@inproceedings{hermany-etal-2026-reproducing,
title = "Reproducing the Results, But not the Interpretations: Evidence for Artifacts in Automatic Creativity Scoring with {LLM}s",
author = "Hermany, Carl and
Momen, Omar and
Zarrie{\ss}, Sina",
editor = "Arad, Dana and
Belinkov, Yonatan and
Chen, Hanjie and
Feldhus, Nils and
Mueller, Aaron and
Mohebbi, Hosein and
Sarti, Gabriele and
Tutek, Martin",
booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.blackboxnlp-1.68/",
pages = "1184--1195",
ISBN = "979-8-89176-476-7",
abstract = "Recent work has shown that finetuned language models can predict human creativity ratings of metaphors, motivating claims that they can comprehend creativity in non-literal language. We question the interpretation of a previously reported performance of finetuned GPT-2 and RoBERTa and investigate the signals underlying their predictions. Using ridge regression probes, random baselines, token-order ablations, and representation-evolution features, we find that pretrained representations perform comparably to finetuned models. Randomly initialized models retain moderate performance when token and positional information is preserved, and token shuffling does not eliminate the predictive signal. These results suggest that performance is supported largely by surface-level cues, including sentence length, token identity, and token co-occurrence. We therefore reproduce the original results but challenge the interpretation, highlighting the importance of controlled reproducibility studies on LM-related findings and claims from other domains."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hermany-etal-2026-reproducing">
<titleInfo>
<title>Reproducing the Results, But not the Interpretations: Evidence for Artifacts in Automatic Creativity Scoring with LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carl</namePart>
<namePart type="family">Hermany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omar</namePart>
<namePart type="family">Momen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Zarrieß</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Arad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yonatan</namePart>
<namePart type="family">Belinkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanjie</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nils</namePart>
<namePart type="family">Feldhus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Mueller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hosein</namePart>
<namePart type="family">Mohebbi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriele</namePart>
<namePart type="family">Sarti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Tutek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-476-7</identifier>
</relatedItem>
<abstract>Recent work has shown that finetuned language models can predict human creativity ratings of metaphors, motivating claims that they can comprehend creativity in non-literal language. We question the interpretation of a previously reported performance of finetuned GPT-2 and RoBERTa and investigate the signals underlying their predictions. Using ridge regression probes, random baselines, token-order ablations, and representation-evolution features, we find that pretrained representations perform comparably to finetuned models. Randomly initialized models retain moderate performance when token and positional information is preserved, and token shuffling does not eliminate the predictive signal. These results suggest that performance is supported largely by surface-level cues, including sentence length, token identity, and token co-occurrence. We therefore reproduce the original results but challenge the interpretation, highlighting the importance of controlled reproducibility studies on LM-related findings and claims from other domains.</abstract>
<identifier type="citekey">hermany-etal-2026-reproducing</identifier>
<location>
<url>https://aclanthology.org/2026.blackboxnlp-1.68/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1184</start>
<end>1195</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reproducing the Results, But not the Interpretations: Evidence for Artifacts in Automatic Creativity Scoring with LLMs
%A Hermany, Carl
%A Momen, Omar
%A Zarrieß, Sina
%Y Arad, Dana
%Y Belinkov, Yonatan
%Y Chen, Hanjie
%Y Feldhus, Nils
%Y Mueller, Aaron
%Y Mohebbi, Hosein
%Y Sarti, Gabriele
%Y Tutek, Martin
%S Proceedings of the 9th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-476-7
%F hermany-etal-2026-reproducing
%X Recent work has shown that finetuned language models can predict human creativity ratings of metaphors, motivating claims that they can comprehend creativity in non-literal language. We question the interpretation of a previously reported performance of finetuned GPT-2 and RoBERTa and investigate the signals underlying their predictions. Using ridge regression probes, random baselines, token-order ablations, and representation-evolution features, we find that pretrained representations perform comparably to finetuned models. Randomly initialized models retain moderate performance when token and positional information is preserved, and token shuffling does not eliminate the predictive signal. These results suggest that performance is supported largely by surface-level cues, including sentence length, token identity, and token co-occurrence. We therefore reproduce the original results but challenge the interpretation, highlighting the importance of controlled reproducibility studies on LM-related findings and claims from other domains.
%U https://aclanthology.org/2026.blackboxnlp-1.68/
%P 1184-1195
Markdown (Informal)
[Reproducing the Results, But not the Interpretations: Evidence for Artifacts in Automatic Creativity Scoring with LLMs](https://aclanthology.org/2026.blackboxnlp-1.68/) (Hermany et al., BlackboxNLP 2026)
ACL