[2605.01048] Compared to What? Baselines and Metrics for Counterfactual Prompting
Skip to main content
Learn about arXiv becoming an independent nonprofit.
We gratefully acknowledge support from the Simons Foundation, member institutions, and all contributors. Donate
> cs > arXiv:2605.01048
Help | Advanced Search
All fields Title Author Abstract Comments Journal reference ACM classification MSC classification Report number arXiv identifier DOI ORCID arXiv author ID Help pages Full text
Search
GO
quick links
Login
Help Pages
About
-->
Computer Science > Computation and Language
arXiv:2605.01048 (cs)
[Submitted on 1 May 2026]
Title:Compared to What? Baselines and Metrics for Counterfactual Prompting
Authors:Zihao Yang, Mosh Levy, Yoav Goldberg, Byron C. Wallace
View a PDF of the paper titled Compared to What? Baselines and Metrics for Counterfactual Prompting, by Zihao Yang and 3 other authors
View PDF HTML (experimental)
Abstract:Counterfactual prompting (i.e., perturbing a single factor and measuring output change) is widely used to evaluate things like LLM bias and CoT faithfulness. But in this work we argue that observed effects cannot be attributed to the targeted factor without accounting for baseline ``meaning-preserving'' modifications to text that establish general model sensitivity. This is because every counterfactual edit is a compound treatment that bundles the variable of interest with incidental surface-form variation; this violates treatment variation irrelevance. We observe prediction flip rates on MedQA of 14.9% when we surgically change patient gender. However, this is statistically indistinguishable from the flip rates induced by simply paraphrasing inputs (14.1%). In this case, it would therefore be unwarranted to conclude that the LLM is especially sensitive to patient gender. To account for this and robustly measure the effects of targeted interventions, we propose a framework in which we compare (via statistical testing) differences observed under target interventions to those induced by paraphrasing inputs. We then use this framework to revisit a analysis done on the MedPerturb dataset, which reported evidence of model sensitivity to patient demographics and stylistic cues. We find that these effects largely dissipate when we account for general model sensitivity, with only 5 of 120 tests reaching statistical significance. Applying the same framework to occupational biography classification, we detect clearly significant directional gender bias, showing that the framework identifies real directional effects even when they are small. We evaluate a range of metrics -- aggregate, per-sample distributional, and regression -- and find that per-sample metrics are dramatically more powerful than aggregate metrics and regression powerfully and uniquely characterizes effect direction and magnitude.
Comments: 24 pages, 10 figures. Under review
Subjects:
Computation and Language (cs.CL); Machine Learning (cs.LG)
Cite as: arXiv:2605.01048 [cs.CL]
(or arXiv:2605.01048v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2605.01048
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Zihao Yang [view email] [v1] Fri, 1 May 2026 19:23:33 UTC (292 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Compared to What? Baselines and Metrics for Counterfactual Prompting, by Zihao Yang and 3 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2026-05
Change to browse by:
cs cs.LG
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)
About
Help
contact arXivClick here to contact arXiv Contact
subscribe to arXiv mailingsClick here to subscribe Subscribe
Copyright
Privacy Policy
Web Accessibility Assistance
arXiv Operational Status