@inproceedings{lee-etal-2026-rigorous,
title = "Rigorous Interpretation Is a Form of Evaluation",
author = "Lee, Isabelle and
Liu, Emmy and
Jiao, Cathy and
Joshi, Brihi and
Yogatama, Dani and
Barez, Fazl and
Saxon, Michael",
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-1.1/",
pages = "1--11",
ISBN = "979-8-89176-429-3",
abstract = "Current machine learning models are evaluated through behavioral snapshots, with benchmark accuracies, win rates and outcome-based metrics. Model explanations and evaluations, however, are fundamentally intertwined: understanding why a model produces a behavior can be as important as measuring what it produces. If we trusted interpretability, we argue that it can serve not merely as diagnostics but as a richer and more principled form of model evaluation beyond surface-level performance metrics. We explore three ways interpretability can function evaluatively: (1) fixing problems by identifying the root causes of unwanted behavior, (2) detecting subtly faulty mechanisms that invalidate model outputs, and (3) predicting potential issues before they arise by fully understanding the model{'}s weaknesses. To fulfill its evaluative potential, we argue that interpretability methods must generate claims that are falsifiable, reproducible, and predictive{---}that is, interpretability must meet scientific standards."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2026-rigorous">
<titleInfo>
<title>Rigorous Interpretation Is a Form of Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmy</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cathy</namePart>
<namePart type="family">Jiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brihi</namePart>
<namePart type="family">Joshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dani</namePart>
<namePart type="family">Yogatama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fazl</namePart>
<namePart type="family">Barez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Saxon</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>Current machine learning models are evaluated through behavioral snapshots, with benchmark accuracies, win rates and outcome-based metrics. Model explanations and evaluations, however, are fundamentally intertwined: understanding why a model produces a behavior can be as important as measuring what it produces. If we trusted interpretability, we argue that it can serve not merely as diagnostics but as a richer and more principled form of model evaluation beyond surface-level performance metrics. We explore three ways interpretability can function evaluatively: (1) fixing problems by identifying the root causes of unwanted behavior, (2) detecting subtly faulty mechanisms that invalidate model outputs, and (3) predicting potential issues before they arise by fully understanding the model’s weaknesses. To fulfill its evaluative potential, we argue that interpretability methods must generate claims that are falsifiable, reproducible, and predictive—that is, interpretability must meet scientific standards.</abstract>
<identifier type="citekey">lee-etal-2026-rigorous</identifier>
<location>
<url>https://aclanthology.org/2026.evaleval-1.1/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1</start>
<end>11</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rigorous Interpretation Is a Form of Evaluation
%A Lee, Isabelle
%A Liu, Emmy
%A Jiao, Cathy
%A Joshi, Brihi
%A Yogatama, Dani
%A Barez, Fazl
%A Saxon, Michael
%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 lee-etal-2026-rigorous
%X Current machine learning models are evaluated through behavioral snapshots, with benchmark accuracies, win rates and outcome-based metrics. Model explanations and evaluations, however, are fundamentally intertwined: understanding why a model produces a behavior can be as important as measuring what it produces. If we trusted interpretability, we argue that it can serve not merely as diagnostics but as a richer and more principled form of model evaluation beyond surface-level performance metrics. We explore three ways interpretability can function evaluatively: (1) fixing problems by identifying the root causes of unwanted behavior, (2) detecting subtly faulty mechanisms that invalidate model outputs, and (3) predicting potential issues before they arise by fully understanding the model’s weaknesses. To fulfill its evaluative potential, we argue that interpretability methods must generate claims that are falsifiable, reproducible, and predictive—that is, interpretability must meet scientific standards.
%U https://aclanthology.org/2026.evaleval-1.1/
%P 1-11
Markdown (Informal)
[Rigorous Interpretation Is a Form of Evaluation](https://aclanthology.org/2026.evaleval-1.1/) (Lee et al., EvalEval 2026)
ACL
- Isabelle Lee, Emmy Liu, Cathy Jiao, Brihi Joshi, Dani Yogatama, Fazl Barez, and Michael Saxon. 2026. Rigorous Interpretation Is a Form of Evaluation. In Proceedings of the Workshop on Evaluating Evaluations (EvalEval), pages 1–11, San Diego, CA. Association for Computational Linguistics.