SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.10023 · NeurIPS · 2024

Deep Bayesian Active Learning for Preference Modeling in Large Language Models

Yarin Gal, Panagiotis Tigas, Alessandro Abate, Luckeciano Melo

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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 2 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/2406.10023.json · badge: /api/ran/2406.10023.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
luckeciano/BAL-PM canonical (classifier label)
classifier basis: census
3 ran · 2 no recorded run
FunctionStatusWhere it lives
compute_entropy_stats Ran
ran, honoured the contract we drafted
luckeciano/BAL-PM/uqlrm/generate_sentence_entropies.py
pointer only (licence: NONE) · get_code("70c52a81fae4c360")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, luckeciano/BAL-PM 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_activation_function Ran
ran; our contract draft was wrong, not the code
luckeciano/BAL-PM/uqlrm/modules/mc_dropout_reward_mlp.py
pointer only (licence: NONE); the stored copy get_code serves, from luckeciano/TD-VCL, is pointer only (licence: NONE) · get_code("cbb32079ed8b32f4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, luckeciano/BAL-PM 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_entropies Ran
ran, honoured the contract we drafted
luckeciano/BAL-PM/uqlrm/generate_sentence_entropies.py
pointer only (licence: NONE) · get_code("ffaae593b5909928")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, luckeciano/BAL-PM 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.

DropoutLinear_forward Not yet run
unverified (harvested, no recorded run)
luckeciano/BAL-PM/uqlrm/modules/mc_dropout_reward_mlp.py
pointer only (licence: NONE) · get_code("127f543d1364a73b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, luckeciano/BAL-PM 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.

create_datasets Not yet run
unverified (harvested, no recorded run)
luckeciano/BAL-PM/uqlrm/adapter_ensemble_reward_training.py
pointer only (licence: NONE) · get_code("7a7d51a3dd2dbbc7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, luckeciano/BAL-PM 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, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 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.

FunctionAlso present inEarliest-datedOthers named
get_activation_function 1 other paper
1 later
2410.07812 (2024-10)
Temporal-Difference Variational Continual Learning

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

Leveraging human preferences for steering the behavior of Large Language Models (LLMs) has demonstrated notable success in recent years. Nonetheless, data selection and labeling are still a bottleneck for these systems, particularly at large scale. Hence, selecting the most informative points for acquiring human feedback may considerably reduce the cost of preference labeling and unleash the further development of LLMs. Bayesian Active Learning provides a principled framework for addressing this challenge and has demonstrated remarkable success in diverse settings. However, previous attempts to employ it for Preference Modeling did not meet such expectations. In this work, we identify that naive epistemic uncertainty estimation leads to the acquisition of redundant samples. We address this by proposing the Bayesian Active Learner for Preference Modeling (BAL-PM), a novel stochastic acquisition policy that not only targets points of high epistemic uncertainty according to the preference model but also seeks to maximize the entropy of the acquired prompt distribution in the feature space spanned by the employed LLM. Notably, our experiments demonstrate that BAL-PM requires 33% to 68% fewer preference labels in two popular human preference datasets and exceeds previous stochastic Bayesian acquisition policies.

For agents

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

get_harvested_code_for_paper("2406.10023")
get_code_for_paper("2406.10023")
have("2406.10023")

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

curl https://syntology.ai/api/ran/2406.10023.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.10023.svg)](https://syntology.ai/paper/2406.10023)

Connect an agent — have() is free.