{"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/fudge-controlled-text-generation-with-future","title":"FUDGE: Controlled Text Generation With Future Discriminators","arxiv_id":"2104.05218","date":"2021-04-12","proceeding":"NAACL 2021 4","authors":["Kevin Yang","Dan Klein"],"abstract":"We propose Future Discriminators for Generation (FUDGE), a flexible and modular method for controlled text generation. Given a pre-existing model G for generating text from a distribution of interest, FUDGE enables conditioning on a desired attribute a (for example, formality) while requiring access only to G's output logits. FUDGE learns an attribute predictor operating on a partial sequence, and uses this predictor's outputs to adjust G's original probabilities. We show that FUDGE models terms corresponding to a Bayesian decomposition of the conditional distribution of G given attribute a. Moreover, FUDGE can easily compose predictors for multiple desired attributes. We evaluate FUDGE on three tasks -- couplet completion in poetry, topic control in language generation, and formality change in machine translation -- and observe gains in all three tasks.","url_abs":"https://arxiv.org/abs/2104.05218v2","url_pdf":"https://arxiv.org/pdf/2104.05218v2.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":"fudge-controlled-text-generation-with-future","repo_url":"https://github.com/yangkevin2/naacl-2021-fudge-controlled-generation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"fudge-controlled-text-generation-with-future","repo_url":"https://github.com/mtsomethree/constrdecoding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"fudge-controlled-text-generation-with-future","repo_url":"https://github.com/nlp-detoxify/fudge-controlled-generation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2104.05218","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.05218"}},"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/mtsomethree/constrdecoding","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yangkevin2/naacl-2021-fudge-controlled-generation","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nlp-detoxify/fudge-controlled-generation","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"samples":3,"ran":1,"repositories":2}},"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":2,"samples":[{"code_sha256_prefix":"7370b219ce77c0b4","entry":"pad_mask","repo":"nlp-detoxify/fudge-controlled-generation","repo_kind":"listed","path":"model.py","file_url":"https://github.com/nlp-detoxify/fudge-controlled-generation/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7370b219ce77c0b4"}},{"code_sha256_prefix":"793a9efe909bef30","entry":"FUDGEModel","repo":"mtsomethree/constrdecoding","repo_kind":"listed","path":"neural_constr.py","file_url":"https://github.com/mtsomethree/constrdecoding/blob/HEAD/neural_constr.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"793a9efe909bef30"}},{"code_sha256_prefix":"e20c3ff4117c8d21","entry":"Model","repo":"nlp-detoxify/fudge-controlled-generation","repo_kind":"listed","path":"model.py","file_url":"https://github.com/nlp-detoxify/fudge-controlled-generation/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e20c3ff4117c8d21"}},{"code_sha256_prefix":"d725c1f76efbd9f4","entry":"_generate_no_beam_search","repo":"yangkevin2/naacl-2021-fudge-controlled-generation","repo_kind":"official","path":"predict_formality.py","file_url":"https://github.com/yangkevin2/naacl-2021-fudge-controlled-generation/blob/HEAD/predict_formality.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d725c1f76efbd9f4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}