arXiv:2604. 26157v4 Announce Type: replace-cross Abstract: Structural generalization in semantic parsing requires systems to apply learned compositional rules to novel structural combinations.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
The paper investigates how verb–noun decomposition, a common strategy for recognizing assembly actions, generalizes to novel combinations of familiar components. Through a systematic study on three datasets (MECCANO, HAViD, and IMPACT), the authors find that while decomposition avoids the zero‑probability ceiling of atomic classifiers, its performance still heavily depends on the co‑occurrence patterns seen during training. The analysis reveals that errors concentrate on the larger‑vocabulary component, that shared‑encoder training can entangle components and worsen generalization, and that these issues stem from primitive support, vocabulary asymmetry, and component entanglement.
arXiv:2607. 02307v1 Announce Type: cross Abstract: Several SLOG test categories explicitly involve directional distinctions (modifier position shifts, argument extraction positions), yet AM-Parser, the previous SOTA, uses an AM algebra whose operations do not encode direction.
arXiv:2609.21509v1 Announce Type: new Abstract: When language models reason in chain-of-thought or exchange free-text intermediates, they serialize structured information into natural language. How m...
The paper evaluates two large language models, Claude Sonnet 4.5 and Claude Opus 5, on the bidirectional English Resource Grammar (ERG) tasks of generating English from Minimal Recursion Semantics (MRS) and parsing English into MRS. In generation, Opus achieves 76.3 BLEU—surpassing a 72k‑pair trained system and matching a million‑pair system—while Sonnet scores 65.7 BLEU, rising to 69.6 when selecting from ACE’s candidates. In parsing, both models lag behind ACE, attaining only 57.2 and 65.5 F₁ respectively, with exact‑match on about 1 % of sentences, highlighting that high generation scores do not guarantee accurate semantic parsing.
arXiv:2607. 18961v1 Announce Type: new Abstract: Large language models (LLMs) generate fluent text by incrementally predicting the next token from a prefix.
The paper investigates why Transformers struggle more with structural than lexical compositional generalisation. It argues that this disparity stems from low structural type diversity rather than an inherent limitation of Transformers. By creating linguistically diverse variants of the COGS and SLOG datasets, the authors show that type diversity correlates equally with generalisation in both lexical and structural cases, challenging previous explanations of the difficulty.