{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/diffusion-lm-improves-controllable-text","title":"Diffusion-LM Improves Controllable Text Generation","arxiv_id":"2205.14217","date":"2022-05-27","proceeding":null,"authors":["Xiang Lisa Li","John Thickstun","Ishaan Gulrajani","Percy Liang","Tatsunori B. Hashimoto"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2205.14217v1","url_pdf":"https://arxiv.org/pdf/2205.14217v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"diffusion-lm-improves-controllable-text","repo_url":"https://github.com/xiangli1999/diffusion-lm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.14217","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14217"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xiangli1999/diffusion-lm","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2,"ran":5,"ran_honours":2,"unverified":3},"by_repo_kind":{"official":{"samples":11,"ran":8,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"cfd76fd0d89574a4","entry":"approx_standard_normal_cdf","repo":"xiangli1999/diffusion-lm","repo_kind":"official","path":"improved-diffusion/improved_diffusion/losses.py","file_url":"https://github.com/xiangli1999/diffusion-lm/blob/HEAD/improved-diffusion/improved_diffusion/losses.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cfd76fd0d89574a4"}},{"code_sha256_prefix":"cd33283d615fb3d7","entry":"discretized_gaussian_log_likelihood","repo":"xiangli1999/diffusion-lm","repo_kind":"official","path":"improved-diffusion/improved_diffusion/losses.py","file_url":"https://github.com/xiangli1999/diffusion-lm/blob/HEAD/improved-diffusion/improved_diffusion/losses.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cd33283d615fb3d7"}},{"code_sha256_prefix":"bd70407415c5ed19","entry":"generate_samples","repo":"xiangli1999/diffusion-lm","repo_kind":"official","path":"improved-diffusion/control_gen/baseline_control.py","file_url":"https://github.com/xiangli1999/diffusion-lm/blob/HEAD/improved-diffusion/control_gen/baseline_control.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bd70407415c5ed19"}},{"code_sha256_prefix":"ee1169ece28e0d9d","entry":"levenshteinDistance","repo":"xiangli1999/diffusion-lm","repo_kind":"official","path":"improved-diffusion/control_gen/eval_control.py","file_url":"https://github.com/xiangli1999/diffusion-lm/blob/HEAD/improved-diffusion/control_gen/eval_control.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ee1169ece28e0d9d"}},{"code_sha256_prefix":"6690b1379e201b37","entry":"load_results_simple","repo":"xiangli1999/diffusion-lm","repo_kind":"official","path":"improved-diffusion/anlg_infill/mbr_eval.py","file_url":"https://github.com/xiangli1999/diffusion-lm/blob/HEAD/improved-diffusion/anlg_infill/mbr_eval.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6690b1379e201b37"}},{"code_sha256_prefix":"23e6db3ffd64425a","entry":"mbr","repo":"xiangli1999/diffusion-lm","repo_kind":"official","path":"improved-diffusion/anlg_infill/mbr_eval.py","file_url":"https://github.com/xiangli1999/diffusion-lm/blob/HEAD/improved-diffusion/anlg_infill/mbr_eval.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"23e6db3ffd64425a"}},{"code_sha256_prefix":"cf2798b666b231ca","entry":"normal_kl","repo":"xiangli1999/diffusion-lm","repo_kind":"official","path":"improved-diffusion/improved_diffusion/losses.py","file_url":"https://github.com/xiangli1999/diffusion-lm/blob/HEAD/improved-diffusion/improved_diffusion/losses.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cf2798b666b231ca"}},{"code_sha256_prefix":"76313eaf1a6e8f2a","entry":"parse_resume_step_from_filename","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"76313eaf1a6e8f2a"}},{"code_sha256_prefix":"8fc7161a00ae39b0","entry":"remove_leaves","repo":"xiangli1999/diffusion-lm","repo_kind":"official","path":"improved-diffusion/control_gen/baseline_control.py","file_url":"https://github.com/xiangli1999/diffusion-lm/blob/HEAD/improved-diffusion/control_gen/baseline_control.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8fc7161a00ae39b0"}},{"code_sha256_prefix":"cc6bf6f3b1388227","entry":"generate_samples_from_scratch","repo":"xiangli1999/diffusion-lm","repo_kind":"official","path":"improved-diffusion/control_gen/baseline_control.py","file_url":"https://github.com/xiangli1999/diffusion-lm/blob/HEAD/improved-diffusion/control_gen/baseline_control.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cc6bf6f3b1388227"}},{"code_sha256_prefix":"a863803cdd5f3ce6","entry":"make_master_params","repo":"xiangli1999/diffusion-lm","repo_kind":"official","path":"improved-diffusion/improved_diffusion/fp16_util.py","file_url":"https://github.com/xiangli1999/diffusion-lm/blob/HEAD/improved-diffusion/improved_diffusion/fp16_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a863803cdd5f3ce6"}},{"code_sha256_prefix":"30e43bcf12d042b0","entry":"unflatten_master_params","repo":"xiangli1999/diffusion-lm","repo_kind":"official","path":"improved-diffusion/improved_diffusion/fp16_util.py","file_url":"https://github.com/xiangli1999/diffusion-lm/blob/HEAD/improved-diffusion/improved_diffusion/fp16_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"30e43bcf12d042b0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}