MUtE: A Dual Framework for Concept Erasure and Counterfactual Interventions — Paper

Abstract

Erasing concept-specific information from representations has been proven useful for mitigating bias or interpreting model decisions. The joint objective is to transform the original representations such that the target concept becomes unpredictable, while maximally preserving concept-unrelated information. In this work, we revisit the optimal bounds of concept erasure to derive a novel class of erasure functions that naturally induce a deterministic, dual counterfactual mapping. Bridging the gap between theoretical optimality and practical representation learning, we design an implementation that imposes a translational bias on counterfactual trajectories - a constraint that aligns with how many concepts geometrically manifest in modern language models. Our framework enables seamless navigation between concept erasure and counterfactual generation. We empirically demonstrate its efficacy in improving downstream algorithmic fairness and generating counterfactual texts.

Authors 1

Antoine Saillenfest

Specification

Official page: arxiv.org/abs/2609.11253
Source:arXiv (Atom API + RSS)T1observed 55 min agohigh
Arxiv announce type: cross
Source:arXiv (Atom API + RSS)T1observed 55 min agohigh
arXiv id: 2609.11253
Source:arXiv (Atom API + RSS)T1observed 55 min agohigh
Categories: cs.LG, cs.CL
Source:arXiv (Atom API + RSS)T1observed 55 min agohigh
PDF: arxiv.org/pdf/2609.11253
Source:arXiv (Atom API + RSS)T1observed 55 min agohigh
Primary category: cs.LG
Source:arXiv (Atom API + RSS)T1observed 55 min agohigh
Published: 11 Sept 2026
Source:arXiv (Atom API + RSS)T1observed 55 min agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

55 min ago

Conflicts

None

No models linked to this paper yet.

Authors: Antoine Saillenfest

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history · Official page

1 claims · 1 propertiesShow all properties

Official pageofficial_url1

Claim history for Official page
Value	Valid from → to	Status	Source	Confidence	Extractor
https://arxiv.org/abs/2609.11253	11 Sept 2026 21:02 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

11 Sept 2026
Property changedPaperMUtE: A Dual Framework for Concept Erasure and Counterfactual Interventions
MUtE: A Dual Framework for Concept Erasure and Counterfactual Interventions: arxiv announce type changed from new to cross
Arxiv announce typenew→crossarxiv
rss.arxiv.org
11 Sept 2026
New paperPaperMUtE: A Dual Framework for Concept Erasure and Counterfactual Interventions
New paper: MUtE: A Dual Framework for Concept Erasure and Counterfactual Interventions
arxiv
rss.arxiv.org

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
arXiv (Atom API + RSS)	rss.arxiv.org/rss/cs.CL	feed	T1· Official	55 min ago	1
arXiv (Atom API + RSS)	rss.arxiv.org/rss/cs.LG	feed	T1· Official	55 min ago	1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.