SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.09254 · NeurIPS · 2024

Selective Generation for Controllable Language Models

Sangdon Park, Minjae Lee, Kyungmin Kim, Taesoo Kim

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 2 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/2307.09254.json · badge: /api/ran/2307.09254.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
ml-postech/selective-generation canonical (classifier label)
classifier basis: census
3 ran · 2 no recorded run
FunctionStatusWhere it lives
dist_mah Ran
ran; our contract draft was wrong, not the code
ml-postech/selective-generation/models/util.py
pointer only (licence: NONE) · get_code("96ffcdf59ac74f29")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ml-postech/selective-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.

neg_log_prob Ran
ran; our contract draft was wrong, not the code
ml-postech/selective-generation/models/util.py
pointer only (licence: NONE) · get_code("b99312b246905851")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ml-postech/selective-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.

pad_left Ran
ran, honoured the contract we drafted
ml-postech/selective-generation/models/util.py
pointer only (licence: NONE) · get_code("b53be62f5c72b88a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ml-postech/selective-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.

get_completion Not yet run
unverified (harvested, no recorded run)
ml-postech/selective-generation/generation/api_gen_answer.py
pointer only (licence: NONE) · get_code("c61efb7cefa9daf5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ml-postech/selective-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.

get_completion Not yet run
unverified (harvested, no recorded run)
ml-postech/selective-generation/generation/api_gen_samples.py
pointer only (licence: NONE) · get_code("7e05f2471cc1bc8c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ml-postech/selective-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.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 5 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

Trustworthiness of generative language models (GLMs) is crucial in their deployment to critical decision making systems. Hence, certified risk control methods such as selective prediction and conformal prediction have been applied to mitigating the hallucination problem in various supervised downstream tasks. However, the lack of appropriate correctness metric hinders applying such principled methods to language generation tasks. In this paper, we circumvent this problem by leveraging the concept of textual entailment to evaluate the correctness of the generated sequence, and propose two selective generation algorithms which control the false discovery rate with respect to the textual entailment relation (FDR-E) with a theoretical guarantee: SGen Sup and SGen Semi . SGen Sup , a direct modification of the selective prediction, is a supervised learning algorithm which exploits entailment-labeled data, annotated by humans. Since human annotation is costly, we further propose a semisupervised version, SGen Semi , which fully utilizes the unlabeled data by pseudolabeling, leveraging an entailment set function learned via conformal prediction. Furthermore, SGen Semi enables to use more general class of selection functions, neuro-selection functions, and provides users with an optimal selection function class given multiple candidates. Finally, we demonstrate the efficacy of the SGen family in achieving a desired FDR-E level with comparable selection efficiency to those from baselines on both open and closed source GLMs. Code and datasets are provided at https://github.com/ml-postech/selective-generation.

For agents

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

get_harvested_code_for_paper("2307.09254")
get_code_for_paper("2307.09254")
have("2307.09254")

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

curl https://syntology.ai/api/ran/2307.09254.json

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

[![Syntology run record](https://syntology.ai/api/ran/2307.09254.svg)](https://syntology.ai/paper/2307.09254)

Connect an agent — have() is free.