Towards Proactive Detection of User-Side Implicit Conflicts in Human-LLM Dialogue

面向人机对话中用户侧隐性冲突的主动检测

Abstract: In Human-LLM dialogue, follow-up user utterances may implicitly conflict with earlier intents, leading the LLM to misinterpret user needs and generate inappropriate responses. A reliable dialogue system should proactively detect user-side conflicts before generating a response and seek clarification when necessary. However, prior work has largely focused on LLM-side conflicts, leaving user-side conflicts underexplored.

摘要： 在人机对话中，用户后续的表述可能会与其先前的意图产生隐性冲突，导致大语言模型（LLM）误解用户需求并生成不恰当的回复。一个可靠的对话系统应当在生成回复前主动检测用户侧的冲突，并在必要时寻求澄清。然而，以往的研究大多集中在模型侧的冲突，而对用户侧冲突的研究尚不充分。

To fill this gap, we construct UC-Bench, a human-annotated benchmark for evaluating user-side conflict detection. Preliminary experiments show that existing LLMs struggle with this task, especially when conflicts arise from implicit incompatibilities grounded in dialogue history. To improve lightweight LLMs with limited training data, we investigate data synthesis for user-side conflict detection. Existing synthesis methods do not explicitly model the implicit incompatibilities between historical and current user utterances, making it difficult to capture the evolution of conflicts and to generate reliably labeled implicit conflict samples.

为了填补这一空白，我们构建了 UC-Bench，这是一个用于评估用户侧冲突检测的人工标注基准。初步实验表明，现有的大语言模型在处理该任务时表现吃力，尤其是在冲突源于基于对话历史的隐性不兼容时。为了提升训练数据有限的轻量级模型，我们研究了用于用户侧冲突检测的数据合成方法。现有的合成方法并未显式建模历史表述与当前用户表述之间的隐性不兼容，导致难以捕捉冲突的演变，也难以生成标注可靠的隐性冲突样本。

We propose SynUC, a constraint-guided synthesis method that represents user-side conflicts in a constraint space and uses the SPEAKING framework to guide traceable constraint transformations. Applying SynUC to WildChat, we construct UC-Data, a user-side conflict training set containing 2,487 samples. On UC-Bench, Qwen3.5-4B trained on UC-Data outperforms larger general-purpose LLMs such as Claude Opus 4.8, as well as the same backbone trained on data synthesized by existing methods.

我们提出了 SynUC，这是一种约束引导的合成方法，它在约束空间中表示用户侧冲突，并利用 SPEAKING 框架来引导可追溯的约束转换。通过将 SynUC 应用于 WildChat，我们构建了 UC-Data，这是一个包含 2,487 个样本的用户侧冲突训练集。在 UC-Bench 测试中，使用 UC-Data 训练的 Qwen3.5-4B 模型表现优于 Claude Opus 4.8 等更大的通用大语言模型，同时也优于使用现有合成方法训练的同基座模型。