用大模型思维链解释视频检索结果，提升可读性与数据质量评估能力。
X-CoT: Explainable Text-to-Video Retrieval via LLM-based Chain-of-Thought Reasoning
- 用大模型思维链替代传统相似度计算，实现逐对比较推理
- 在多个基准上检索性能提升，生成完整推理过程
- 适合需要可解释性的视频检索研究与数据质检场景
现有文本到视频检索系统主要依赖嵌入模型提取特征并计算余弦相似度进行排序，但存在两个局限：低质量文本-视频配对难以识别且会损害检索效果；仅靠余弦相似度无法提供排序解释，限制可解释性。本文提出X-CoT框架，利用大模型思维链（LLM CoT）替代嵌入模型的相似度匹配，实现可解释的检索。首先扩展现有基准，增加视频标注以支持语义理解、减少数据偏差；其次设计检索思维链，包含逐对比较步骤，生成详细推理并完成完整排序。实验表明，X-CoT在多个基准上提升检索性能，并输出可解释的推理链条，有助于模型行为与数据质量分析。代码与数据已开源。
原文摘要 · Abstract (English)
Prevalent text-to-video retrieval systems mainly adopt embedding models for feature extraction and compute cosine similarities for ranking. However, this design presents two limitations. Low-quality text-video data pairs could compromise the retrieval, yet are hard to identify and examine. Cosine similarity alone provides no explanation for the ranking results, limiting the interpretability. We ask that can we interpret the ranking results, so as to assess the retrieval models and examine the text-video data? This work proposes X-CoT, an explainable retrieval framework upon LLM CoT reasoning in place of the embedding model-based similarity ranking. We first expand the existing benchmarks with additional video annotations to support semantic understanding and reduce data bias. We also devise a retrieval CoT consisting of pairwise comparison steps, yielding detailed reasoning and complete ranking. X-CoT empirically improves the retrieval performance and produces detailed rationales. It also facilitates the model behavior and data quality analysis. Code and data are available at: https://github.com/PrasannaPulakurthi/X-CoT.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。