aiqbench analysis
This reproducibility study re-examines LXR, a learned method for generating counterfactual explanations of recommender systems, and extends it to non-top-ranked items. It also finds that simple baselines like item popularity sometimes match LXR, and that explanation quality varies with item popularity. For ML readers, the useful takeaway is that explanation methods for recommenders need checking against simple baselines before their results are trusted.
Counterfactual Profile Perturbations for Recommendation Explanations: A Reproducibility Study
arXiv:2610.36208v1 Announce Type: cross Abstract: This reproducibility paper explores the counterfactual explanation technique known as Learning to eXplain Recommendations (LXR). Prior work has shown that LXR can reliably identify perturbations that, if applied to a user's profile, cause the user's top ranked item to no longer be recommended, thereby explaining the item's recommendation as a function of the user's rating choices. In this paper, we extend this work in multiple ways. We expand the scope of the original LXR study to look at explanations for items other than the most highly recommended item, finding that LXR is also effective at this version of the task. We consider alternate baselines for LXR, including item popularity and latent factor similarity, and we see that for some tasks these alternatives work surprisingly well. We also examine the impact of item popularity, finding that LXR offers better explanation quality (shorter perturbations) when less popular items are being explained. Finally, we conduct a brute-force exploration of a subset of the perturbation space in order to estimate a lower bound for optimal perturbation size against which LXR and other such methods can be compared.
Abstract:This reproducibility paper explores the counterfactual explanation technique known as Learning to eXplain Recommendations (LXR). Prior work has shown that LXR can reliably identify perturbations that, if applied to a user's profile, cause the user's top ranked item to no longer be recommended, thereby explaining the item's recommendation as a function of the user's rating choices. In this paper, we extend this work in multiple ways. We expand the scope of the original LXR study to look at explanations for items other than the most highly recommended item, finding that LXR is also effective at this version of the task. We consider alternate baselines for LXR, including item popularity and latent factor similarity, and we see that for some tasks these alternatives work surprisingly well. We also examine the impact of item popularity, finding that LXR offers better explanation quality (shorter perturbations) when less popular items are being explained. Finally, we conduct a brute-force exploration of a subset of the perturbation space in order to estimate a lower bound for optimal perturbation size against which LXR and other such methods can be compared.
Information Retrieval (cs.IR); Artificial Intelligence (cs.AI)
arXiv:2610.36208 [cs.IR]
(or arXiv:2610.36208v1 [cs.IR] for this version)
https://doi.org/10.48550/arXiv.2610.36208 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
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.
Full text under the publisher's open licence · 280 words
Related coverage
Can a Cacheable Decision Model Follow Rules?
arXiv · Oct 1, 2026
The Injection Paradox: Brand-Level Suppression in Safety-Trained LLM Recommendations via RAG Context Injection
arXiv · Jun 9, 2026
Detecting Functional Memorization in Code Language Models
arXiv · Aug 24, 2026
CEL: Comprehensive Counterfactual Explanations Library and Benchmark
arXiv · Jul 28, 2026