基于推理的无监督文本聚类细化方法
Reasoning-Based Refinement of Unsupervised Text Clusters with LLMs
AI总结：
本文提出利用大语言模型作为语义评判者，对无监督聚类结果进行推理细化，通过三个阶段提升聚类的连贯性与可解释性，实验证明其在社交媒体数据中优于传统方法。
摘要：
无监督方法广泛用于从大规模文本中诱导潜在语义结构，但其输出常包含不连贯、冗余或缺乏依据的聚类，难以在无标注数据的情况下验证。本文提出一种基于推理的细化框架，利用大语言模型（LLM）作为语义评判者，而非嵌入生成器，以验证和重构任意无监督聚类算法的输出。框架引入三个推理阶段：（i）连贯性验证，LLM评估聚类摘要是否由成员文本支持；（ii）冗余裁决，根据语义重叠合并或拒绝候选聚类；（iii）标签接地，通过两阶段过程为聚类分配可解释标签，完全无监督地生成和整合语义相似的标签。此设计将表征学习与结构验证解耦，缓解了仅依赖嵌入方法的常见失败模式。我们在真实世界社交媒体数据集上评估该框架，来自两个交互模型不同的平台，证明了在聚类连贯性和人类对齐标签质量上的持续改进。人类评估显示，尽管没有黄金标准标注，与LLM生成标签的共识强烈。我们进一步在匹配的时间和体积条件下进行鲁棒性分析，以评估跨平台稳定性。除了经验性收益，我们的结果表明，基于LLM的推理可以作为一种通用机制，用于验证和细化无监督语义结构，使在无监督情况下对大规模文本集合进行更可靠和可解释的分析成为可能。
英文摘要：
Unsupervised methods are widely used to induce latent semantic structure from large text collections, yet their outputs often contain incoherent, redundant, or poorly grounded clusters that are difficult to validate without labeled data. We propose a reasoning-based refinement framework that leverages large language models (LLMs) not as embedding generators, but as semantic judges that validate and restructure the outputs of arbitrary unsupervised clustering algorithms. Our framework introduces three reasoning stages: (i) coherence verification, where LLMs assess whether cluster summaries are supported by their member texts; (ii) redundancy adjudication, where candidate clusters are merged or rejected based on semantic overlap; and (iii) label grounding, where clusters are assigned interpretable labels through a two-stage process that generates and consolidates semantically similar labels in a fully unsupervised manner. This design decouples representation learning from structural validation and mitigates the common failure modes of embedding-only approaches. We evaluate the framework in real-world social media corpora from two platforms with distinct interaction models, demonstrating consistent improvements in cluster coherence and human-aligned labeling quality over classical topic models and recent representation-based baselines. Human evaluation shows strong agreement with LLM-generated labels, despite the absence of gold-standard annotations. We further conduct robustness analysis under matched temporal and volume conditions to assess cross-platform stability. Beyond empirical gains, our results suggest that LLM-based reasoning can serve as a general mechanism for validating and refining unsupervised semantic structure, enabling more reliable and interpretable analysis of large text collections without supervision.
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。
