On Defining Erasure Harms for NLP

Concept erasure aims to remove a target concept from a representation while preserving the other information encoded in it. This is difficult because representations encode many concepts that are often correlated with the erasure target, so removing the target risks damaging them. We propose the Manifold Constraint Hypothesis (MCH): if natural representations concentrate on a structured, lower-dimensional manifold, then interventions should be constrained to that manifold and better preserve other information encoded in the representation during interventions. We instantiate MCH in a new concept erasure method: MANifold aware Concept Erasure (MANCE). MANCE performs iterative updates to the representations using signals from a classifier that predicts a target concept. We estimate the manifold using representations obtained from natural inputs, and then we project the concept removal update to the estimated manifold. We perform extensive evaluation on 119 settings spanning text and vision, including 13 language models, three NLP concepts, and 40 CelebA-CLIP attributes. Employing MANCE on top of previous methods shows consistent improved leakage results. We also introduce MANCE+ and MANCE++, which prepend a closed-form erasure algorithm before employing MANCE, achieving better leakage--surgicality tradeoffs relative to matched full-space updates. MANCE++, our best method, achieves state-of-the-art results on nonlinear concept erasure. These results support MCH in the erasure setting: interventions should be constrained to the natural representation manifold.

Concept erasure aims to remove semantic concepts from a trained generative model and is increasingly important for responsible AI deployment. However, verifying whether a model has robustly removed targeted concepts remains a critical challenge. Existing evaluation methods are typically pre-defined and static, failing to expose vulnerabilities under diverse natural-language probes and challenging conditions. Moreover, manually designed evaluation strategies can be biased and difficult to scale. We posit that concept erasure evaluation is best formulated as an adaptive hypothesis search, operationalised by agents that iteratively propose, critique, and verify tests to systematically expand coverage of failure modes. To this end, we propose Stress Testing Agents for Concept Erasure (STACE), a framework that autonomously stress-tests concept-erased models using multiple Large Language Model (LLM) agents, by iteratively generating and verifying stress-testing hypotheses grounded by external knowledge. We also introduce a suite of metrics for assessing the performance and efficiency of LLM-agent-powered stress-testing frameworks. Our extensive experiments show that STACE outperforms five LLM-based evaluation baselines on four concept categories. Further analysis across two T2I models, six concept erasure approaches, and various erasure strengths show that STACE is robust for different settings. We also show that STACE can be adapted beyond concept erasure evaluation to other problem domains, such as LLM jailbreaking. Our code is available anonymously.

Modern language models rely on pretraining filters to remove undesirable content from training corpora and inference-time guardrails to suppress undesirable outputs during deployment. In this paper, we examine how these filtering and moderation decisions produce forms of epistemic erasure and reveal tensions both across automated systems and between these systems and human judgment. We audit four pretraining filters and three inference-time guardrails on Common Crawl sentences containing gender and regional-origin mentions, together with a manually annotated subset of 500 sentences. Our analysis shows that filtering and guardrail decisions are strongly associated with blocklist-based lexical cues, while frequently failing to flag content containing private information or explicit hate speech. At the same time, marginalized groups, particularly transgender people, women, and Central Americans, are significantly over-flagged across systems. Human annotators, by contrast, would retain 88.5% of filter-flagged and 91.3% of guardrail-flagged content, often recognizing representational harms arising from tensions of content removal that current systems fail to capture. Taken together, our findings document a form of epistemic erasure in which mentions of marginalized groups are disproportionately removed before pretraining and additionally suppressed again at inference time.