Transformer language models develop attention heads that specialize in syntactic relations, for example, attending from verbs to their subjects. Do these heads play a causal role in the model's syntactic predictions? Evidence for such a role is mixed to negative: even when we force these heads to attend to a distractor noun other than the subject, the model's syntactic predictions are still more consistent with the subject than with the distractor. Interventions on specialized syntax heads had a significantly stronger effect on syntactic predictions than interventions on random heads, but only in one of the two measures we propose.
Figures & tables
Figure 1: Conceptual prediction for the causal influence of subject-verb attention heads on next-word predictions.
Figure 2: Top: 100k simulations estimating the relative probability, σ , assigned to the subject-consistent conditionation in the original model (right), and SV heads are forced to attend to only the distractor, σ(x;mdHsv) (left). A value greater than 0.5 (red) indicates a preference for the true subject, and a value less than 0.5 (blue) indicates a preference for the distractor-as-subject interpretation. Bottom: 100k simulations estimating the effect of SV heads on next-word prediction preference, relative to the baseline, measured over diagnostic pairs (left) and the full next-word distribution (right). Within each plot, positive values (blue) correspond to simulations where the intervention on the four SV heads had a larger effect on next word predictions than the same intervention on 4 random non-SV heads, while negative values (red) indicate the opposite.
Appendix figures & tables2 assets
Supplementary material from the paper’s appendix.
Appendix
Original Stimulus
Swap
The pumpkin near the child is {carved, upset}
pumpkin → stone
The plant by the gnome is {leafy, scary}
gnome → bear
The man with the crutch is {unhealthy, bent}
crutch → rod
The eraser beside the pencil is {round, sharp}
eraser → circle
The note for the proprietor is {illegible, happy}
proprietor → owner
Appendix
Table 1: One of the 48 items in our materials, adapted from Schlueter et al. (2019) . Participants in the original study read the sentence fragment, then selected one of the two adjectives to complete the sentence. The first adjective is consistent with the actual subject, woman , and the second adjective is consistent with the non-subject distractor noun, window(s) .
Stimulus ( x≤v )
{ c(s),c(d) }
P(cs∣xs)
P(cs∣xd)
P(cs∣x)
σ
The woman by the window is…
{amused,dusty}
0.96
0.042
0.94
0.98
The flower by the bed is
{blooming,made}
0.11
0.000091
0.11
1.0
The notebook for the class is
{ripped,difficult}
0.14
0.017
0.12
0.81
The laptop on the magazine is
{overheating,lengthy}
0.84
0.018
0.81
0.96
The stone near the child is
{carved,upset}
0.99
0.015
0.99
0.99
The baby near the pillow is
{happy,fluffy}
0.93
0.33
0.86
0.93
Appendix
Table 2: All 48 items in our materials, adapted from Schlueter et al. (2019) . Along with various quantities of interest from the original model, including the relative probability of the subject-consistent continuation, c(s) , given the subject-only reference sentence (e.g. x(s)= The woman is… ); given the distractor-only baseline (e.g. x(d)= The window is… ), and given the full sentence (e.g. x= The woman by the window is… ).
We show how causal interventions in Transformer models provide insights into English syntax by focusing on a long-standing challenge for syntactic theory: syntactic islands. Extraction from coordinated verb phrases is often degraded, yet acceptability varies gradiently with lexical content (e.g., "I know what he hates art and loves" vs. "I know what he looked down and saw"). We show that modern Transformer language models replicate human judgments across this gradient. Using causal interventions that isolate functionally relevant subspaces in Transformer blocks, attention modules, and MLPs, we demonstrate that extraction from coordination islands engages the same filler-gap mechanisms as canonical wh-dependencies, but that these mechanisms are selectively blocked to varying degrees. By projecting a large corpus of unrelated text onto these causally identified subspaces, we derive a novel linguistic hypothesis: the conjunction "and" is represented differently in extractable versus non-extractable constructions, corresponding to expressions encoding relational dependencies versus purely conjunctive uses. These results illustrate how mechanistic interpretability can inform syntax, generating new hypotheses about linguistic representation and processing.
We present a systematic review of 337 articles evaluating the syntactic abilities of Transformer-based language models (TLMs), reporting on over 3,000 datapoints spanning a wide range of syntactic phenomena, languages, models, and methods. We take the data to collectively show that TLMs encode a non-trivial amount of syntactic knowledge. Behavioral evidence shows strong performance on formal syntactic phenomena, but weaker and more variable performance on phenomena at the syntax-semantics interface. Performance is also consistently lower for languages with less digital support. Probing and mechanistic studies further support the presence of syntactic knowledge in TLMs. Yet, because most work remains observational and methodologically heterogeneous, insight into the detailed computational mechanisms underlying syntactic processing remains limited. At the same time, the literature remains heavily concentrated on English and BERT-like models. We discuss the implications of our results and provide recommendations for future research.
Transformers underlie almost all state-of-the-art language models in computational linguistics, yet their cognitive adequacy as models of human sentence processing remains disputed. In this work, we use a surprisal-based linking mechanism to systematically evaluate eleven autoregressive transformers of varying sizes and architectures on a more comprehensive set of English agreement attraction configurations than prior work. Our experiments yield mixed results: While transformer predictions generally align with human reading time data for prepositional phrase configurations, performance degrades significantly on object-extracted relative clause configurations. In the latter case, predictions also diverge markedly across models, and no model successfully replicates the asymmetric interference patterns observed in humans. We conclude that current transformer models do not explain human morphosyntactic processing, and that evaluations of transformers as cognitive models must adopt rigorous, comprehensive experimental designs to avoid spurious generalizations from isolated syntactic configurations or individual models.