Concept-Based Explanation

While multi-concept unlearning has shown progress, extending to large-scale scenarios remains difficult, as existing methods face three persistent challenges: **(i)** they often introduce conflicting weight updates, making some targets difficult to unlearn or causing degradation of generative capability; **(ii)** they lack precise mechanisms to keep unlearning strictly confined to target concepts, resulting in collateral damage on similar content; **(iii)** many approaches rely on additional data or auxiliary modules, causing scalability and efficiency bottlenecks as the number of concepts grows. To simultaneously address these challenges, we propose **Scalable-Precise Concept Unlearning (ScaPre)**, a unified and lightweight framework tailored for scalable and precise large-scale unlearning. ScaPre introduces a *conflict-aware stable design*, which integrates the spectral trace regularizer and geometry alignment to stabilize the optimization space, suppress conflicting updates, and preserve the pretrained global structure. Furthermore, the *Informax Decoupler* identifies concept-relevant parameters and adaptively reweights updates, ensuring that unlearning is confined to the target subspace without collateral damage. ScaPre yields an efficient closed-form solution, requiring no additional data or auxiliary sub-models, while maintaining both scalability and precision. Comprehensive experiments across large-scale objects, styles, and explicit content benchmarks demonstrate that ScaPre effectively removes target concepts while maintaining generation quality. It can forget up to **×5** more concepts than the best baseline within the limits of acceptable generative quality, and outperforms existing multi-concept approaches in precision and efficiency, achieving a new state of the art for large-scale unlearning.

Concept Bottleneck Models (CBMs) use a set of human-interpretable concepts to predict the final task label, enabling domain experts to not only validate the CBM's predictions, but also intervene on incorrect concepts at test time. However, these interventions fail to address systemic misalignment between the CBM and the expert's reasoning, such as when the model learns shortcuts from biased data. To address this, we present a general interpretable debugging framework for CBMs that follows a two-step process of *Removal* and *Retraining*. In the *Removal* step, experts use concept explanations to identify and remove any undesired concepts. In the *Retraining* step, we introduce **CBDebug**, a novel method that leverages the interpretability of CBMs as a bridge for converting concept-level user feedback into sample-level auxiliary labels. These labels are then used to apply supervised bias mitigation and targeted augmentation, reducing the model’s reliance on undesired concepts. We evaluate our framework with both real and automated expert feedback, and find that **CBDebug** significantly outperforms prior retraining methods across multiple CBM architectures (PIP-Net, Post-hoc CBM) and benchmarks with known spurious correlations.

Real-world processes often contain intermediate state that can be modeled as an extremely sparse activation tensor. In this work, we analyze the identifiability of such sparse and local latent intermediate variables, which we call motifs. We prove our Motif Identifiability Theorem, stating that under certain assumptions it is possible to precisely identify these motifs exclusively by reducing end-to-end error. Additionally, we provide the Sparling algorithm, which uses a new kind of informational bottleneck that enforces levels of activation sparsity unachievable using other techniques. We find that extreme sparsity is necessary to achieve good intermediate state modeling empirically. On our synthetic DigitCircle domain as well as the LaTeX-OCR and Audio-MNIST-Sequence domains, we are able to precisely localize the intermediate states up to feature permutation with $>90\%$ accuracy, even though we only train end-to-end.

The rapid progress of visual autoregressive (VAR) models has brought new opportunities for text-to-image generation, but also heightened safety concerns. Existing concept erasure techniques, primarily designed for diffusion models, fail to generalize to VARs due to their next-scale token prediction paradigm. In this paper, we first propose a novel VAR Erasure framework **VARE** that enables stable concept erasure in VAR models by leveraging auxiliary visual tokens to reduce fine-tuning intensity. Building upon this, we introduce **S-VARE**, a novel and effective concept erasure method designed for VAR, which incorporates a filtered cross entropy loss to precisely identify and minimally adjust unsafe visual tokens, along with a preservation loss to maintain semantic fidelity, addressing the issues such as language drift and reduced diversity introduce by na\"ive fine-tuning. Extensive experiments demonstrate that our approach achieves surgical concept erasure while preserving generation quality, thereby closing the safety gap in autoregressive text-to-image generation by earlier methods.

Sparse autoencoders (SAEs) and transcoders have become important tools for machine learning interpretability. However, measuring the quality of the features they uncover remains challenging, and there is no consensus in the community about which benchmarks to use. Most evaluation procedures start by producing a single-sentence explanation for each feature in the sparse coder. These explanations are then evaluated based on how well they enable an LLM to predict the activation of a feature in new contexts. This method makes it difficult to disentangle the explanation generation and evaluation process from the actual interpretability of the features in the sparse coder. In this work, we adapt existing methods to assess the interpretability of sparse coders, with the advantage that they do not require generating natural language explanations as an intermediate step. This enables a more direct and potentially standardized assessment of interpretability. Furthermore, we compare the scores produced by our interpretability metrics with human evaluations across similar tasks and varying setups, offering suggestions for the community on improving the evaluation of these techniques.

When large language models (LLMs) use in-context learning (ICL) to solve a new task, they must infer latent concepts from demonstration examples. This raises the question of whether and how transformers represent latent structures as part of their computation. Our work experiments with several controlled tasks, studying this question using mechanistic interpretability. First, we show that in transitive reasoning tasks with a latent, discrete concept, the model successfully identifies the latent concept and does step-by-step concept composition. This builds upon prior work that analyzes single-step reasoning. Then, we consider tasks parameterized by a latent numerical concept. We discover low-dimensional subspaces in the model's representation space, where the geometry cleanly reflects the underlying parameterization. Overall, we show that small and large models can indeed disentangle and utilize latent concepts that they learn in-context from a handful of abbreviated demonstrations.

Human cognition is compositional, and one can parse a visual scene into independent concepts and the corresponding concept-changing rules. By contrast, many vision-language systems process images holistically, with limited support for explicit decomposition. And previous methods of decomposing concepts and rules often rely on hand-crafted inductive biases or human-designed priors. We introduce a framework (CRD) to decompose concept-level rules with Large Vision-Language Models (LVLMs), which explains visual input by extracting LVLM-extracted concepts and the rules governing their variation. The proposed method operates in two stages: (1) a pretrained LVLM proposes visual concepts and concept values, which are employed to instantiate a space of concept rule functions that model concept changes and spatial distributions; (2) an iterative process to select a concise set of concepts that best account for the input according to the rule function. We evaluate CRD on an abstract visual reasoning benchmark and a real-world image caption dataset. Across both settings, our approach outperforms baseline models while improving interpretability by explicitly revealing underlying concepts and compositional rules, advancing explainable and generalizable visual reasoning.

Modern deep neural networks remain challenging to interpret due to the opacity of their latent representations, impeding model understanding, debugging, and debiasing. Concept Embedding Models (CEMs) address this by mapping inputs to human-interpretable concept representations from which tasks can be predicted. Yet, CEMs fail to represent inter-concept relationships and require concept annotations at different granularities during training, limiting their applicability. In this paper, we introduce *Hierarchical Concept Embedding Models* (HiCEMs), a new family of CEMs that explicitly model concept relationships through hierarchical structures. To enable HiCEMs in real-world settings, we propose *Concept Splitting*, a method for automatically discovering finer-grained sub-concepts from a pretrained CEM’s embedding space without requiring additional annotations. This allows HiCEMs to generate fine-grained explanations from limited concept labels, reducing annotation burdens. Our evaluation across multiple datasets, including a user study and experiments on *PseudoKitchens*, a newly proposed concept-based dataset of 3D kitchen renders, demonstrates that (1) Concept Splitting discovers human-interpretable sub-concepts absent during training that can be used to train highly accurate HiCEMs, and (2) HiCEMs enable powerful test-time concept interventions at different granularities, leading to improved task accuracy.

Current safety evaluations of language models rely on benchmark-based assessments that may miss targeted vulnerabilities. We present RepIt, a simple and data-efficient framework for isolating concept-specific representations in LM activations. While existing steering methods already achieve high attack success rates through broad interventions, RepIt enables a more concerning capability: selective suppression of refusal on targeted concepts while preserving refusal elsewhere. Across five frontier LMs, RepIt produces evaluation-evading models that answer questions related to weapons of mass destruction while still scoring as safe on standard benchmarks. We find the edit of the steering vector localizes to just 100-200 neurons, and robust concept vectors can be extracted from as few as a dozen examples on a single A6000, highlighting how targeted, hard-to-detect modifications can exploit evaluation blind spots with minimal resources. By demonstrating precise concept disentanglement, this work exposes critical vulnerabilities in current safety evaluation practices and demonstrates an immediate need for more comprehensive, representation-aware assessments.

In high-stakes domains like healthcare, users often expect that sharing personal information with machine learning systems will yield tangible benefits, such as more accurate diagnoses and clearer explanations of contributing factors. However, the validity of this assumption remains largely unexplored. We propose a unified framework to fairly quantify if personalizing a model improves both prediction and explanation for every group who provide personal data. We show that its impacts on prediction and explanation can diverge: a model may become more or less explainable even when prediction is unchanged. For practical settings, we study a standard hypothesis test for detecting personalization effects on demographic groups. We derive a finite-sample lower bound on its probability of error as a function of group sizes, number of personal attributes, and desired benefit from personalization. This provides actionable insights, such as which dataset characteristics are necessary to test an effect, or the maximum effect that can be tested given a dataset. We apply our framework to real-world tabular datasets using feature-attribution methods, uncovering scenarios where effects are fundamentally untestable due to the dataset statistics. Our results highlight the need for joint evaluation of prediction and explanation in personalized models and the importance of designing models and datasets with sufficient information for such evaluation.

Time-series forecasting finds broad applications in real-world scenarios. Due to the dynamic nature of time series data, it is important for time-series forecasting models to handle potential distribution shifts over time. In this paper, we initially identify two types of distribution shifts in time series: concept drift and temporal shift. We acknowledge that while existing studies primarily focus on addressing temporal shift issues in time series forecasting, designing proper concept drift methods for time series forecasting has received comparatively less attention. Motivated by the need to address potential concept drift, while conventional concept drift methods via invariant learning face certain challenges in time-series forecasting, we propose a soft attention mechanism that finds invariant patterns from both lookback and horizon time series. Additionally, we emphasize the critical importance of mitigating temporal shifts as a preliminary to addressing concept drift. In this context, we introduce ShifTS, a method-agnostic framework designed to tackle temporal shift first and then concept drift within a unified approach. Extensive experiments demonstrate the efficacy of ShifTS in consistently enhancing the forecasting accuracy of agnostic models across multiple datasets, and outperforming existing concept drift, temporal shift, and combined baselines.

Machine unlearning as an emerging research topic for data regulations, aims to adjust a trained model to approximate a retrained one that excludes a portion of training data. Previous studies showed that class-wise unlearning is effective in forgetting the knowledge of a training class, either through gradient ascent on the forgetting data or fine-tuning with the remaining data. However, while these methods are useful, they are insufficient as the class label and the target concept are often considered to coincide. In this work, we expand the scope by considering the label domain mismatch and investigate three problems beyond the conventional all matched forgetting, e.g., target mismatch, model mismatch, and data mismatch forgetting. We systematically analyze the new challenges in restrictively forgetting the target concept and also reveal crucial forgetting dynamics in the representation level to realize these tasks. Based on that, we propose a general framework, namely, TARget-aware Forgetting (TARF). It enables the additional tasks to actively forget the target concept while maintaining the rest part, by simultaneously conducting annealed gradient ascent on the forgetting data and selected gradient descent on the hard-to-affect remaining data. Various experiments under our new settings are conducted to demonstrate the effectiveness of our TARF.

We propose a concept-based adversarial attack framework that extends beyond single-image perturbations by adopting a probabilistic perspective. Rather than modifying a single image, our method operates on an entire concept - represented by a distribution - to generate diverse adversarial examples. Preserving the concept is essential, as it ensures that the resulting adversarial images remain identifiable as instances of the original underlying category or identity. By sampling from this concept-based adversarial distribution, we generate images that maintain the original concept but vary in pose, viewpoint, or background, thereby misleading the classifier. Mathematically, this framework remains consistent with traditional adversarial attacks in a principled manner. Our theoretical and empirical results demonstrate that concept-based adversarial attacks yield more diverse adversarial examples and effectively preserve the underlying concept, while achieving higher attack efficiency.

Unlearning has emerged as a key technique to mitigate harmful content generation in diffusion models. However, existing methods often remove not only the target concept, but also benign co-occurring concepts. Unlearning nudity can unintentionally suppress the concept of person, preventing a model from generating images with person. We define these undesirably suppressed co-occurring concepts that must be preserved $\textbf{CARE}$ ($\textbf{C}$o-occurring $\textbf{A}$ssociated $\textbf{RE}$tained concepts). Then, we introduce the $\textbf{CARE score}$, a general metric that directly quantifies their preservation across unlearning tasks. With this foundation, we propose $\textbf{ReCARE}$ ($\textbf{R}$obust $\textbf{e}$rasure for $\textbf{CARE}$), a framework that explicitly safeguards CARE while erasing only the target concept. ReCARE automatically constructs the CARE-set, a curated vocabulary of benign co-occurring tokens extracted from target images, and leverages this vocabulary during training for stable unlearning. Extensive experiments across various target concepts ($\textit{Nudity}$, $\textit{Van Gogh}$ style, and $\textit{Tench}$ object) demonstrate that ReCARE achieves overall state-of-the-art performance in balancing robust concept erasure, overall utility, and CARE preservation.

A common and effective human strategy to improve a poor outcome is to first identify prior experiences most relevant to the outcome and then focus on learning from those experiences. This paper investigates whether this human strategy can improve generalization of meta-reinforcement learning (MRL). MRL learns a meta-prior from a set of training tasks such that the meta-prior can adapt to new tasks in a distribution. However, the meta-prior usually has imbalanced generalization, i.e., it adapts well to some tasks but adapts poorly to others. We propose a two-stage approach to improve generalization. The first stage identifies "critical" training tasks that are most relevant to achieve good performance on the poorly adapted tasks. The second stage improves generalization by encouraging the meta-prior to pay more attention to the critical tasks. We use conditional mutual information to mathematically formalize the notion of "paying more attention". We formulate a bilevel optimization problem to maximize the conditional mutual information by augmenting the critical tasks and propose an algorithm to solve the bilevel optimization problem. We theoretically guarantee that (1) the algorithm converges at the rate of $O(1/\sqrt{K})$ and (2) the generalization improves after the task augmentation. We use two real-world experiments, two MuJoCo experiments, and a Meta-World experiment to validate the algorithm.

Temporal graph neural networks (TGNN) extend graph neural networks to dynamic networks and have demonstrated strong predictive power. However, interpreting TGNN remains far less explored than their static-graph counterparts. This paper introduces TEMporal Graph eXplainer (TemGX), a training-free,post-hoc framework that help users interpret and understand TGNN behavior by discovering temporal subgraphs and their evolution that are responsible for TGNN output of interests.We introduce a class of explainability measures that extends influence maximization in terms of structural influence and time decay to model temporal influence. We formulate the explanation task as a constrained optimization problem, and propose fast algorithms to discover explanations with guarantees on their temporal explainability. Our experimental study verifies the effectiveness and efficiency of TemGX for TGNN explanation, compared with state-of-the-art explainers. We also showcase how TemGX supports inference queries for dynamic network analysis.

Do large language models (LLMs) represent concepts abstractly, i.e., independent of input format? We revisit Function Vectors (FVs), compact representations of in-context learning (ICL) tasks that causally drive task performance. Across multiple LLMs, we show that FVs are not fully invariant: FVs are nearly orthogonal when extracted from different input formats (e.g., open-ended vs. multiple-choice), even if both target the same concept. We identify Concept Vectors (CVs), which carry more stable concept representations. Like FVs, CVs are composed of attention head outputs; however, unlike FVs, the constituent heads are selected using Representational Similarity Analysis (RSA) based on whether they encode concepts consistently across input formats. While these heads emerge in similar layers to FV-related heads, the two sets are largely distinct, suggesting different underlying mechanisms. Steering experiments reveal that FVs excel in-distribution, when extraction and application formats match (e.g., both open-ended in English), while CVs generalize better out-of-distribution across both question types (open-ended vs. multiple-choice) and languages. Our results show that LLMs do contain abstract concept representations, but these differ from those that drive ICL performance.

Concept Bottleneck Generative Models (CBGMs) incorporate a human-interpretable concept bottleneck layer, which makes them interpretable and steerable. However, designing such a layer for generative models poses the same challenges as for concept bottleneck models in a supervised context, if not greater ones. Deterministic mappings from the model inner representations to soft concepts in existing CBGMs: (i) limit steerable generation to modifying concepts in existing inputs; and, more importantly, (ii) are susceptible to *concept leakage*, which hinders their steerability. To address these limitations, we first introduce the Variational Hard Concept Bottleneck (VHCB) layer. The VHCB maps probabilistic estimates of binary latent variables to hard concepts, which have been shown to mitigate leakage. Remarkably, its probabilistic formulation enables direct generation from a specified set of concepts. Second, we propose a systematic evaluation framework for assessing the steerability of CBGMs across various tasks (e.g., activating and deactivating concepts). Our framework which allows us to empirically demonstrate that the VHCB layer consistently improves steerability.

Deep learning representations are often difficult to interpret, which can hinder their deployment in sensitive applications. Concept Bottleneck Models (CBMs) have emerged as a promising approach to mitigate this issue by learning representations that support target task performance while ensuring that each component predicts a concrete concept from a predefined set. In this work, we argue that CBMs do not impose a true bottleneck: the fact that a component can predict a concept does not guarantee that it encodes only information about that concept. This shortcoming raises concerns regarding interpretability and the validity of intervention procedures. To overcome this limitation, we propose Minimal Concept Bottleneck Models (MCBMs), which incorporate an Information Bottleneck (IB) objective to constrain each representation component to retain only the information relevant to its corresponding concept. This IB is implemented via a variational regularization term added to the training loss. As a result, MCBMs yield more interpretable representations, support principled concept-level interventions, and remain consistent with probability-theoretic foundations.

Diffusion models are usually evaluated by their final outputs, gradually denoising random noise into meaningful images. Yet, generation unfolds along a trajectory, and understanding this dynamic process is crucial for explaining how controllable, reliable, and predictable these models are in terms of their success/failure modes. In this work, we ask the question: *when* does noise turn into a specific concept (e.g., age) and lock in the denoising trajectory? We propose PCI Prompt-Conditioned Intervention) to study this question. PCI is a training-free and model-agnostic framework for analyzing concept dynamics through diffusion time. The central idea is the analysis of *Concept Insertion Success* (CIS), defined as the probability that a concept inserted at a given timestep is preserved and reflected in the final image, offering a way to characterize the temporal dynamics of concept formation. Applied to several state-of-the-art text-to-image diffusion models and a broad taxonomy of concepts, PCI reveals diverse temporal behaviors across diffusion models, in which certain phases of the trajectory are more favorable to specific concepts even within the same concept type. These findings also provide actionable insights for text-driven image editing, highlighting *when* interventions are most effective without requiring access to model internals or training, and yielding quantitatively stronger edits that achieve a balance of semantic accuracy and content preservation than strong baselines.