SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.14872 · 2024

How to Evaluate Reward Models for RLHF

arXiv · PDF · Open in the Atlas

Code that ran

7 of 7 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, 1 violated it and 1 has no contract verdict; 4 failures of our instrument; 0 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/2410.14872.json · badge: /api/ran/2410.14872.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
lmarena/ppe canonical (classifier label)
classifier basis: census
7 ran · 0 no recorded run
FunctionStatusWhere it lives
allow_llm_judge Ran
ran on a synthesized input
lmarena/ppe/utils/scorers.py
pointer only (licence: NONE) · get_code("79e87e8e79b02b1f")
How it ran

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

chat_completion_openai Ran
ran; our contract draft was wrong, not the code
lmarena/ppe/utils/core.py
pointer only (licence: NONE) · get_code("162803a87a848f49")
How it ran

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

contains_list Ran
ran, violated the contract we drafted
lmarena/ppe/display.py
pointer only (licence: NONE) · get_code("afbaf46000344a52")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lmarena/ppe 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_accuracy Ran
ran, honoured the contract we drafted
lmarena/ppe/utils/scorers.py
pointer only (licence: NONE) · get_code("d59fa2d0990791a0")
How it ran

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

make_config Ran
ran; our contract draft was wrong, not the code
lmarena/ppe/utils/core.py
pointer only (licence: NONE); the stored copy get_code serves, from wwn1233/sedareval, is pointer only (licence: NONE) · get_code("07e6f41cf857a76f")
How it ran

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

recursive_union Ran
ran; our contract draft was wrong, not the code
lmarena/ppe/score.py
pointer only (licence: NONE) · get_code("4146a53b035f7dbf")
How it ran

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

register Ran
ran; our contract draft was wrong, not the code
lmarena/ppe/utils/core.py
pointer only (licence: NONE) · get_code("0289a0e6c43b86d3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lmarena/ppe 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 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 6 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
make_config 3 other papers
1 dated earlier, 2 later
2406.11939 (2024-06)
From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline
2501.15595 (2025-01)
SedarEval: Automated Evaluation using Self-Adaptive Rubrics
2606.10528 (2026-06)
Representation-Aware Advantage Estimation: Your Reward Model Provides More Than A Scalar Output

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 introduce a new benchmark for reward models that quantifies their ability to produce strong language models through RLHF (Reinforcement Learning from Human Feedback). The gold-standard approach is to run a full RLHF training pipeline and directly probe downstream LLM performance. However, this process is prohibitively expensive. To address this, we build a predictive model of downstream LLM performance by evaluating the reward model on proxy tasks. These proxy tasks consist of a large-scale human preference and a verifiable correctness preference dataset, in which we measure 12 metrics across 12 domains. To investigate which reward model metrics are most correlated to gold-standard RLHF outcomes, we launch an end-to-end RLHF experiment on a large-scale crowdsourced human preference platform to view real reward model downstream performance as ground truth. Ultimately, we compile our data and findings into Preference Proxy Evaluations (PPE), the first reward model benchmark explicitly linked to post-RLHF real-world human preference performance, which we open-source for public use and further development. Our code and evaluations can be found at https://github.com/lmarena/PPE .

For agents

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

get_harvested_code_for_paper("2410.14872")
get_code_for_paper("2410.14872")
have("2410.14872")

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

curl https://syntology.ai/api/ran/2410.14872.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.14872.svg)](https://syntology.ai/paper/2410.14872)

Connect an agent — have() is free.