新研究探讨Transformer学习动力学和推理机制 · 追踪4个来源

报道来源 [4]

1. arXiv cs.AI TIER_1 English(EN) · Tiberiu Musat, Tiago Pimentel, Nicholas Zucchet, Thomas Hofmann · 2026-07-14 04:00

   Invariant Learning Dynamics of Transformers in Inductive Reasoning Tasks

   arXiv:2607.11875v1 Announce Type: cross Abstract: We present a theoretical framework to explain the emergence of inductive reasoning abilities in Transformer language models. While previous works on Transformer learning dynamics have so far been mostly tied to specific tasks, we …

2. arXiv cs.AI TIER_1 English(EN) · Zixuan Gong, Shijia Li, Yong Liu, Jiaye Teng · 2026-07-14 04:00

   Disentangling Feature Structure: A Mathematically Provable Two-Stage Training Dynamics in Transformers

   arXiv:2502.20681v3 Announce Type: replace-cross Abstract: Transformers may exhibit two-stage training dynamics during the real-world training process. For instance, when training GPT-2 on the Counterfact dataset, the answers progress from syntactically incorrect to syntactically …

3. arXiv cs.AI TIER_1 English(EN) · Pengxiao Lin, Zheng-An Chen, Zhi-Qin John Xu · 2026-07-14 04:00

   Unveiling the Mechanisms of Multi-Hop Reasoning in Transformers via Identity Bridge

   arXiv:2509.24653v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) excel at multi-hop reasoning in distribution, yet fail on unseen compositions, a phenomenon known as the curse of two-hop reasoning. In this work, we argue that this phenomenon can be attribute…

4. arXiv cs.AI TIER_1 English(EN) · Thomas Hofmann · 2026-07-13 17:56

   Transformer在归纳推理任务中的不变学习动力学

   We present a theoretical framework to explain the emergence of inductive reasoning abilities in Transformer language models. While previous works on Transformer learning dynamics have so far been mostly tied to specific tasks, we study a generalized class of inductive tasks that …