SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.07401 · 2023

On Diversified Preferences of Large Language Model Alignment

arXiv · PDF · Open in the Atlas

Code that ran

6 of 9 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; 6 failures 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/2312.07401.json · badge: /api/ran/2312.07401.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
dunzeng/more canonical (classifier label)
classifier basis: census
6 ran · 3 no recorded run
FunctionStatusWhere it lives
get_data_iter Ran
ran; our contract draft was wrong, not the code
dunzeng/more/reward_datasets.py
pointer only (licence: NONE) · get_code("520e1c7389395ede")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dunzeng/more 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.

gpt_winer Ran
ran; our contract draft was wrong, not the code
dunzeng/more/evaluation_utils.py
pointer only (licence: NONE) · get_code("f43d68f055c6659c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dunzeng/more 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.

gradient_normalizers Ran
ran; our contract draft was wrong, not the code
dunzeng/more/min_norm_solvers.py
pointer only (licence: NONE) · get_code("1b7ba4d146c226aa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dunzeng/more 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.

load_dataset Ran
ran; our contract draft was wrong, not the code
dunzeng/more/reward_model_inference.py
pointer only (licence: NONE) · get_code("53aceea1ad75f96e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dunzeng/more 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.

more_data_collator_without_resampling Ran
ran; our contract draft was wrong, not the code
dunzeng/more/reward_datasets.py
pointer only (licence: NONE) · get_code("ec5cde88ee0532ee")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dunzeng/more 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.

reward_data_collator Ran
ran; our contract draft was wrong, not the code
dunzeng/more/reward_datasets.py
pointer only (licence: NONE) · get_code("5b32b7c64711b73b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dunzeng/more 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.

compute_ppl Not yet run
unverified (harvested, no recorded run)
dunzeng/more/evaluation_utils.py
pointer only (licence: NONE) · get_code("bd566700507d4d13")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dunzeng/more 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.

dialog_to_llama_tokens Not yet run
unverified (harvested, no recorded run)
dunzeng/more/llm_inferencing.py
pointer only (licence: NONE) · get_code("4cc0a4e7f078667f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dunzeng/more 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.

hh_to_dialog Not yet run
unverified (harvested, no recorded run)
dunzeng/more/llm_inferencing.py
pointer only (licence: NONE) · get_code("9816d50d6a55e67e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dunzeng/more 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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 9 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

Aligning large language models (LLMs) with human preferences has been recognized as the key to improving LLMs' interaction quality. However, in this pluralistic world, human preferences can be diversified due to annotators' different tastes, which hinders the effectiveness of LLM alignment methods. This paper presents the first quantitative analysis of the experimental scaling law for reward models with varying sizes, from 1.3 billion to 7 billion parameters, trained with human feedback exhibiting diverse preferences. Our analysis reveals that the impact of diversified human preferences depends on both model size and data size. Larger models with sufficient capacity mitigate the negative effects of diverse preferences, while smaller models struggle to accommodate them. To mitigate the impact of diverse preferences, we introduce a new metric, Expected Calibration Error (ECE), to evaluate RMs and show their obvious positive correlation with the alignment performance of LLMs. Furthermore, we propose a Multi-Objective Reward learning method (MORE) to enhance the calibration performance of RMs on shared preferences. Through experiments on four models and five human preference datasets, we find the calibration error can be adopted as a key metric for evaluating RMs and MORE can obtain superior alignment performance.

For agents

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

get_harvested_code_for_paper("2312.07401")
get_code_for_paper("2312.07401")
have("2312.07401")

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

curl https://syntology.ai/api/ran/2312.07401.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.07401.svg)](https://syntology.ai/paper/2312.07401)

Connect an agent — have() is free.