通过人工语言实验，发现大模型在推理时能隐式学习语言规律，表现类似人类。
Implicit In-Context Learning: Evidence from Artificial Language Experiments
- 用人工语言实验测试模型在推理中隐式学习能力
- o3-mini在词法层面更接近人类，两者在句法上均表现相似
- 为理解大模型语言学习机制提供新证据，适合关注认知类比的研究者
人类通过隐式学习掌握语言，无需明确意识即可吸收复杂模式。尽管大语言模型展现出出色的语言能力，但它们在推理阶段是否具备类似人类的模式识别能力仍不明确。我们改编了三项经典的人工语言学习实验，涵盖词法、词形句法和句法三个领域，系统评估了两个先进OpenAI模型gpt-4o和o3-mini在推理阶段的隐式学习表现。结果显示，模型与人类行为在不同语言领域存在特定一致性：o3-mini在词法层面更接近人类，而两者在句法层面均表现出相似性。
原文摘要 · Abstract (English)
Humans acquire language through implicit learning, absorbing complex patterns without explicit awareness. While LLMs demonstrate impressive linguistic capabilities, it remains unclear whether they exhibit human-like pattern recognition during in-context learning at inferencing level. We adapted three classic artificial language learning experiments spanning morphology, morphosyntax, and syntax to systematically evaluate implicit learning at inferencing level in two state-of-the-art OpenAI models: gpt-4o and o3-mini. Our results reveal linguistic domain-specific alignment between models and human behaviors, o3-mini aligns better in morphology while both models align in syntax.
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。