SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.05218 · NAACL · 2021

FUDGE: Controlled Text Generation With Future Discriminators

Dan Klein, Kevin Yang

arXiv · PDF · Open in the Atlas

Code that ran

1 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2104.05218.json · badge: /api/ran/2104.05218.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
nlp-detoxify/fudge-controlled-generation community
Papers with Code archive
1 ran · 1 no recorded run
mtsomethree/constrdecoding community
Papers with Code archive
0 ran · 1 no recorded run
yangkevin2/naacl-2021-fudge-controlled-generation marked official in Papers with Code
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
pad_mask Ran
ran; our contract draft was wrong, not the code
nlp-detoxify/fudge-controlled-generation/model.py
pointer only (licence: NONE) · get_code("7370b219ce77c0b4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nlp-detoxify/fudge-controlled-generation when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

FUDGEModel Not yet run
unverified (harvested, no recorded run)
mtsomethree/constrdecoding/neural_constr.py
code served (permissive licence) · get_code("793a9efe909bef30")
How it ran

no invocation recorded.

Model Not yet run
unverified (harvested, no recorded run)
nlp-detoxify/fudge-controlled-generation/model.py
pointer only (licence: NONE) · get_code("e20c3ff4117c8d21")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nlp-detoxify/fudge-controlled-generation when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

_generate_no_beam_search Not yet run
unverified (harvested, no recorded run)
yangkevin2/naacl-2021-fudge-controlled-generation/predict_formality.py
code served (permissive licence) · get_code("d725c1f76efbd9f4")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We propose Future Discriminators for Generation (FUDGE), a flexible and modular method for controlled text generation. Given a preexisting 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. Elizabeth Salesky, Matthias Sperber, and Alex Waibel. 2019. Fluent translations from disfluent speech in end-to-end speech translation. arXiv preprint arXiv:1906.00556. Abigail See, Peter J Liu, and Christopher D Manning. 2017. Get to the point: Summarization with pointer-generator networks. arXiv preprint arXiv:1704.04368. Abigail See, Stephen Roller, Douwe Kiela, and Jason Weston. 2019. What makes a good conversation? how controllable attributes affect human judgments. arXiv preprint arXiv:1902.08654.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2104.05218")
get_code_for_paper("2104.05218")
have("2104.05218")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2104.05218.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2104.05218.svg)](https://syntology.ai/paper/2104.05218)

Connect an agent — have() is free.