany) (CHI ’23). Association for Computing Machinery, New York, NY, USA, Article 437, 21 pages. https://doi.org/10.1145/3544548.3581388
  50. Ask-before-Plan: Proactive Language Agents for Real-World Planning. arXiv preprint arXiv:2406.12639 (2024).
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (9)
  1. Yingzhe Peng (7 papers)
  2. Xiaoting Qin (14 papers)
  3. Zhiyang Zhang (9 papers)
  4. Jue Zhang (43 papers)
  5. Qingwei Lin (81 papers)
  6. Xu Yang (222 papers)
  7. Dongmei Zhang (193 papers)
  8. Saravan Rajmohan (85 papers)
  9. Qi Zhang (785 papers)

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now