Related papers: RADE: Reference-Assisted Dialogue Evaluation for O…

Task-based dialogue systems assist users in achieving specific goals, such as executing actions or retrieving information, through natural language interactions. Accurate coreference resolution is essential, as it involves identifying…

As Large Language Models (LLMs) become increasingly integrated into real-world, autonomous applications, relying on static, pre-annotated references for evaluation poses significant challenges in cost, scalability, and completeness. We…

Task-oriented dialogue systems in industry settings need to have high conversational capability, be easily adaptable to changing situations and conform to business constraints. This paper describes a 3-step procedure to develop a…

Being able to generate informative and coherent dialogue responses is crucial when designing human-like open-domain dialogue systems. Encoder-decoder-based dialogue models tend to produce generic and dull responses during the decoding step…

Recommender systems are embracing conversational technologies to obtain user preferences dynamically, and to overcome inherent limitations of their static models. A successful Conversational Recommender System (CRS) requires proper handling…

We present PolyResponse, a conversational search engine that supports task-oriented dialogue. It is a retrieval-based approach that bypasses the complex multi-component design of traditional task-oriented dialogue systems and the use of…

The amount of dialogue history to include in a conversational agent is often underestimated and/or set in an empirical and thus possibly naive way. This suggests that principled investigations into optimal context windows are urgently…

Conversational recommender systems (CRSs) integrate both recommendation and dialogue tasks, making their evaluation uniquely challenging. Existing approaches primarily assess CRS performance by separately evaluating item recommendation and…

Open domain dialog systems face the challenge of being repetitive and producing generic responses. In this paper, we demonstrate that by conditioning the response generation on interpretable discrete dialog attributes and composed…

Conditioned dialogue generation suffers from the scarcity of labeled responses. In this work, we exploit labeled non-dialogue text data related to the condition, which are much easier to collect. We propose a multi-task learning approach to…

Since the pre-trained language models are widely used, retrieval-based open-domain dialog systems, have attracted considerable attention from researchers recently. Most of the previous works select a suitable response only according to the…

Existing retrieval-augmented generation (RAG) systems are primarily designed under the assumption that each query has a single correct answer. This overlooks common information-seeking scenarios with multiple plausible answers, where…

Reward-driven proactive dialogue agents require precise estimation of user satisfaction as an intrinsic reward signal to determine optimal interaction strategies. Specifically, this framework triggers clarification questions when detecting…

Commit messages are important for software development and maintenance. Many neural network-based approaches have been proposed and shown promising results on automatic commit message generation. However, the generated commit messages could…

Conversational recommender systems (CRS) dynamically obtain the user preferences via multi-turn questions and answers. The existing CRS solutions are widely dominated by deep reinforcement learning algorithms. However, deep reinforcement…

Conversational search supports multi-turn user-system interactions to solve complex information needs. Different from the traditional single-turn ad-hoc search, conversational search encounters a more challenging problem of…

At the heart of improving conversational AI is the open problem of how to evaluate conversations. Issues with automatic metrics are well known (Liu et al., 2016, arXiv:1603.08023), with human evaluations still considered the gold standard.…

Retrieval Augmented Generation (RAG) is increasingly being used when building Generative AI applications. Evaluating these applications and RAG pipelines is mostly done manually, via a trial and error process. Automating evaluation of RAG…

Process or step-wise supervision has played a crucial role in advancing complex multi-step reasoning capabilities of Large Language Models (LLMs). However, efficient, high-quality automated process annotation remains a significant…

Current methods in open-domain question answering (QA) usually employ a pipeline of first retrieving relevant documents, then applying strong reading comprehension (RC) models to that retrieved text. However, modern RC models are complex…