Papers › Pushdown Layers: Encoding Recursive Structure in Transformer Language Models

Pushdown Layers: Encoding Recursive Structure in Transformer Language Models

29 Oct 2023arXiv:2310.19089archive 2025-07-28

Shikhar Murty, Pratyusha Sharma, Jacob Andreas, Christopher D. Manning

Recursion is a prominent feature of human language, and fundamentally challenging for self-attention due to the lack of an explicit recursive-state tracking mechanism. Consequently, Transformer language models poorly capture long-tail recursive structure and exhibit sample-inefficient syntactic generalization. This work introduces Pushdown Layers, a new self-attention layer that models recursive state via a stack tape that tracks estimated depths of every token in an incremental parse of the observed prefix. Transformer LMs with Pushdown Layers are syntactic language models that autoregressively and synchronously update this stack tape as they predict new tokens, in turn using the stack tape to softly modulate attention over tokens -- for instance, learning to "skip" over closed constituents. When trained on a corpus of strings annotated with silver constituency parses, Transformers equipped with Pushdown Layers achieve dramatically better and 3-5x more sample-efficient syntactic generalization, while maintaining similar perplexities. Pushdown Layers are a drop-in replacement for standard self-attention. We illustrate this by finetuning GPT2-medium with Pushdown Layers on an automatically parsed WikiText-103, leading to improvements on several GLUE text classification tasks.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2310.19089")

Code

Syntology Ran 14 of 23 code samples harvested from 1 repository linked to this paper; 9 have no recorded run. Of those that ran: 1 ran · honoured contract; 13 ran with no contract checked.

By repository: official repository: 23 samples from 1 repository, 14 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

murtyshikhar/pushdown-layers officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

23 samples harvested; 14 ran; 1 honoured the contract we drafted; 9 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
13ran
9unverified

Licence: 23 of the 23 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from MurtyShikhar/Pushdown-Layers. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

AttentionMask MurtyShikhar/Pushdown-Layers/models/pushdown_transformer_lm.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · 551d6401ece551f3 · report
DotDict MurtyShikhar/Pushdown-Layers/models/pushdown_transformer_lm.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · a7a732117e3ad716 · report
MultiHeadAttentionBase MurtyShikhar/Pushdown-Layers/models/pushdown_transformer_lm.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · 6ea6715c721ed9a7 · report
PositionalEncoding MurtyShikhar/Pushdown-Layers/models/pushdown_transformer_lm.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · 545b1940b792fa22 · report
RelativeAttentionBase MurtyShikhar/Pushdown-Layers/models/pushdown_transformer_lm.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · 59316687afde843b · report
TiedEmbedding MurtyShikhar/Pushdown-Layers/models/pushdown_transformer_lm.py official repository ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 5612e13b2384e5b0 · report
TransformerEncoder MurtyShikhar/Pushdown-Layers/models/pushdown_transformer_lm.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · 217b95213cfe1f2b · report
TransformerResult MurtyShikhar/Pushdown-Layers/models/pushdown_transformer_lm.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · cd78addc129539b3 · report
compute_per_token_logprob murtyshikhar/pushdown-layers/pushdown_util.py official repository ran no licence file found · pointer only · 70622ae82f44b450 · report
compute_stack_logprobs murtyshikhar/pushdown-layers/pushdown_util.py official repository ran no licence file found · pointer only · dcf24b95d9f14aa9 · report
get_parsing_accuracy murtyshikhar/pushdown-layers/eval_utils/eval_pushdown_model.py official repository ran no licence file found · pointer only · 45d4819a42863712 · report
logsumexp murtyshikhar/pushdown-layers/beam_search_util.py official repository ran fingerprinted no licence file found · pointer only · 6b331f505ce51944 · report
sinusoidal_pos_embedding MurtyShikhar/Pushdown-Layers/models/pushdown_transformer_lm.py official repository ran · honoured contract no licence file found · pointer only · f24ed9058bec8d35 · report
sinusoidal_pos_embedding murtyshikhar/pushdown-layers/layers/positional_encoding.py official repository ran no licence file found · pointer only · d6b9018a0880eafd · report
PushdownAttention MurtyShikhar/Pushdown-Layers/models/pushdown_transformer_lm.py official repository unverified no licence file found · pointer only · 040a0db1fa164ee2 · report
PushdownLM MurtyShikhar/Pushdown-Layers/models/pushdown_transformer_lm.py official repository unverified no licence file found · pointer only · 1d6a2fb2322500d7 · report
StackPredictor MurtyShikhar/Pushdown-Layers/models/pushdown_transformer_lm.py official repository unverified no licence file found · pointer only · ea75be5e2691ee1e · report
Transformer MurtyShikhar/Pushdown-Layers/models/pushdown_transformer_lm.py official repository unverified no licence file found · pointer only · e1e85555ec42de79 · report
TransformerEncoderLayer MurtyShikhar/Pushdown-Layers/models/pushdown_transformer_lm.py official repository unverified no licence file found · pointer only · cd05f27177c97848 · report
TransformerEncoderWithLayer MurtyShikhar/Pushdown-Layers/models/pushdown_transformer_lm.py official repository unverified no licence file found · pointer only · 5d6f6fc2cd657722 · report
TransformerEncoderWithLayer murtyshikhar/pushdown-layers/layers/transformer/transformer.py official repository unverified no licence file found · pointer only · 9f7833997a6a7918 · report
TransformerLM MurtyShikhar/Pushdown-Layers/models/pushdown_transformer_lm.py official repository unverified no licence file found · pointer only · 199613ff3592d354 · report
cross_entropy murtyshikhar/pushdown-layers/layers/cross_entropy_label_smoothing.py official repository unverified no licence file found · pointer only · de36bbda5931ac11 · report

Tasks

Text Classificationtext-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections