X-CoT: Explainable Text-to-Video Retrieval via LLM-based Chain-of-Thought Reasoning
This addresses the need for interpretable retrieval systems in multimedia applications, though it is incremental as it builds upon existing LLM and CoT methods.
The paper tackles the problem of low interpretability and data quality issues in text-to-video retrieval by proposing X-CoT, an explainable framework using LLM-based chain-of-thought reasoning, which improves retrieval performance and provides detailed rationales.
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.