用指令引导发现隐藏因素，无需任务标注就能提升模型表现。
Latent Factor Models Meets Instructions: Goal-conditioned Latent Factor Discovery without Task Supervision
- 结合大模型指令理解与统计建模，从噪声数据中挖掘目标相关属性。
- 在多个任务上提升性能5%-52%，人类评估偏好度高出1.8倍。
- 适合需要可解释性表示的场景，如推荐、法律文档分类。
指令跟随的大语言模型最近使系统能够基于自然语言描述的目标，从无结构文档中发现隐藏概念。然而，发现质量受大模型推理能力影响，当数据噪声大或超出其知识范围时性能下降。我们提出Instruct-LF，一种面向目标的潜在因子发现系统，将大模型的指令跟随能力与统计模型结合，以处理大规模、噪声多的数据集。Instruct-LF利用大模型从文档中提取细粒度的目标相关属性，估算其在数据集中的出现情况，并通过梯度优化揭示隐藏因子，每个因子由共现属性簇表示。我们在电影推荐、文本世界导航和法律文档分类任务上评估了Instruct-LF生成的潜在因子。这些可解释表示在下游任务中性能优于最佳基线5%-52%，在人类评估中偏好度平均高出1.8倍。
原文摘要 · Abstract (English)
Instruction-following LLMs have recently allowed systems to discover hidden concepts from a collection of unstructured documents based on a natural language description of the purpose of the discovery (i.e., goal). Still, the quality of the discovered concepts remains mixed, as it depends heavily on LLM's reasoning ability and drops when the data is noisy or beyond LLM's knowledge. We present Instruct-LF, a goal-oriented latent factor discovery system that integrates LLM's instruction-following ability with statistical models to handle large, noisy datasets where LLM reasoning alone falls short. Instruct-LF uses LLMs to propose fine-grained, goal-related properties from documents, estimates their presence across the dataset, and applies gradient-based optimization to uncover hidden factors, where each factor is represented by a cluster of co-occurring properties. We evaluate latent factors produced by Instruct-LF on movie recommendation, text-world navigation, and legal document categorization tasks. These interpretable representations improve downstream task performance by 5-52% than the best baselines and were preferred 1.8 times as often as the best alternative, on average, in human evaluation.
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。