SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2510.18232 · ICML · 2025

ACTG-ARL: Differentially Private Conditional Text Generation with RL-Boosted Control

Han Zhao, Peter Kairouz, Shanshan Wu, Zheng Xu, Da Yu, Yuzheng Hu, Ryan Mckenna

arXiv · PDF · Open in the Atlas

Code that ran

10 of 10 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 7 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2510.18232.json · badge: /api/ran/2510.18232.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
tanyuqian/synthetic-private-data canonical (classifier label)
classifier basis: census
6 ran · 0 no recorded run
actg-arl/ACTG-ARL canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
collate_fn Ran
ran; our contract draft was wrong, not the code
tanyuqian/synthetic-private-data/finetune.py
pointer only (licence: NONE) · get_code("52b43047818c6eae")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tanyuqian/synthetic-private-data 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.

exponential_mechanism Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
actg-arl/ACTG-ARL/AIM/common.py
pointer only (licence: NONE) · get_code("58907038637470a3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, actg-arl/ACTG-ARL 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.

get_gen_dataset Ran
ran; our contract draft was wrong, not the code
tanyuqian/synthetic-private-data/data_utils.py
pointer only (licence: NONE) · get_code("bf86928de402abfa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tanyuqian/synthetic-private-data 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.

get_src Ran
ran; our contract draft was wrong, not the code
tanyuqian/synthetic-private-data/finetune.py
pointer only (licence: NONE) · get_code("1bc4b3de0f3bd617")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tanyuqian/synthetic-private-data 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.

get_topic_keywords Ran
ran; our contract draft was wrong, not the code
tanyuqian/synthetic-private-data/data_utils.py
pointer only (licence: NONE) · get_code("065e099344411cf0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tanyuqian/synthetic-private-data 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.

loss_fn Ran
ran; our contract draft was wrong, not the code
tanyuqian/synthetic-private-data/finetune.py
pointer only (licence: NONE) · get_code("9de7ddca8f9bbc3c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tanyuqian/synthetic-private-data 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.

pred_fn Ran
ran; our contract draft was wrong, not the code
tanyuqian/synthetic-private-data/evaluate_next_word_prediction.py
pointer only (licence: NONE) · get_code("80242254dcc941ad")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tanyuqian/synthetic-private-data 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.

zcdp_delta Ran
ran, honoured the contract we drafted
actg-arl/ACTG-ARL/AIM/accounting.py
pointer only (licence: NONE) · get_code("4a9cfab866ddf4ff")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, actg-arl/ACTG-ARL 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.

zcdp_eps Ran
ran, honoured the contract we drafted
actg-arl/ACTG-ARL/AIM/accounting.py
pointer only (licence: NONE) · get_code("a53fe06a625ac0cc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, actg-arl/ACTG-ARL 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.

zcdp_rho Ran
ran, honoured the contract we drafted
actg-arl/ACTG-ARL/AIM/accounting.py
pointer only (licence: NONE) · get_code("5049d40dc24ec5a2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, actg-arl/ACTG-ARL 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.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 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 10 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

Generating high-quality synthetic text under differential privacy (DP) is critical for training and evaluating language models without compromising user privacy. Prior work on synthesizing DP datasets often fail to preserve key statistical attributes, suffer utility loss from the noise required by DP, and lack fine-grained control over generation. To address these challenges, we make two contributions. First, we introduce a hierarchical framework that decomposes DP synthetic text generation into two subtasks: feature learning and conditional text generation. This design explicitly incorporates learned features into the generation process and simplifies the end-to-end synthesis task. Through systematic ablations, we identify the most effective configuration: a rich tabular schema as feature, a DP tabular synthesizer, and a DP fine-tuned conditional generator, which we term ACTG (Attribute-Conditioned Text Generation). Second, we propose Anchored RL (ARL), a post-training method that improves the instruction-following ability of ACTG for conditional generation. ARL combines RL to boost control with an SFT anchor on best-of-N data to prevent reward hacking. Together, these components form our end-to-end algorithm ACTG-ARL, which advances both the quality of DP synthetic text (+20% MAUVE over prior work) and the control of the conditional generator under strong privacy guarantees. Our code is at https: //github.com/actg-arl/ACTG-ARL.

For agents

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

get_harvested_code_for_paper("2510.18232")
get_code_for_paper("2510.18232")
have("2510.18232")

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

curl https://syntology.ai/api/ran/2510.18232.json

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

[![Syntology run record](https://syntology.ai/api/ran/2510.18232.svg)](https://syntology.ai/paper/2510.18232)

Connect an agent — have() is free.