English
Related papers

Related papers: ATOD: An Evaluation Framework and Benchmark for Ag…

200 papers

Intent detection is a key part of any Natural Language Understanding (NLU) system of a conversational assistant. Detecting the correct intent is essential yet difficult for email conversations where multiple directives and intents are…

Computation and Language · Computer Science 2022-08-22 Soham Deshmukh , Charles Lee

Task-Oriented Dialogue (TOD) systems assist users in completing tasks through natural language interactions, often relying on a single-layered workflow structure for slot-filling in public tasks, such as hotel bookings. However, in…

Computation and Language · Computer Science 2025-09-09 Lingbo Mo , Shun Jiang , Akash Maharaj , Bernard Hishamunda , Yunyao Li

Agent applications are increasingly adopted to automate workflows across diverse tasks. However, due to the heterogeneous domains they operate in, it is challenging to create a scalable evaluation framework. Prior works each employ their…

Artificial Intelligence · Computer Science 2026-03-17 Penny Chong , Harshavardhan Abichandani , Jiyuan Shen , Atin Ghosh , Min Pyae Moe , Yifan Mai , Daniel Dahlmeier

Achieving robust language technologies that can perform well across the world's many languages is a central goal of multilingual NLP. In this work, we take stock of and empirically analyse task performance disparities that exist between…

Computation and Language · Computer Science 2023-10-20 Songbo Hu , Han Zhou , Moy Yuan , Milan Gritta , Guchun Zhang , Ignacio Iacobacci , Anna Korhonen , Ivan Vulić

Recent research in dialogue systems and corpora has focused on two main categories: task-oriented (TOD) and open-domain (chit-chat) dialogues. TOD systems help users accomplish specific tasks, while open-domain systems aim to create…

Computation and Language · Computer Science 2024-04-30 Wen-Yu Chang , Yun-Nung Chen

Large Language Models (LLMs) have showcased remarkable capabilities in various Natural Language Processing tasks. For automatic open-domain dialogue evaluation in particular, LLMs have been seamlessly integrated into evaluation frameworks,…

Computation and Language · Computer Science 2024-07-08 John Mendonça , Alon Lavie , Isabel Trancoso

Despite recent advances in understanding and leveraging long-range conversational memory, existing benchmarks still lack systematic evaluation of large language models(LLMs) across diverse memory dimensions, particularly in multi-session…

Computation and Language · Computer Science 2026-01-08 Ye Shen , Dun Pei , Yiqiu Guo , Junying Wang , Yijin Guo , Zicheng Zhang , Qi Jia , Jun Zhou , Guangtao Zhai

The recent development of language models has shown promising results by achieving state-of-the-art performance on various natural language tasks by fine-tuning pretrained models. In task-oriented dialogue (ToD) systems, language models can…

Computation and Language · Computer Science 2022-01-24 Vinsen Marselino Andreas , Genta Indra Winata , Ayu Purwarianti

The rapid evolution of large language models (LLMs) has transformed conversational agents, enabling complex human-machine interactions. However, evaluation frameworks often focus on single tasks, failing to capture the dynamic nature of…

Computation and Language · Computer Science 2025-02-10 Pietro Alessandro Aluffi , Patrick Zietkiewicz , Marya Bazzi , Matt Arderne , Vladimirs Murevics

The goal of building intelligent dialogue systems has largely been separately pursued under two paradigms: task-oriented dialogue (TOD) systems, which perform goal-oriented functions, and open-domain dialogue (ODD) systems, which focus on…

Computation and Language · Computer Science 2022-04-06 Tom Young , Frank Xing , Vlad Pandelea , Jinjie Ni , Erik Cambria

Task-oriented dialog (TOD) systems facilitate users in accomplishing complex, multi-turn tasks through natural language. While instruction-tuned large language models (LLMs) have demonstrated strong performance on a range of single-turn NLP…

Computation and Language · Computer Science 2025-12-29 Moghis Fereidouni , Md Sajid Ahmed , Adib Mosharrof , A. B. Siddique

Previous dialogue summarization datasets mainly focus on open-domain chitchat dialogues, while summarization datasets for the broadly used task-oriented dialogue haven't been explored yet. Automatically summarizing such task-oriented…

Computation and Language · Computer Science 2021-10-26 Lulu Zhao , Fujia Zheng , Keqing He , Weihao Zeng , Yuejie Lei , Huixing Jiang , Wei Wu , Weiran Xu , Jun Guo , Fanyu Meng

Many efforts have been made to construct dialog systems for different types of conversations, such as task-oriented dialog (TOD) and open-domain dialog (ODD). To better mimic human-level conversations that usually fuse various dialog modes,…

Computation and Language · Computer Science 2023-08-01 Miaoran Li , Baolin Peng , Michel Galley , Jianfeng Gao , Zhu Zhang

Recent end-to-end spoken dialogue models enable natural interaction. However, as user demands become increasingly complex, models that rely solely on conversational abilities often struggle to cope. Incorporating agentic capabilities is…

Sound · Computer Science 2026-04-20 Tianle Liang , Yifu Chen , Shengpeng Ji , Yijun Chen , Zhiyang Jia , Jingyu Lu , Fan Zhuo , Xueyi Pu , Yangzhuo Li , Zhou Zhao

Large Language Models (LLMs) have shown strong potential as conversational agents. Yet, their effectiveness remains limited by deficiencies in robust long-term memory, particularly in complex, long-term web-based services such as online…

Computation and Language · Computer Science 2026-02-03 Tiantian Chen , Jiaqi Lu , Ying Shen , Lin Zhang

Evaluating Large Language Models (LLMs) as general-purpose agents is essential for understanding their capabilities and facilitating their integration into practical applications. However, the evaluation process presents substantial…

Computation and Language · Computer Science 2024-12-25 Chang Ma , Junlei Zhang , Zhihao Zhu , Cheng Yang , Yujiu Yang , Yaohui Jin , Zhenzhong Lan , Lingpeng Kong , Junxian He

Large language models (LLMs) are widely used as general-purpose knowledge sources, but they rely on parametric knowledge, limiting explainability and trustworthiness. In task-oriented dialogue (TOD) systems, this separation is explicit,…

Computation and Language · Computer Science 2025-12-22 Renato Vukovic , Carel van Niekerk , Michael Heck , Benjamin Ruppik , Hsien-Chin Lin , Shutong Feng , Nurul Lubis , Milica Gasic

Multilingual task-oriented dialogue (ToD) facilitates access to services and information for many (communities of) speakers. Nevertheless, the potential of this technology is not fully realised, as current datasets for multilingual ToD -…

Computation and Language · Computer Science 2023-05-24 Olga Majewska , Evgeniia Razumovskaia , Edoardo Maria Ponti , Ivan Vulić , Anna Korhonen

Task-oriented conversational systems are essential for efficiently addressing diverse user needs, yet their development requires substantial amounts of high-quality conversational data that is challenging and costly to obtain. While large…

Information Retrieval · Computer Science 2025-11-06 Zhefan Wang , Ning Geng , Zhiqiang Guo , Weizhi Ma , Min Zhang

Programmable task-oriented dialogue (TOD) agents enable language models to follow structured dialogue policies, but their effectiveness hinges on accurate state tracking. We present PyTOD, an agent that generates executable code to track…