Macro: Enhancing Multilingual Counterfactual Explanations through Alignment-as-Preference Optimization
Self-generated counterfactual explanations (SCEs) are minimally modified inputs (minimality) generated by large language models (LLMs) that flip their own predictions (validity), offering a causally grounded approach to unraveling black-box LLM behavior. Yet extending them beyond English remains challenging: existing methods struggle to produce valid SCEs in non-dominant languages, and a persistent trade-off between validity and minimality undermines explanation quality. We introduce Macro, a pr
Record details
Published: 12 May 2026
Source: arXiv
Category: Research
Topics: Safety & alignment
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion
arXiv · 12 May 2026
Measuring What Matters Beyond Text: Evaluating Multimodal Summaries by Quality, Alignment, and Diversity
arXiv · 12 May 2026
Toward Stable Value Alignment: Introducing Independent Modules for Consistent Value Guidance
arXiv · 12 May 2026
SafeSteer: A Decoding-level Defense Mechanism for Multimodal Large Language Models
arXiv · 12 May 2026
Two Wrongs, No Right: Auditing Social-Desirability Bias in LLM Annotators for Computational Social Science
arXiv · 12 May 2026
Modulation Consistency-based Contrastive Learning for Self-Supervised Automatic Modulation Classification
arXiv · 12 May 2026
How to cite this record
ethics.ai (12 May 2026), “Macro: Enhancing Multilingual Counterfactual Explanations through Alignment-as-Preference Optimization,” evidence record 4500, https://ethics.ai/record/4500 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.