arXiv Machine Learning June 8, 2026 By Adam Belahcen, St\'ephane Mussard

Aumann-SHAP: The Geometry of Counterfactual Interaction Explanations in Machine Learning

Read the original on arXiv Machine Learning →

arXiv:2603. 14014v2 Announce Type: replace Abstract: We introduce Aumann-SHAP, an interaction-aware framework that decomposes counterfactual transitions by restricting the model to a local hypercube connecting baseline and counterfactual features.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 2

Tractable Shapley Values and Interactions via Tensor Networks

arXiv:2510. 22138v3 Announce Type: replace Abstract: We show how to replace the O(2^n) coalition enumeration over n features behind Shapley values and Shapley-style interaction indices with a few-evaluation scheme on a tensor-network (TN) surrogate: TN-SHAP.

By Farzaneh Heidari, Chao Li, Guillaume Rabusseau

arXiv Machine Learning

Aug 10

Sharding Prevents LLM Oversight Failures and Adversarial Exploitation

arXiv:2608. 06422v1 Announce Type: new Abstract: Giving an LLM judge more compute does not necessarily make it check more requirements.

By Victor Akinwande, J. Zico Kolter, Aran Nayebi

llms safety

arXiv Machine Learning

Jun 9

Function-Vector Heads Are Two Populations: Writers and Cancellers in In-Context Learning

arXiv:2606. 07560v1 Announce Type: cross Abstract: Function-vector (FV) heads (Todd et al.

By Han-yu Wang

llms

arXiv AI

Jul 7

Attributing Emergence in Million-Agent Systems

arXiv:2605. 11404v2 Announce Type: replace Abstract: Large language models (LLMs) can simulate human-like reasoning and decision-making in individual agents.

By Ling Tang, Jilin Mei, Qian Chen, Qihan Ren, Linfeng Zhang, Quanshi Zhang, Jing Shao, Xia Hu, Dongrui Liu

llms agents safety

arXiv Machine Learning

6d ago

RelShap: Relationally Consistent Shapley Explanations

arXiv:2608. 11508v1 Announce Type: new Abstract: Machine learning pipelines commonly flatten relational data into single-table representations, discarding structural constraints.

By Seungeun Lee, Joao Fonseca, Julia Stoyanovich

arXiv Machine Learning

Jul 10

Calibrated Stackelberg Games: Learning Optimal Commitments Against Calibrated Agents

arXiv:2306. 02704v2 Announce Type: replace-cross Abstract: We introduce \emph{Calibrated Stackelberg Games (CSGs)}, a generalization of the standard Stackelberg Games (SGs) framework.

By Nika Haghtalab, Chara Podimata, Kunhe Yang

agents safety

Related stories

Tractable Shapley Values and Interactions via Tensor Networks

Sharding Prevents LLM Oversight Failures and Adversarial Exploitation

Function-Vector Heads Are Two Populations: Writers and Cancellers in In-Context Learning

Attributing Emergence in Million-Agent Systems

RelShap: Relationally Consistent Shapley Explanations

Calibrated Stackelberg Games: Learning Optimal Commitments Against Calibrated Agents