During the workshop, we deeply discussed what CONversational Information ACcess (CONIAC) is and its unique features, proposing a world model abstracting it, and defined the Conversational Agents Framework for Evaluation (CAFE) for the evaluation of CONIAC systems, consisting of six major components: 1) goals of the system's stakeholders, 2) user tasks to be studied in the evaluation, 3) aspects of the users carrying out the tasks, 4) evaluation criteria to be considered, 5) evaluation methodology to be applied, and 6) measures for the quantitative criteria chosen.
Conversational Search (CS) involves retrieving relevant documents from a corpus while considering the conversational context, integrating retrieval with context modeling. Recent advancements in Large Language Models (LLMs) have significantly enhanced CS by enabling query rewriting based on conversational context. However, employing LLMs during inference poses efficiency challenges. Existing solutions mitigate this issue by distilling embeddings derived from human-rewritten queries, focusing primarily on learning the context modeling task. These methods, however, often separate the contrastive retrieval task from the distillation process, treating it as an independent loss term. To overcome these limitations, we introduce DiSCo (Distillation of Sparse Conversational retrieval), a novel approach that unifies retrieval and context modeling through a relaxed distillation objective. Instead of relying exclusively on representation learning, our method distills similarity scores between conversations and documents, providing more freedom in the representation space and better leveraging the contrastive nature of document relevance. Extensive experiments on Learned Sparse Retrieval (LSR) across five CS datasets demonstrate that DiSCo achieves substantial improvements in both in-domain and out-of-domain retrieval tasks, achieving up to a six-point gain in recall for out-of-domain datasets over state-of-the-art methods. Additionally, DiSCo employs a multi-teacher distillation strategy, using multiple LLMs as teachers, further enhancing performance and surpassing the individual teachers in in-domain settings. Furthermore, analysis of model sparsity reveals that DiSCo allows for more effective control over the sparsity of the trained models.
User simulation is a promising approach for automatically training and evaluating conversational information access agents, enabling the generation of synthetic dialogues and facilitating reproducible experiments at scale. However, the objectives of user simulation for the different uses remain loosely defined, hindering the development of effective simulators. In this work, we formally characterize the distinct objectives for user simulators: training aims to maximize behavioral similarity to real users, while evaluation focuses on the accurate prediction of real-world conversational agent performance. Through an empirical study, we demonstrate that optimizing for one objective does not necessarily lead to improved performance on the other. This finding underscores the need for tailored design considerations depending on the intended use of the simulator. By establishing clear objectives and proposing concrete measures to evaluate user simulators against those objectives, we pave the way for the development of simulators that are specifically tailored to their intended use, ultimately leading to more effective conversational agents.
We observe a change in the way users access information, that is, the rise of conversational information access (CIA) agents. However, the automatic evaluation of these agents remains an open challenge. Moreover, the training of CIA agents is cumbersome as it mostly relies on conversational corpora, expert knowledge, and reinforcement learning. User simulation has been identified as a promising solution to tackle automatic evaluation and has been previously used in reinforcement learning. In this research, we investigate how user simulation can be leveraged in the context of CIA. We organize the work in three parts. We begin with the identification of requirements for user simulators for training and evaluating CIA agents and compare existing types of simulator regarding these. Then, we plan to combine these different types of simulators into a new hybrid simulator. Finally, we aim to extend simulators to handle more complex information seeking scenarios.
Conversational information access is an emerging research area. Currently, human evaluation is used for end-to-end system evaluation, which is both very time and resource intensive at scale, and thus becomes a bottleneck of progress. As an alternative, we propose automated evaluation by means of simulating users. Our user simulator aims to generate responses that a real human would give by considering both individual preferences and the general flow of interaction with the system. We evaluate our simulation approach on an item recommendation task by comparing three existing conversational recommender systems. We show that preference modeling and task-specific interaction models both contribute to more realistic simulations, and can help achieve high correlation between automatic evaluation measures and manual human assessments.
Dialog state tracking (DST) is a crucial component in a task-oriented dialog system for conversational information access. A common practice in current dialog systems is to define the dialog state by a set of slot-value pairs. Such representation of dialog states and the slot-filling based DST have been widely employed, but suffer from three drawbacks. (1) The dialog state can contain only a single value for a slot, and (2) can contain only users' affirmative preference over the values for a slot. (3) Current task-based dialog systems mainly focus on the searching task, while the enquiring task is also very common in practice. The above observations motivate us to enrich current representation of dialog states and collect a brand new dialog dataset about movies, based upon which we build a new DST, called enriched DST (EDST), for flexible accessing movie information. The EDST supports the searching task, the enquiring task and their mixed task. We show that the new EDST method not only achieves good results on Iqiyi dataset, but also outperforms other state-of-the-art DST methods on the traditional dialog datasets, WOZ2.0 and DSTC2.