基于物体描述的推理提高了基于任务的对话系统中的指代消解
Reasoning over Object Descriptions Improves Coreference Resolution in Task-Based Dialogue Systems
AI总结：
本文提出一种单模态测试时推理方法，通过详细物体元数据和对话历史推理提升指代消解，实验表明在SIMMC 2.1数据集上效果显著，且在少样本设置下能有效泛化到新场景和物体。
摘要：
基于任务的对话系统通过自然语言交互帮助用户完成特定目标，如执行操作或检索信息。准确的指代消解至关重要，因为它涉及识别对话中的物体引用，这在视觉化环境中变得越来越具有挑战性，因为场景复杂且物体元数据多样。然而，基于任务的对话中的指代消解仍然受到跨领域泛化能力差和对监督模型的依赖限制。在本工作中，我们提出了一种单模态测试时推理方法，使大语言模型（LLMs）能够通过详细物体元数据和对话历史推理来提高指代消解。在SIMMC 2.1数据集上的实验证明，LLMs可以生成逐步推理过程，有效对齐对话上下文与场景中的物体。广泛实验突显了模型准确链接对话和物体的能力。此外，我们展示在少样本设置下测试时推理能有效泛化到未见场景和新物体，优于基于编码器的监督方法在跨领域评估中。这些发现强调了结构化元数据和精心设计提示工程在增强基于任务的对话系统鲁棒性和泛化能力中的关键作用。
英文摘要：
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 object references within the dialogue - a task that becomes increasingly challenging in visually grounded environments characterized by complex scenes and diverse object metadata. However, coreference resolution in task-based dialogue remains limited by poor generalization across domains and heavy reliance on supervised models that often overfit to dataset-specific artifacts. In this work, we propose a unimodal test-time reasoning approach that enables large language models (LLMs) to reason over detailed object metadata and dialogue history to improve coreference resolution. Empirical results on the SIMMC 2.1 dataset demonstrate that LLMs can generate step-by-step reasoning processes that effectively align dialogue context with objects present in the scene. Extensive experiments highlight the models' ability to link conversations and objects accurately. Moreover, we show that test-time reasoning under few-shot settings generalizes effectively to unseen scenarios and novel objects, outperforming encoder-based supervised methods in cross-domain evaluations. These findings underscore the critical role of structured metadata and careful prompt engineering in enhancing the robustness and generalization of task-oriented dialogue systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
