SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.13006 · ICLR · 2024

Systematic Evaluation of LLM-as-a-Judge in LLM Alignment Tasks: Explainable Metrics and Diverse Prompt Templates

Fei Liu, Jingyang Lin, Hui Wei, Shenghua He, Tian Xia, Andy Wong, Mei Han, U Merced

arXiv · PDF · Open in the Atlas

Code that ran

6 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, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 1 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/2408.13006.json · badge: /api/ran/2408.13006.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
shenghh2015/llm-judge-eval canonical (classifier label)
classifier basis: census
6 ran · 1 no recorded run
FunctionStatusWhere it lives
create_comparison_prompt Ran
ran; our contract draft was wrong, not the code
shenghh2015/llm-judge-eval/utils/utils_judge.py
pointer only (licence: NONE) · get_code("5025a6a8bfcb633d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shenghh2015/llm-judge-eval 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.

extract_template_name Ran
ran; our contract draft was wrong, not the code
shenghh2015/llm-judge-eval/utils/utils_visualize.py
pointer only (licence: NONE) · get_code("12f7cbf0ec203ecb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shenghh2015/llm-judge-eval 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.

find_latest Ran
ran; our contract draft was wrong, not the code
shenghh2015/llm-judge-eval/utils/utils_others.py
pointer only (licence: NONE) · get_code("a8b1ffab6e08bd4a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shenghh2015/llm-judge-eval 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_std Ran
ran, honoured the contract we drafted
shenghh2015/llm-judge-eval/utils/utils_visualize.py
pointer only (licence: NONE) · get_code("86106f801d5dc2c8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shenghh2015/llm-judge-eval 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.

import_template Ran
ran; our contract draft was wrong, not the code
shenghh2015/llm-judge-eval/utils/utils_judge.py
pointer only (licence: NONE) · get_code("14c3351cff9920bc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shenghh2015/llm-judge-eval 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.

remove_redundant Ran
ran; our contract draft was wrong, not the code
shenghh2015/llm-judge-eval/utils/utils_judge.py
pointer only (licence: NONE) · get_code("e84225b86120d10a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shenghh2015/llm-judge-eval 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_mean Not yet run
unverified (harvested, no recorded run)
shenghh2015/llm-judge-eval/utils/utils_visualize.py
pointer only (licence: NONE) · get_code("ecc8c3ebd720ff32")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shenghh2015/llm-judge-eval 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 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, 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 7 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

LLM-as-a-Judge has been widely applied to evaluate and compare different LLM alignmnet approaches (e.g., RLHF and DPO). However, concerns regarding its reliability have emerged, due to LLM judges' biases and inconsistent decisionmaking. Previous research has developed evaluation frameworks to assess reliability of LLM judges and their alignment with human preferences. However, the employed evaluation metrics often lack adequate explainability and fail to address LLM internal inconsistency. Additionally, existing studies inadequately explore the impact of various prompt templates when applying LLM-as-a-Judge methods, leading to potentially inconsistent comparisons between different alignment algorithms. In this work, we systematically evaluate LLM-as-a-Judge on alignment tasks by defining more theoretically interpretable evaluation metrics and explicitly mitigating LLM internal inconsistency from reliability metrics. We develop an open-source framework to evaluate, compare, and visualize the reliability and alignment of LLM judges, which facilitates practitioners to choose LLM judges for alignment tasks. In the experiments, we examine effects of diverse prompt templates on LLM-judge reliability and also demonstrate our developed framework by comparing various LLM judges on two common alignment datasets (i.e., TL;DR Summarization and HH-RLHF-Helpfulness). Our results indicate a significant impact of prompt templates on LLM judge performance, as well as a mediocre alignment level between the tested LLM judges and human evaluators.

For agents

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

get_harvested_code_for_paper("2408.13006")
get_code_for_paper("2408.13006")
have("2408.13006")

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

curl https://syntology.ai/api/ran/2408.13006.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.13006.svg)](https://syntology.ai/paper/2408.13006)

Connect an agent — have() is free.