The paper examines the compositionality gap in GPT‑2‑like transformers, where models can combine known facts in‑distribution but fail to generalize to out‑of‑distribution knowledge. By aligning the training distribution so that both ID and OOD atomic facts appear in the same positional format as the second‑hop retrieval step of a known compositional circuit, the authors show that the model can transfer its learned compositional behavior to unseen OOD facts. This demonstrates that the gap is not an inherent architectural limitation but can be addressed through targeted training distribution design.
Compositional generalization remains a persistent limitation of transformer language models: even when a model learns to combine known facts correctly in-distribution (ID), the same compositional mech...
Large language models can solve complex multi‑hop tasks but often fail on simple two‑hop queries, even when each hop is individually correct. In a controlled symbolic setting, the authors find that models generalize reliably when the second hop follows the training distribution, but always fail when it deviates. Mechanistic analysis shows that successful generalization relies on consistent intermediate representations across contexts, whereas failures arise from a mismatch between lower‑layer representation construction and upper‑layer mapping to outputs. The study proposes a recurrent‑style training strategy that improves out‑of‑distribution two‑hop generalization.
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.
arXiv:2604. 07822v2 Announce Type: replace-cross Abstract: We study implicit reasoning, i.
arXiv:2607. 11875v1 Announce Type: cross Abstract: We present a theoretical framework to explain the emergence of inductive reasoning abilities in Transformer language models.
arXiv:2505.22635v2 Announce Type: replace-cross Abstract: A common approach for teaching large language models (LLMs) to reason is to train on chain-of-thought (CoT) traces of in-distribution reasoni...
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 unifies several synthetic tasks known in the literature, including in-context n-grams and multi-hop reasoning.
arXiv:2607. 00341v1 Announce Type: cross Abstract: Large language models achieve strong performance on many reasoning tasks when allowed to externalize intermediate steps as Chain-of-Thought (CoT).
The State Stream Transformer (SST) V2 introduces a parameter‑efficient, FFN‑driven nonlinear recurrence that streams latent states horizontally across a sequence, enabling continuous latent deliberation at inference time. A two‑pass parallel training procedure approximates this recurrence, making co‑training practical. Experiments on GSM8K and GPQA‑Diamond show that SST achieves a 61.11% architectural capacity bound and a 15.15‑point improvement over a fine‑tuning‑matched baseline, while reducing GSM8K errors by 46%.
arXiv:2607. 15178v1 Announce Type: cross Abstract: Transformer reasoning is limited by autoregressive decoding, which repeat edly compresses rich hidden computation through token space and makes it difficult for intermediate reasoning states to persist across time.
The paper investigates how transformer models learn latent structure by training a small decoder-only transformer on three variants of the Alchemy benchmark. It finds that the model acquires different components of latent structure in discrete stages, with a notable asymmetry: it robustly composes fundamental transitions but struggles to decompose complex examples into atomic transitions. Layer‑specific causal interventions reveal plasticity windows where freezing layers delays or prevents stage completion, offering a detailed view of capability evolution during training.
arXiv:2505.09716v4 Announce Type: replace Abstract: Out-of-distribution (OOD) generalisation through composition requires a system to discover invariant properties from input-output associations and...