Proactive Conversational AI: A Comprehensive Survey of Advancements and Opportunities

Y Deng, L Liao, W Lei, G Yang, W Lam… - ACM Transactions on …, 2025‏ - dl.acm.org
Dialogue systems are designed to offer human users social support or functional services
through natural language interactions. Traditional conversation research has put significant …

Dialogstudio: Towards richest and most diverse unified dataset collection for conversational ai

J Zhang, K Qian, Z Liu, S Heinecke, R Meng… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Despite advancements in conversational AI, language models encounter challenges to
handle diverse conversational tasks, and existing dialogue dataset collections often lack …

Ambrosia: A benchmark for parsing ambiguous questions into database queries

I Saparina, M Lapata - Advances in Neural Information …, 2025‏ - proceedings.neurips.cc
Practical semantic parsers are expected to understand user utterances and map them to
executable programs, even when these are ambiguous. We introduce a new benchmark …

CHIRON: Rich character representations in long-form narratives

A Gurung, M Lapata - arxiv preprint arxiv:2406.10190, 2024‏ - arxiv.org
Characters are integral to long-form narratives, but are poorly understood by existing story
analysis and generation systems. While prior work has simplified characters via graph …

Resolving ambiguities in text-to-image generative models

N Mehrabi, P Goyal, A Verma, J Dhamala… - Proceedings of the …, 2023‏ - aclanthology.org
Natural language often contains ambiguities that can lead to misinterpretation and
miscommunication. While humans can handle ambiguities effectively by asking clarifying …

Is the elephant flying? resolving ambiguities in text-to-image generative models

N Mehrabi, P Goyal, A Verma, J Dhamala… - arxiv preprint arxiv …, 2022‏ - arxiv.org
Natural language often contains ambiguities that can lead to misinterpretation and
miscommunication. While humans can handle ambiguities effectively by asking clarifying …

Using textual interface to align external knowledge for end-to-end task-oriented dialogue systems

Q Wu, D Alnuhait, D Chen, Z Yu - arxiv preprint arxiv:2305.13710, 2023‏ - arxiv.org
Traditional end-to-end task-oriented dialogue systems have been built with a modularized
design. However, such design often causes misalignment between the agent response and …

Intent disambiguation for task-oriented dialogue systems

A Alfieri, R Wolter, SH Hashemi - Proceedings of the 31st ACM …, 2022‏ - dl.acm.org
Task-Oriented Dialogue Systems (TODS) have been widely deployed for domain specific
virtual assistants at contact centres to route customers' calls or deliver information needs of …

[PDF][PDF] Isabel: An inclusive and collaborative task-oriented dialogue system

A Sicilia, Y Asano, K Atwell, Q Cheng… - Alexa Prize …, 2023‏ - assets.amazon.science
In the rapidly evolving landscape of multimodal interactive technologies, a critical gap
persists in their utility and reach across diverse user populations. These technologies, while …

[PDF][PDF] The Measurement of Knowledge in Knowledge Graphs

JX Dou, H Mao, R Bao, PP Liang, X Tan… - Proceedings of the …, 2023‏ - researchgate.net
Abstract Knowledge graphs (KG) have emerged as comprehensive tools to enable
knowledge discovery. Knowledge representation learning learns knowledge graph …