The paper investigates how large language models (LLMs) handle two usage‑based grammatical strategies: coercion, where a mismatched word is reinterpreted to fit its context, and preemption, where a plausible structure is avoided because it never appears in expected contexts. Experiments across models of varying sizes show that larger LLMs successfully recognize and produce constructional productivity in coercive situations, even with novel words, but they fail to exhibit preemptive behavior, lacking the negative evidence that would guide avoidance of unconventional but semantically viable constructions. The authors argue that coercion is detectable due to its surprising, semantically motivated nature, whereas preemption lacks such a signature, leading to an asymmetry where models coerce but do not preempt.
By Claire Bonial, Claire Benet Post, Laura Michaelis, Harish Tayyar Madabushi
The paper investigates natural language autoencoders (NLAs) as tools for verbalizing activation differences in large language models. It examines whether NLAs capture compositional structure, generalize to fine‑tuned models, recover fine‑tuning objectives, and can be specialized for model diffing. Experiments across four models show that NLAs largely succeed in these tasks, though they do not yet match state‑of‑the‑art diffing methods on emergent misalignment detection.
By Andrea Blasi N\'u\~nez, Gianluca Barmina, Federico Torrielli, Thiusius Rajeeth Savarimuthu, Peter Schneider-Kamp, Lukas Galke Poech
The paper investigates natural language autoencoders (NLAs) that convert large language model activations into readable text. It examines whether NLAs capture compositional structure, generalize to fine‑tuned models, recover fine‑tuning objectives, and can be specialized for model diffing. Experiments across multiple models show positive results: NLAs preserve compositionality, transfer to lightweight fine‑tunes, recover hidden objectives, and outperform a black‑box baseline on diffing tasks, though they lag behind state‑of‑the‑art methods for misalignment detection.
arXiv:2606. 00230v1 Announce Type: new Abstract: Grokking, the phenomenon in which neural networks generalize long after fitting their training data, has been studied in supervised settings on many epochs.
By Sherin Muckatira, Namrata Shivagunde, Vijeta Deshpande, Anna Rumshisky
The paper investigates whether language models can transfer hierarchical syntactic knowledge from a source language (L1) to a target language (L2) using a novel cross‑lingual poverty‑of‑stimulus (CPOS) experimental design. Results show that models can partially transfer L1 structural evidence to L2, producing a small but detectable hierarchical bias that varies across language pairs. The study further demonstrates that vocabulary overlap is crucial for successful transfer, indicating that cross‑lingual learning of hierarchical generalization is conditionally achievable.
By Shin Yamaguchi, Masaya Taniguchi, Tatsuki Kuribayashi, Taro Watanabe, Yoshinobu Kano
The study investigates how augmenting training data with conceptually related alternatives—beyond nouns to include verbs and adjectives—affects large language models trained with next-token prediction. Results show that while concept augmentation consistently improves perplexity on news data regardless of part of speech, verbs yield the most reliable downstream performance gains. Representational analyses reveal that the conditions producing the largest downstream improvements do not always correspond to the greatest changes in internal representations.
By Laya Iyer, Chen Shani
The paper investigates indirect evidence in language models by applying influence functions to identify training sentences that affect predictions on 15 grammatical phenomena from BLiMP. After filtering out direct evidence, the authors select the 60,000 most influential remaining sentences and show that removing them significantly degrades held‑out accuracy, more so than random removal. They further analyze the characteristics of this indirect evidence and demonstrate that clustering phenomena based on shared indirect evidence recovers known linguistic categories.
By William Dai, Zhenghao Herbert Zhou, Maya Viswanathan, Robert Frank
arXiv:2609.37497v1 Announce Type: new
Abstract: Modern transformer models excel at capturing semantic relationships through sentence embeddings, yet their ability to perform pragmatic reasoning remai...
By Stefania Butnaru, Claudiu Creanga
arXiv:2610.09571v1 Announce Type: new
Abstract: Negation is an essential feature of human language, yet large language models (LLMs) remain unreliable in processing it. We evaluate recent open-source...
By Jongwook Yoon, Jongwon Lim, Sungjib Lim, Woojin Cho, Yohan Jo
The paper studies structural priming in language model production by conducting controlled sentence‑completion experiments on dative constructions. Results show that language models exhibit priming effects, especially when sentences are semantically coherent, with stronger relative increases for double‑object datives and larger absolute increases for prepositional‑object datives. The study also finds that primed completions involve more lexico‑semantic repetition, indicating that priming operates across syntactic, lexical, and semantic levels.
By Giulia Pucci, Ruizhe Li, Arabella Sinclair
Large language models are typically trained with next-token prediction (NTP), which rewards predicting specific tokens rather than explicitly accounting for the semantic similarities between different...
arXiv:2607. 29062v1 Announce Type: new Abstract: Model capabilities have improved in large part due to scaling chain of thought.
By Matthew Nguyen, Kyle Cox, Austin Meek, Iv\'an Arcuschin