The paper investigates how language models avoid overgeneralizations by distinguishing between two types of indirect negative evidence: preemption and entrenchment. Through controlled rearing experiments on models trained on child‑caregiver conversations, the authors find that models do not exhibit verb‑specific preemption but show weak abstract preemption. Analysis of training dynamics suggests that competing structures act as indirect positive evidence rather than negative in the verb‑specific condition.
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.
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.
arXiv:2607. 29062v1 Announce Type: new Abstract: Model capabilities have improved in large part due to scaling chain of thought.
arXiv:2603. 01437v2 Announce Type: replace Abstract: As chain of thought (CoT) has become central to scaling reasoning capabilities in large language models (LLMs), it has also emerged as a promising tool for interpretability, suggesting the opportunity to understand model decisions through verbalized reasoning.
arXiv:2606. 08682v1 Announce Type: cross Abstract: Activation steering has emerged as a popular inference-time technique for modulating the behavior of large language models (LLMs).
arXiv:2607. 21498v1 Announce Type: cross Abstract: A rhetorical figure that Cicero and Quintilian catalogued two thousand years ago reappears, systematically, in the text of large language models: epanorthosis, the self-correction of the specimen {\guillemotleft}This is not a course.
arXiv:2604. 06374v2 Announce Type: replace-cross Abstract: Latent reasoning via continuous chain-of-thoughts (Latent CoT) has emerged as a promising alternative to discrete CoT reasoning.
arXiv:2602. 12811v2 Announce Type: replace-cross Abstract: When humans and large language models (LLMs) process the same text, activations in the LLMs correlate with brain activity measured, e.
Large Language Models (LLMs) frequently exhibit sycophancy, where they agree with a user's statement even when incorrect. While sycophancy is often treated as a single defined behavior, it can manifest in substantially distinct ways and circumstances, raising the question of whether this multi-faceted nature is reflected in its internal mechanisms.
arXiv:2608. 05734v1 Announce Type: new Abstract: Subliminal Learning (SL) is a surprising type of generalization displayed by modern language models.
Language models trained on tokenized text still reliably produce morphemes whose form depends on phonology, but it was unclear whether this relies on memorization or rule-like generalization. The study shows that for the English indefinite article a/an, the phonological condition is encoded along a single linear direction in trigger-token embeddings, causally drives article selection in token-level wug tests, and is used by the model to forecast the upcoming trigger token’s phonological feature for article choice. The authors further investigate whether this rule-like generalization extends to allomorph selection in other languages and to explicit phonological judgment, offering a mechanistic account that separates generation-time ability from metalinguistic judgments.
arXiv:2607. 28319v1 Announce Type: cross Abstract: This work presents Fairness Pruning, a lightweight structural intervention method designed for the management and future mitigation of demographic bias in large language models (LLMs).