Papers › Diffusion-LM Improves Controllable Text Generation

Diffusion-LM Improves Controllable Text Generation

27 May 2022arXiv:2205.14217archive 2025-07-28

Xiang Lisa Li, John Thickstun, Ishaan Gulrajani, Percy Liang, Tatsunori B. Hashimoto

Controlling the behavior of language models (LMs) without re-training is a major open problem in natural language generation. While recent works have demonstrated successes on controlling simple sentence attributes (e.g., sentiment), there has been little progress on complex, fine-grained controls (e.g., syntactic structure). To address this challenge, we develop a new non-autoregressive language model based on continuous diffusions that we call Diffusion-LM. Building upon the recent successes of diffusion models in continuous domains, Diffusion-LM iteratively denoises a sequence of Gaussian vectors into word vectors, yielding a sequence of intermediate latent variables. The continuous, hierarchical nature of these intermediate variables enables a simple gradient-based algorithm to perform complex, controllable generation tasks. We demonstrate successful control of Diffusion-LM for six challenging fine-grained control tasks, significantly outperforming prior work.

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 12 code samples: 11 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 12: 11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 10 ran (4 with no instrument failure; 6 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 11 samples that ran have no recorded date.

xiangli1999/diffusion-lm officialmentioned in papermentioned on GitHubjaxApache-2.0Syntology: 11 samples, 10 ran (6 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

12 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 6 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.

3ran · honoured contract
6ran · our draft was wrong
2ran
1unverified

Licence: 12 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. For 11 of them, 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 xiangli1999/diffusion-lm. 1 sample is listed last, in a group without a repository. “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.

xiangli1999/diffusion-lm official repository 11 samples, 10 ran (6 instrument-failed) · 1 unverified
approx_standard_normal_cdf in 150 papers
census: 4 implementations from 14 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
improved-diffusion/improved_diffusion/losses.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · cfd76fd0d89574a4 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
discretized_gaussian_log_likelihood in 124 papers
census: 6 implementations from 10 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32
improved-diffusion/improved_diffusion/losses.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · cd33283d615fb3d7 · report fixture: signature x:Tensor/2/float, means:Tensor/2/float, log_scales:Tensor/2/float · returned Tensor · level recorded, date not recorded
generate_samples in 16 papers improved-diffusion/control_gen/baseline_control.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · bd70407415c5ed19 · report fixture: signature args:Args/0/?, prompt:Tensor/2/int, model:callable/0/?, tokenizer:MinimalTokenizer/0/? · returned list · level recorded 2026-09-24
levenshteinDistance improved-diffusion/control_gen/eval_control.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · ee1169ece28e0d9d · report fixture: signature s1:str/0/str, s2:str/0/str · returned int · level recorded 2026-09-24
load_results_simple improved-diffusion/anlg_infill/mbr_eval.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 6690b1379e201b37 · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-24
make_master_params in 90 papers improved-diffusion/improved_diffusion/fp16_util.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · a863803cdd5f3ce6 · report fixture: signature model_params:list/1/Tensor · returned list · level recorded 2026-09-25
mbr improved-diffusion/anlg_infill/mbr_eval.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 23e6db3ffd64425a · report fixture: signature result_lst:list/1/ndarray, total_len:int/0/int, sample_size:int/0/int, utility:callable/0/? · returned list · level recorded 2026-09-24
normal_kl in 188 papers
census: 14 implementations from 24 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32 · arg 4: rank 2, kind float, dtype float32
improved-diffusion/improved_diffusion/losses.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · cf2798b666b231ca · report fixture: signature mean1:Tensor/2/float, logvar1:Tensor/2/float, mean2:Tensor/2/float, logvar2:Tensor/2/float · returned Tensor · level recorded 2026-09-22
remove_leaves improved-diffusion/control_gen/baseline_control.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 8fc7161a00ae39b0 · report fixture: signature tree_:Tree/1/Tree · returned Tree · level recorded 2026-09-24
unflatten_master_params in 90 papers improved-diffusion/improved_diffusion/fp16_util.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 30e43bcf12d042b0 · report fixture: signature model_params:list/1/Tensor, master_params:list/1/Tensor · returned tuple · level recorded 2026-09-25
generate_samples_from_scratch improved-diffusion/control_gen/baseline_control.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · cc6bf6f3b1388227 · report
Repository not located 1 sample, 1 ran (0 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
parse_resume_step_from_filename in 19 papers repository not located ran · honoured contract fingerprinted licence of this copy not recorded · 76313eaf1a6e8f2a · report fixture: signature filename:str/0/str · returned int · level recorded, date not recorded

Tasks

Language ModelingLanguage ModellingSentenceText Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

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