Task Generalization With AutoRegressive Compositional Structure: Can Learning From $\d$ Tasks Generalize to $\d^{T}$ Tasks?
원문 초록
Large language models (LLMs) exhibit remarkable task generalization, solving tasks they were never explicitly trained on with only a few demonstrations. This raises a fundamental question: When can learning from a small set of tasks generalize to a large task family? In this paper, we investigate task generalization through the lens of AutoRegressive Compositional (ARC) structure, where each task is a composition of $T$ operations, and each operation is among a finite family of $\d$ subtasks. This yields a total class of size~\( \d^\TT \). We first show that generalization to all \( \d^\TT \) tasks is theoretically achievable by training on only \( \tilde{O}(\d) \) tasks. Empirically, we demonstrate that Transformers achieve such exponential task generalization on sparse parity functions via in-context learning (ICL) and Chain-of-Thought (CoT) reasoning. We further demonstrate this generalization in arithmetic and language translation, extending beyond parity functions.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Improving In-Context Learning with Reasoning Distillation
Assay2Mol: large language model-based drug design using BioAssay context
Tile-Based ViT Inference with Visual-Cluster Priors for Zero-Shot Multi-Species Plant Identification
DS@GT at CheckThat! 2025: Detecting Subjectivity via Transfer-Learning and Corrective Data Augmentation
DS@GT at CheckThat! 2025: Evaluating Context and Tokenization Strategies for Numerical Fact Verification
DS@GT at CheckThat! 2025: Ensemble Methods for Detection of Scientific Discourse on Social Media
토론
이 논문과 연결된 포럼 글이 아직 없습니다.