The study investigates whether large language models retain traces of abandoned syntactic analyses after encountering garden‑path sentences. Across 24 models ranging from 124 M to 70 B parameters, the authors find that a residue of the initial, incorrect analysis influences later object attachment, while an adaptation toward the resolved structure scales with disambiguation error. Activation‑patching experiments show that the residue is carried by noun‑phrase states computed under the object analysis, and that overriding these states largely removes the effect.
By Xiang Ding
arXiv:2608. 04021v1 Announce Type: cross Abstract: Cloze-style probes that vary how often a target token appears implicitly assume that more copies of a target affect prediction the same way regardless of where the readout slot sits.
By Han-yu Wang
The paper investigates whether language models can identify sentences from their training data by using exact duplication counts from publicly released corpora for two model families, OLMo‑2 and Pythia. It finds that for typical duplication levels, models show only a weak trace of exposure, with a rank correlation near –0.08, and that strong signals only appear when a sentence appears roughly a thousand times, at which point fame rather than memory dominates. The study also demonstrates that common membership tests can be misleading, as changing a single word does not alter the model’s preference, and that controlling for register can significantly improve detector performance.
By Arman Nik Khah
The paper investigates how periodic subject changes—termed interruptions—affect the perceived novelty and coherence of text generated by base language models. By inserting a new subject every few hundred tokens into a stream that otherwise repeats, the authors find that judged surprise increases by 1.2 to 1.4 points and connection by 0.8 points compared to habituation alone. The study also reports that such interruptions do not produce integrated documents, and that the effect is robust across different models and evaluation protocols.
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
What do a language model's hidden states say about the organization of a single text? From one forward pass, without training, we score every token position on two properties.
arXiv:2607. 07891v1 Announce Type: cross Abstract: Roy Harris's Integrationist linguistics offers a compelling critique of the referentialist tradition embedded deep at the heart of computational approaches to language, arguing that language is not a code that maps onto a pre-given world but a situated, bipartite activity oriented toward prospective joint action.
By J. Mark Bishop, Stephen J. Cowley
When a tool-using agent is given the same task in a different language, does it still take the same steps? Multilingual evaluation rarely asks: it compares final answers and discards the actions.
arXiv:2606. 07555v1 Announce Type: cross Abstract: Glossaries, technical specifications, and system prompts routinely ask language models to use familiar words in unfamiliar ways.
By Han-yu Wang
The paper investigates how semantic meaning is arranged locally within large language models. By using two controlled probes—one cross‑lingual and one refinement probe—on four decoder‑only LLMs, it finds that after removing dominant variance directions, sentence pairs rank by semantic relatedness, semantic factors cluster around an invariant core with structured variation, refinement tightens neighborhoods, and sentence‑level versus token‑local readouts reveal complementary geometric patterns. These results suggest that LLM semantics form local anisotropic neighborhoods that contract when meaning is refined.
By Andr\'es Daniel Godoy Ortiz
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.
The study examines whether large language models (LLMs) show syntactic convergence with human users by analyzing turn‑adjacent reuse of context‑free grammar (CFG) rules in 1,901 matched positions across sixteen open‑weight Llama and Gemma models. All models exhibited greater CFG‑rule overlap with the preceding human turn than with unrelated primes, especially for lower‑frequency rules, and instruction‑tuned models showed even higher overlap with the actual prime than the human responses they replaced. However, instruction tuning also increased overlap with unrelated primes, reduced the actual‑versus‑random difference, and lowered conditional rule‑reuse odds when controlling for rule‑set size, while consistently producing responses with higher lexical and semantic similarity to the preceding turn.
By Zandi Eberstadt