Papers › SpikingBERT: Distilling BERT to Train Spiking Language Models Using Implicit Differentiation

SpikingBERT: Distilling BERT to Train Spiking Language Models Using Implicit Differentiation

21 Aug 2023arXiv:2308.10873archive 2025-07-28

Malyaban Bal, Abhronil Sengupta

Large language Models (LLMs), though growing exceedingly powerful, comprises of orders of magnitude less neurons and synapses than the human brain. However, it requires significantly more power/energy to operate. In this work, we propose a novel bio-inspired spiking language model (LM) which aims to reduce the computational cost of conventional LMs by drawing motivation from the synaptic information flow in the brain. In this paper, we demonstrate a framework that leverages the average spiking rate of neurons at equilibrium to train a neuromorphic spiking LM using implicit differentiation technique, thereby overcoming the non-differentiability problem of spiking neural network (SNN) based algorithms without using any type of surrogate gradient. The steady-state convergence of the spiking neurons also allows us to design a spiking attention mechanism, which is critical in developing a scalable spiking LM. Moreover, the convergence of average spiking rate of neurons at equilibrium is utilized to develop a novel ANN-SNN knowledge distillation based technique wherein we use a pre-trained BERT model as "teacher" to train our "student" spiking architecture. While the primary architecture proposed in this paper is motivated by BERT, the technique can be potentially extended to different kinds of LLMs. Our work is the first one to demonstrate the performance of an operational spiking LM architecture on multiple different tasks in the GLUE benchmark.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 17 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 13 ran (8 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 4 of the 13 samples that ran have no recorded date.

neurocomplab-psu/spikingbert officialmentioned in papermentioned on GitHubpytorchSyntology: 17 samples, 13 ran (5 instrument-failed) · 4 unverified 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

17 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
4ran · our draft was wrong
1ran; the contract check could not run
6ran
4unverified

Licence: 17 of the 17 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 neurocomplab-psu/spikingbert. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

neurocomplab-psu/spikingbert official repository 17 samples, 13 ran (5 instrument-failed) · 4 unverified
swish in 258 papers
census: 14 implementations from 37 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
transformer/modeling.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 0f786c407fb1ee4c · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
acc_and_f1 in 39 papers spiking_bert_task_distill.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic no licence file found · pointer only · cac113ca87b9d9f3 · report fixture: signature preds:ndarray/1/int, labels:ndarray/1/int · returned dict · level recorded 2026-09-22
compute_spectral_norm implicit_bert/modules/optimizations.py ran fingerprinted no licence file found · pointer only · 3dce841898f3d634 · report fixture: signature weight_mat:Tensor/2/float, iterations:int/0/int · returned Tensor · level recorded 2026-09-24
convert_example_to_features in 10 papers spiking_bert_general_distill.py ran no licence file found · pointer only · f2f5b170e5141470 · report fixture: signature example:dict/0/?, tokenizer:MinimalTokenizer/0/?, max_seq_length:int/0/int · returned InputFeatures · level recorded 2026-09-24
convert_examples_to_features in 134 papers spiking_bert_task_distill.py ran no licence file found · pointer only · ca4a60dd9a4dee68 · report fixture: signature examples:list/1/MockExample, label_list:list/1/str, max_seq_length:int/0/int, tokenizer:MockTokenizer/0/?, output_mode:str/0/str, eval:bool/0/bool · returned list · level recorded 2026-09-24
create_instances_from_document in 5 papers preprocess_training_data.py ran no licence file found · pointer only · 6376a70f6dfc27d6 · report fixture: signature doc_database:DocDatabase/0/?, doc_idx:int/0/int, max_seq_length:int/0/int, short_seq_prob:float/0/float, masked_lm_prob:float/0/float, max_predictions_per_seq:int/0/int, whole_word_mask:bool/0/bool, vocab_list:list/1/str, bi_text:bool/0/bool · returned list · level recorded 2026-09-24
create_masked_lm_predictions in 5 papers preprocess_training_data.py ran no licence file found · pointer only · c1f215df4049f030 · report fixture: signature tokens:list/1/str, masked_lm_prob:float/0/float, max_predictions_per_seq:int/0/int, whole_word_mask:bool/0/bool, vocab_list:list/1/str · returned tuple · level recorded 2026-09-24
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
transformer/modeling.py ran · honoured contract fingerprinted no licence file found · pointer only · fdc64f4c72036ae4 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
get_tasks in 21 papers download_glue_data.py ran · our draft was wrong no licence file found · pointer only · 3caf26b311c98658 · report fixture: signature task_names:str/0/str · returned list · level recorded 2026-09-22
line_search in 14 papers implicit_bert/modules/broyden.py ran · our draft was wrong no licence file found · pointer only · cf5710371bcfb0ab · report fixture: signature update:Tensor/1/float, x0:Tensor/1/float, g0:Tensor/1/float, g:callable/0/?, nstep:int/0/int, on:bool/0/bool · returned tuple · level recorded, date not recorded
rmatvec in 8 papers implicit_bert/modules/broyden.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 968a8f446ad3c5b1 · report fixture: signature part_Us:Tensor/4/float, part_VTs:Tensor/4/float, x:Tensor/3/float · returned Tensor · level recorded, date not recorded
scalar_search_armijo in 11 papers implicit_bert/modules/broyden.py ran · honoured contract no licence file found · pointer only · b2b5022f654ee4d3 · report fixture: signature phi:callable/0/?, phi0:float/0/float, derphi0:float/0/float, c1:float/0/float, alpha0:float/0/float, amin:float/0/float · returned tuple · level recorded, date not recorded
weight_norm in 14 papers implicit_bert/modules/optimizations.py ran no licence file found · pointer only · f0fda38cdd52aefb · report fixture: signature module:callable/0/?, names:list/1/str, dim:int/0/int · returned tuple · level recorded 2026-09-24
create_training_file preprocess_training_data.py unverified no licence file found · pointer only · a8d00bf9b456b3f6 · report
load_tf_weights_in_bert in 135 papers transformer/modeling.py unverified no licence file found · pointer only · 0453ed29d1aecc4c · report
simple_accuracy in 66 papers spiking_bert_task_distill.py unverified no licence file found · pointer only · 3c241ecfe3749a6d · report
weight_spectral_norm implicit_bert/modules/optimizations.py unverified no licence file found · pointer only · e2f5c84554d935f4 · report

Tasks

Knowledge DistillationLanguage Modelling

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutKnowledge DistillationLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight DecayWordPiece

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