Proactive User Information Acquisition via Chats on User-Favored Topics

• URL: http://arxiv.org/abs/2504.07698v1
• Date: Thu, 10 Apr 2025 12:32:16 GMT
• Title: Proactive User Information Acquisition via Chats on User-Favored Topics
• Authors: Shiki Sato, Jun Baba, Asahi Hentona, Shinji Iwata, Akifumi Yoshimoto, Koichiro Yoshino,
• Abstract summary: This study proposes the PIVOT task, designed to advance the technical foundation for these systems.<n>We found that even recent large language models (LLMs) show a low success rate in the PIVOT task.<n>We developed a simple but effective system for this task by incorporating insights obtained through the analysis of this dataset.
• Score: 3.6698472838681893
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Chat-oriented dialogue systems designed to provide tangible benefits, such as sharing the latest news or preventing frailty in senior citizens, often require Proactive acquisition of specific user Information via chats on user-faVOred Topics (PIVOT). This study proposes the PIVOT task, designed to advance the technical foundation for these systems. In this task, a system needs to acquire the answers of a user to predefined questions without making the user feel abrupt while engaging in a chat on a predefined topic. We found that even recent large language models (LLMs) show a low success rate in the PIVOT task. We constructed a dataset suitable for the analysis to develop more effective systems. Finally, we developed a simple but effective system for this task by incorporating insights obtained through the analysis of this dataset.

Related papers

• Enhancing Discoverability in Enterprise Conversational Systems with Proactive Question Suggestions [5.356008176627551]
  This paper proposes a framework to enhance question suggestions in conversational enterprise AI systems. Our approach combines periodic user intent analysis at the population level with chat session-based question generation. We evaluate the framework using real-world data from the AI Assistant for Adobe Experience Platform.
  arXiv  Detail & Related papers  (2024-12-14T19:04:16Z)
• Unimib Assistant: designing a student-friendly RAG-based chatbot for all their needs [1.0805849839756092]
  This pilot study focuses on specializing ChatGPT behavior through a Retrieval-Augmented Generation (RAG) system using the OpenAI custom GPTs feature. We created a Unimib Assistant to provide information and solutions to the specific needs of University of Milano-Bicocca (Unimib) students. The satisfaction and overall experience of the users was impaired by the system's inability to always provide fully accurate information.
  arXiv  Detail & Related papers  (2024-11-29T09:07:21Z)
• Improving Ontology Requirements Engineering with OntoChat and Participatory Prompting [3.3241053483599563]
  ORE has primarily relied on manual methods, such as interviews and collaborative forums, to gather user requirements from domain experts. Current OntoChat offers a framework for ORE that utilise large language models (LLMs) to streamline the process. This study produces pre-defined prompt templates based on user queries, focusing on creating and refining personas, goals, scenarios, sample data, and data resources for user stories.
  arXiv  Detail & Related papers  (2024-08-09T19:21:14Z)
• Chitchat as Interference: Adding User Backstories to Task-Oriented Dialogues [0.0]
  We use few-shot prompting with Llama-2-70B to enhance the MultiWOZ dataset with user backstories. We test two models: one trained solely on TODs and another trained on TODs with a preliminary chitchat interaction. Our dataset can be effectively used for training purposes, enabling a system to consistently acknowledge the user's backstory.
  arXiv  Detail & Related papers  (2024-02-23T10:27:42Z)
• Learning from Implicit User Feedback, Emotions and Demographic Information in Task-Oriented and Document-Grounded Dialogues [52.95506649193427]
  We introduce FEDI, the first English task-oriented and document-grounded dialogue dataset annotated with this information. Experiments with Flan-T5, GPT-2 and Llama 2 show a particularly positive impact on task completion and factual consistency.
  arXiv  Detail & Related papers  (2024-01-17T14:52:26Z)
• User Simulation for Evaluating Information Access Systems [38.48048183731099]
  evaluating the effectiveness of interactive intelligent systems is a complex scientific challenge. This book provides a thorough understanding of user simulation techniques designed specifically for evaluation. It covers both general frameworks for designing user simulators, and specific models and algorithms for simulating user interactions with search engines, recommender systems, and conversational assistants.
  arXiv  Detail & Related papers  (2023-06-14T14:54:06Z)
• "What do others think?": Task-Oriented Conversational Modeling with Subjective Knowledge [69.46702968979885]
  Task-oriented Dialogue (TOD) Systems aim to build dialogue systems that assist users in accomplishing specific goals. Traditional TODs rely on domain-specific APIs/DBs or external factual knowledge to generate responses. We propose a novel task of subjective-knowledge-based TOD (SK-TOD)
  arXiv  Detail & Related papers  (2023-05-20T04:43:26Z)
• Are Akpans Trick or Treat: Unveiling Helpful Biases in Assistant Systems [55.09907990139756]
  Information-seeking AI assistant systems aim to answer users' queries about knowledge in a timely manner. In this paper, we study computational measurements of helpfulness. Experiments with state-of-the-art dialogue systems reveal that existing systems tend to be more helpful for questions regarding concepts from highly-developed countries.
  arXiv  Detail & Related papers  (2022-05-25T07:58:38Z)
• KETOD: Knowledge-Enriched Task-Oriented Dialogue [77.59814785157877]
  Existing studies in dialogue system research mostly treat task-oriented dialogue and chit-chat as separate domains. We investigate how task-oriented dialogue and knowledge-grounded chit-chat can be effectively integrated into a single model.
  arXiv  Detail & Related papers  (2022-05-11T16:01:03Z)
• Interacting with Non-Cooperative User: A New Paradigm for Proactive Dialogue Policy [83.61404191470126]
  We propose a new solution named I-Pro that can learn Proactive policy in the Interactive setting. Specifically, we learn the trade-off via a learned goal weight, which consists of four factors. The experimental results demonstrate I-Pro significantly outperforms baselines in terms of effectiveness and interpretability.
  arXiv  Detail & Related papers  (2022-04-07T14:11:31Z)
• CAiRE in DialDoc21: Data Augmentation for Information-Seeking Dialogue System [55.43871578056878]
  In DialDoc21 competition, our system achieved 74.95 F1 score and 60.74 Exact Match score in subtask 1, and 37.72 SacreBLEU score in subtask 2.
  arXiv  Detail & Related papers  (2021-06-07T11:40:55Z)
• Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters [52.725200145600624]
  We propose KnowExpert to bypass the retrieval process by injecting prior knowledge into the pre-trained language models with lightweight adapters. Experimental results show that KnowExpert performs comparably with the retrieval-based baselines.
  arXiv  Detail & Related papers  (2021-05-13T12:33:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.