Papers › Diffusion Guided Language Modeling

Diffusion Guided Language Modeling

8 Aug 2024arXiv:2408.04220archive 2025-07-28

Justin Lovelace, Varsha Kishore, YiWei Chen, Kilian Q. Weinberger

Current language models demonstrate remarkable proficiency in text generation. However, for many applications it is desirable to control attributes, such as sentiment, or toxicity, of the generated language -- ideally tailored towards each specific use case and target audience. For auto-regressive language models, existing guidance methods are prone to decoding errors that cascade during generation and degrade performance. In contrast, text diffusion models can easily be guided with, for example, a simple linear sentiment classifier -- however they do suffer from significantly higher perplexity than auto-regressive alternatives. In this paper we use a guided diffusion model to produce a latent proposal that steers an auto-regressive language model to generate text with desired properties. Our model inherits the unmatched fluency of the auto-regressive approach and the plug-and-play flexibility of diffusion. We show that it outperforms previous plug-and-play guidance methods across a wide range of benchmark data sets. Further, controlling a new attribute in our framework is reduced to training a single logistic regression classifier.

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 15 code samples harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 2 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 14 ran (9 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 14 samples that ran have no recorded date.

justinlovelace/diffusion-guided-lm officialmentioned in paperMITSyntology: 15 samples, 14 ran (5 instrument-failed) · 1 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

15 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 2 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
2ran · violated contract
5ran · our draft was wrong
6ran
1unverified

Licence: 1 of the 15 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from justinlovelace/diffusion-guided-lm. “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.

justinlovelace/diffusion-guided-lm official repository 15 samples, 14 ran (5 instrument-failed) · 1 unverified
convert_epsweight_to_vweight diffusion/loss_weighting.py ran · our draft was wrong fingerprinted MIT (permissive) · 5668b62a6e4b01bb · report fixture: signature eps_weight:Tensor/2/float, gamma:Tensor/2/float · returned Tensor · level recorded 2026-09-26
convert_epsweight_to_xweight diffusion/loss_weighting.py ran · our draft was wrong fingerprinted MIT (permissive) · 0dacf1cd4472c7f4 · report fixture: signature eps_weight:Tensor/2/float, gamma:Tensor/2/float · returned Tensor · level recorded 2026-09-24
convert_vweight_to_epsweight diffusion/loss_weighting.py ran MIT (permissive) · 44964eb2373817aa · report fixture: signature v_weight:Tensor/2/float, gamma:Tensor/0/float, monotonic:bool/0/bool · returned Tensor · level recorded 2026-09-24
cosine_schedule in 14 papers diffusion/noise_schedule.py ran · our draft was wrong MIT (permissive) · 1d0ae3a51abe89ef · report fixture: signature t:Tensor/1/float, start:float/0/float, end:float/0/float, tau:float/0/float, clip_min:float/0/float · returned Tensor · level recorded 2026-09-24
create_causal_mask in 6 papers models/modules/blocks.py ran MIT (permissive) · 8d1a3ec5840c93c9 · report fixture: signature i:int/0/int, j:int/0/int, device:device/0/? · returned Tensor · level recorded 2026-09-26
distinctness evaluation/wrappers.py ran · honoured contract MIT (permissive) · 0dd9d3962e8f433d · report fixture: signature generations:list/1/str · returned tuple · level recorded 2026-09-24
exists in 528 papers
census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
models/diff_gpt.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · aa5486a3650902d8 · report fixture: signature val:Tensor/1/int · returned bool · level recorded, date not recorded
exists in 528 papers
census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
diffusion/trainer.py ran · violated contract MIT (permissive) · 608e364a9d2376a3 · report fixture: signature x:Tensor/1/int · returned bool · level recorded, date not recorded
log in 61 papers
census: 10 implementations from 16 papers, 7 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
diffusion/noise_schedule.py ran · our draft was wrong fingerprinted MIT (permissive) · d93be7ef30d67f1e · report fixture: signature t:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22
log_snr_to_alpha2 diffusion/noise_schedule.py ran · our draft was wrong fingerprinted MIT (permissive) · 464efe215a8b78a6 · report fixture: signature log_snr:Tensor/2/float · returned Tensor · level recorded 2026-09-24
predict_noise_from_start diffusion/diff_utils.py ran MIT (permissive) · c2cdff12cab93636 · report fixture: signature z_t:Tensor/2/float, x0:Tensor/2/float, alpha2:Tensor/1/float · returned Tensor · level recorded 2026-09-24
predict_start_from_noise diffusion/diff_utils.py ran fingerprinted MIT (permissive) · 669feaf2125330e9 · report fixture: signature z_t:Tensor/2/float, noise:Tensor/2/float, alpha2:Tensor/0/float · returned Tensor · level recorded 2026-09-24
predict_start_from_v diffusion/diff_utils.py ran fingerprinted MIT (permissive) · 080807179fd2bc7d · report fixture: signature z_t:Tensor/2/float, v:Tensor/2/float, alpha2:Tensor/0/float · returned Tensor · level recorded 2026-09-24
variance_preserving_map models/diff_gpt.py ran MIT (permissive) · 95df472b7c0a3c59 · report fixture: signature x:Tensor/2/float, alpha2:Tensor/0/float, eps:Tensor/2/float · returned Tensor · level recorded 2026-09-24
compute_olmo_perplexity evaluation/wrappers.py unverified MIT (permissive) · fdee5b2a7081c1df · report

Tasks

AttributeLanguage ModelingLanguage ModellingText Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DiffusionLogistic Regression

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