From Rubrics to Recipe: Principle-Centric Benchmark for Evaluating Large Language Models

Shirley Anugrah Hayati; Ruizi Wang; Dongyeop Kang

From Rubrics to Recipe: Principle-Centric Benchmark for Evaluating Large Language Models

Shirley Anugrah Hayati, Ruizi Wang, Dongyeop Kang

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use <b>...</b> for bold, <i>...</i> for italic, and <url>...</url> for URLs.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Large language models (LLMs) are often evaluated on benchmarks that rely on surfacelevel instructions, obscuring what defines highquality performance. We argue that tasks can be more precisely characterized through principles: human-readable rules that specify what matters for a good response to the task. Our study proposes a framework to automatically extract and generate task-level principles for data generation and evaluation. Using this approach, we build a benchmark of over 20K principle-aligned instances, enabling controllable data creation and fine-grained, interpretable assessment of LLMs. Experiments show that principles both improve output quality and scale evaluation beyond manual curation, offering a new recipe for principled assessment of LLM capabilities.1

Anthology ID:: 2026.evaleval-1.15
Volume:: Proceedings of the Workshop on Evaluating Evaluations (EvalEval)
Month:: July
Year:: 2026
Address:: San Diego, CA
Editors:: Mubashara Akhtar, Jan Batzner, Leshem Choshen, Avijit Ghosh, Usman Gohar, Jennifer Mickel, Ichhya Pant, Zeerak Talat, Michelle Lin
Venues:: EvalEval | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 82–99
Language:
URL:: https://aclanthology.org/2026.evaleval-1.15/
DOI:
Bibkey:
Cite (ACL):: Shirley Anugrah Hayati, Ruizi Wang, and Dongyeop Kang. 2026. From Rubrics to Recipe: Principle-Centric Benchmark for Evaluating Large Language Models. In Proceedings of the Workshop on Evaluating Evaluations (EvalEval), pages 82–99, San Diego, CA. Association for Computational Linguistics.
Cite (Informal):: From Rubrics to Recipe: Principle-Centric Benchmark for Evaluating Large Language Models (Hayati et al., EvalEval 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.evaleval-1.15.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{hayati-etal-2026-rubrics,
    title = "From Rubrics to Recipe: Principle-Centric Benchmark for Evaluating Large Language Models",
    author = "Hayati, Shirley Anugrah  and
      Wang, Ruizi  and
      Kang, Dongyeop",
    editor = "Akhtar, Mubashara  and
      Batzner, Jan  and
      Choshen, Leshem  and
      Ghosh, Avijit  and
      Gohar, Usman  and
      Mickel, Jennifer  and
      Pant, Ichhya  and
      Talat, Zeerak  and
      Lin, Michelle",
    booktitle = "Proceedings of the Workshop on Evaluating Evaluations ({E}val{E}val)",
    month = jul,
    year = "2026",
    address = "San Diego, CA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.evaleval-1.15/",
    pages = "82--99",
    ISBN = "979-8-89176-429-3",
    abstract = "Large language models (LLMs) are often evaluated on benchmarks that rely on surfacelevel instructions, obscuring what defines highquality performance. We argue that tasks can be more precisely characterized through principles: human-readable rules that specify what matters for a good response to the task. Our study proposes a framework to automatically extract and generate task-level principles for data generation and evaluation. Using this approach, we build a benchmark of over 20K principle-aligned instances, enabling controllable data creation and fine-grained, interpretable assessment of LLMs. Experiments show that principles both improve output quality and scale evaluation beyond manual curation, offering a new recipe for principled assessment of LLM capabilities.1"
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hayati-etal-2026-rubrics">
    <titleInfo>
        <title>From Rubrics to Recipe: Principle-Centric Benchmark for Evaluating Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shirley</namePart>
        <namePart type="given">Anugrah</namePart>
        <namePart type="family">Hayati</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ruizi</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dongyeop</namePart>
        <namePart type="family">Kang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Workshop on Evaluating Evaluations (EvalEval)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Mubashara</namePart>
            <namePart type="family">Akhtar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jan</namePart>
            <namePart type="family">Batzner</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Leshem</namePart>
            <namePart type="family">Choshen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Avijit</namePart>
            <namePart type="family">Ghosh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Usman</namePart>
            <namePart type="family">Gohar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jennifer</namePart>
            <namePart type="family">Mickel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ichhya</namePart>
            <namePart type="family">Pant</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zeerak</namePart>
            <namePart type="family">Talat</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Michelle</namePart>
            <namePart type="family">Lin</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, CA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-429-3</identifier>
    </relatedItem>
    <abstract>Large language models (LLMs) are often evaluated on benchmarks that rely on surfacelevel instructions, obscuring what defines highquality performance. We argue that tasks can be more precisely characterized through principles: human-readable rules that specify what matters for a good response to the task. Our study proposes a framework to automatically extract and generate task-level principles for data generation and evaluation. Using this approach, we build a benchmark of over 20K principle-aligned instances, enabling controllable data creation and fine-grained, interpretable assessment of LLMs. Experiments show that principles both improve output quality and scale evaluation beyond manual curation, offering a new recipe for principled assessment of LLM capabilities.1</abstract>
    <identifier type="citekey">hayati-etal-2026-rubrics</identifier>
    <location>
        <url>https://aclanthology.org/2026.evaleval-1.15/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>82</start>
            <end>99</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T From Rubrics to Recipe: Principle-Centric Benchmark for Evaluating Large Language Models
%A Hayati, Shirley Anugrah
%A Wang, Ruizi
%A Kang, Dongyeop
%Y Akhtar, Mubashara
%Y Batzner, Jan
%Y Choshen, Leshem
%Y Ghosh, Avijit
%Y Gohar, Usman
%Y Mickel, Jennifer
%Y Pant, Ichhya
%Y Talat, Zeerak
%Y Lin, Michelle
%S Proceedings of the Workshop on Evaluating Evaluations (EvalEval)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, CA
%@ 979-8-89176-429-3
%F hayati-etal-2026-rubrics
%X Large language models (LLMs) are often evaluated on benchmarks that rely on surfacelevel instructions, obscuring what defines highquality performance. We argue that tasks can be more precisely characterized through principles: human-readable rules that specify what matters for a good response to the task. Our study proposes a framework to automatically extract and generate task-level principles for data generation and evaluation. Using this approach, we build a benchmark of over 20K principle-aligned instances, enabling controllable data creation and fine-grained, interpretable assessment of LLMs. Experiments show that principles both improve output quality and scale evaluation beyond manual curation, offering a new recipe for principled assessment of LLM capabilities.1
%U https://aclanthology.org/2026.evaleval-1.15/
%P 82-99

Download as File

Markdown (Informal)

[From Rubrics to Recipe: Principle-Centric Benchmark for Evaluating Large Language Models](https://aclanthology.org/2026.evaleval-1.15/) (Hayati et al., EvalEval 2026)

From Rubrics to Recipe: Principle-Centric Benchmark for Evaluating Large Language Models (Hayati et al., EvalEval 2026)

ACL

Shirley Anugrah Hayati, Ruizi Wang, and Dongyeop Kang. 2026. From Rubrics to Recipe: Principle-Centric Benchmark for Evaluating Large Language Models. In Proceedings of the Workshop on Evaluating Evaluations (EvalEval), pages 82–99, San Diego, CA. Association for Computational Linguistics.