用三要素分析大规模LoRA，让检索更准更可靠。
CARLoS: Retrieval via Concise Assessment Representation of LoRAs at Scale
- 通过语义方向、强度和一致性三要素表征LoRA行为
- 在650个LoRA上验证，检索准确率优于文本基线
- 适合需要精准筛选LoRA的开发者与版权研究者
生成组件（如LoRA）的爆发式增长带来了庞大但无序的生态。现有发现方法依赖不可靠的用户描述或有偏的流行度指标，影响可用性。我们提出CARLoS，一种无需额外元数据的大规模LoRA表征框架。通过对超过650个LoRA在多种提示词和随机种子下进行图像生成分析，以可信方式评估其行为。利用CLIP嵌入及其与基础模型生成结果的差异，我们构建了一个三部分的简洁表征：方向（定义语义偏移）、强度（量化效果显著性）和一致性（衡量效果稳定性）。基于此表征，我们设计了高效的语义检索框架，能将文本查询匹配到相关LoRA，同时过滤过强或不稳定的模型，在自动与人工评估中均优于文本基线。尽管检索是主要目标，该表征还支持将强度与一致性关联至版权中的实质性与自愿性概念，为LoRA分析提供实际应用价值。
原文摘要 · Abstract (English)
The rapid proliferation of generative components, such as LoRAs, has created a vast but unstructured ecosystem. Existing discovery methods depend on unreliable user descriptions or biased popularity metrics, hindering usability. We present CARLoS, a large-scale framework for characterizing LoRAs without requiring additional metadata. Analyzing over 650 LoRAs, we employ them in image generation over a variety of prompts and seeds, as a credible way to assess their behavior. Using CLIP embeddings and their difference to a base-model generation, we concisely define a three-part representation: Directions, defining semantic shift; Strength, quantifying the significance of the effect; and Consistency, quantifying how stable the effect is. Using these representations, we develop an efficient retrieval framework that semantically matches textual queries to relevant LoRAs while filtering overly strong or unstable ones, outperforming textual baselines in automated and human evaluations. While retrieval is our primary focus, the same representation also supports analyses linking Strength and Consistency to legal notions of substantiality and volition, key considerations in copyright, positioning CARLoS as a practical system with broader relevance for LoRA analysis.
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。