论文检索

Social Aspects · Accountability, Transparency, and Interpretability

Pouria Fatemi, Ehsan Sharifian, Mohammad Hossein Yassaee

Counterfactual explanations enhance interpretability by identifying alternative inputs that produce different outputs, offering localized insights into model decisions. However, traditional methods often neglect causal relationships, leading to unrealistic examples. While newer approaches integrate causality, they are computationally expensive. To address these challenges, we propose an efficient method called BRACE based on backtracking counterfactuals that incorporates causal reasoning to generate actionable explanations. We first examine the limitations of existing methods and then introduce our novel approach and its features. We also explore the relationship between our method and previous techniques, demonstrating that it generalizes them in specific scenarios. Finally, experiments show that our method provides deeper insights into model outputs.

Optimization

Lisa Jin, Jianhao Ma, Zechun Liu, Andrey Gromov, Aaron Defazio, Lin Xiao

We develop a novel optimization method for quantization-aware training (QAT). Specifically, we show that convex, piecewise-affine regularization (PAR) can effectively induce neural network weights to cluster towards discrete values. We minimize PAR-regularized loss functions using an aggregate proximal stochastic gradient method (AProx) and prove that it enjoys last-iterate convergence. Our approach provides an interpretation of the straight-through estimator (STE), a widely used heuristic for QAT, as the asymptotic form of PARQ. We conduct experiments to demonstrate that PARQ obtains competitive performance on convolution- and transformer-based vision tasks.

Deep Learning · Generative Models and Autoencoders

Charles O'Neill, Alim Gumran, David Klindt

A recent line of work has shown promise in using sparse autoencoders (SAEs) to uncover interpretable features in neural network representations. However, the simple linear-nonlinear encoding mechanism in SAEs limits their ability to perform accurate sparse inference. Using compressed sensing theory, we prove that an SAE encoder is inherently insufficient for accurate sparse inference, even in solvable cases. We then decouple encoding and decoding processes to empirically explore conditions where more sophisticated sparse inference methods outperform traditional SAE encoders. Our results reveal substantial performance gains with minimal compute increases in correct inference of sparse codes. We demonstrate this generalises to SAEs applied to large language models, where more expressive encoders achieve greater interpretability. This work opens new avenues for understanding neural network representations and analysing large language model activations.

Deep Learning · Sequential Models, Time series

Zhen Liu, Yicheng Luo, Boyuan Li, Emadeldeen Eldele, Min Wu, Qianli Ma

Shapelets are discriminative subsequences (or shapes) with high interpretability in time series classification. Due to the time-intensive nature of shapelet discovery, existing shapelet-based methods mainly focus on selecting discriminative shapes while discarding others to achieve candidate subsequence sparsification. However, this approach may exclude beneficial shapes and overlook the varying contributions of shapelets to classification performance. To this end, we propose a Soft sparse Shapes (SoftShape) model for efficient time series classification. Our approach mainly introduces soft shape sparsification and soft shape learning blocks. The former transforms shapes into soft representations based on classification contribution scores, merging lower-scored ones into a single shape to retain and differentiate all subsequence information. The latter facilitates intra- and inter-shape temporal pattern learning, improving model efficiency by using sparsified soft shapes as inputs. Specifically, we employ a learnable router to activate a subset of class-specific expert networks for intra-shape pattern learning. Meanwhile, a shared expert network learns inter-shape patterns by converting sparsified shapes into sequences. Extensive experiments show that SoftShape outperforms state-of-the-art methods and produces interpretable results.

Deep Learning · Large Language Models

Phillip Guo, Aaquib Syed, Abhay Sheshadri, Aidan Ewart, Gintare Karolina Dziugaite

Methods for knowledge editing and unlearning in large language models seek to edit or remove undesirable knowledge or capabilities without compromising general language modeling performance. This work investigates how mechanistic interpretability---which, in part, aims to identify model components (circuits) associated to specific interpretable mechanisms that make up a model capability---can improve the precision and effectiveness of editing and unlearning. We find a stark difference in unlearning and edit robustness when training components localized by different methods. We highlight an important distinction between methods that localize components based primarily on preserving outputs, and those finding high level mechanisms with predictable intermediate states. In particular, localizing edits/unlearning to components associated with the *lookup-table mechanism* for factual recall 1) leads to more robust edits/unlearning across different input/output formats, and 2) resists attempts to relearn the unwanted information, while also reducing unintended side effects compared to baselines, on both a sports facts dataset and the CounterFact dataset across multiple models.We also find that certain localized edits disrupt the latent knowledge in the model more than any other baselines, making unlearning more robust to various attacks.

Deep Learning · Algorithms

Zhangchi Zhao, Jun Shu, Deyu Meng, Zongben Xu

Inspired by the Kolmogorov-Arnold representation theorem, KANs offer a novel framework for function approximation by replacing traditional neural network weights with learnable univariate functions. This design demonstrates significant potential as an efficient and interpretable alternative to traditional MLPs. However, KANs are characterized by a substantially larger number of trainable parameters, leading to challenges in memory efficiency and higher training costs compared to MLPs. To address this limitation, we propose to generate weights for KANs via a smaller meta-learner, called MetaKANs. By training KANs and MetaKANs in an end-to-end differentiable manner, MetaKANs achieve comparable or even superior performance while significantly reducing the number of trainable parameters and maintaining promising interpretability. Extensive experiments on diverse benchmark tasks, including symbolic regression, partial differential equation solving, and image classification, demonstrate the effectiveness of MetaKANs in improving parameter efficiency and memory usage. The proposed method provides an alternative technique for training KANs, that allows for greater scalability and extensibility, and narrows the training cost gap with MLPs stated in the original paper of KANs. Our code is available at \url{https://github.com/Murphyzc/MetaKAN}.

Social Aspects · Accountability, Transparency, and Interpretability

Jing Huang, Junyi Tao, Thomas Icard, Diyi Yang, Christopher Potts

Interpretability research now offers a variety of techniques for identifying abstract internal mechanisms in neural networks. Can such techniques be used to predict how models will behave on out-of-distribution examples? In this work, we provide a positive answer to this question. Through a diverse set of language modeling tasks—including symbol manipulation, knowledge retrieval, and instruction following—we show that the most robust features for correctness prediction are those that play a distinctive causal role in the model’s behavior. Specifically, we propose two methods that leverage causal mechanisms to predict the correctness of model outputs: counterfactual simulation (checking whether key causal variables are realized) and value probing (using the values of those variables to make predictions). Both achieve high AUC-ROC in distribution and outperform methods that rely on causal-agnostic features in out-of-distribution settings, where predicting model behaviors is more crucial. Our work thus highlights a novel and significant application for internal causal analysis of language models.

General Machine Learning · Supervised Learning

Shengbin Ye, Meng Li

Symbolic regression (SR) is a powerful technique for discovering symbolic expressions that characterize nonlinear relationships in data, gaining increasing attention for its interpretability, compactness, and robustness. However, existing SR methods do not scale to datasets with a large number of input variables (referred to as extreme-scale SR), which is common in modern scientific applications. This "large $p$'' setting, often accompanied by measurement error, leads to slow performance of SR methods and overly complex expressions that are difficult to interpret. To address this scalability challenge, we propose a method called PAN+SR, which combines a key idea of ab initio nonparametric variable selection with SR to efficiently pre-screen large input spaces and reduce search complexity while maintaining accuracy. The use of nonparametric methods eliminates model misspecification, supporting a strategy called parametric-assisted nonparametric (PAN). We also extend SRBench, an open-source benchmarking platform, by incorporating high-dimensional regression problems with various signal-to-noise ratios. Our results demonstrate that PAN+SR consistently enhances the performance of 19 contemporary SR methods, enabling several to achieve state-of-the-art performance on these challenging datasets.

Optimization · Convex

Abdel-Rahim Mezidi, Jordan Patracone, Saverio Salzo, Amaury Habrard, Massimiliano Pontil, Rémi Emonet, Marc Sebban

We present several advances on neural operators by viewing the action of operator layers as the minimizers of Bregman regularized optimization problems over Banach function spaces. The proposed framework allows interpreting the activation operators as Bregman proximity operators from dual to primal space. This novel viewpoint is general enough to recover classical neural operators as well as a new variant, coined Bregman neural operators, which includes the inverse activation operator and features the same expressivity of standard neural operators. Numerical experiments support the added benefits of the Bregman variant of Fourier neural operators for training deeper and more accurate models.

Applications · Health / Medicine

Rina Bao, Shilong Dong, Zhenfang Chen, Sheng He, Patricia Ellen Grant, Yangming Ou

Medical Visual Question Answering (MVQA) requires AI models to answer questions related to medical images, offering significant potential to assist medical professionals in evaluating and diagnosing diseases, thereby improving early interventions. However, existing MVQA datasets primarily focus on basic questions regarding visual perception and pattern recognition, without addressing the more complex questions that are critical in clinical diagnosis and decision-making. This paper introduces a new benchmark designed for professional-level medical reasoning, simulating the decision-making process. We achieve this by collecting MRI and clinical data related to Hypoxic-Ischemic Encephalopathy, enriched with expert annotations and insights. Building on this data, we generate clinical question-answer pairs and MRI interpretations to enable comprehensive diagnosis, interpretation, and prediction of neurocognitive outcomes. Our evaluation of current large vision-language models (LVLMs) shows limited performance on this benchmark, highlighting both the challenges of the task and the importance of this benchmark for advancing medical AI. Furthermore, we propose a novel ``Clinical Graph of Thoughts" model, which integrates domain-specific medical knowledge and clinical reasoning processes with the interpretive abilities of LVLMs. The model demonstrates promising results, achieving around 15\% absolute gain on the most important neurocognitive outcome task, while the benchmark still reveals substantial opportunities for further research innovation.

Social Aspects · Accountability, Transparency, and Interpretability

Hayden McTavish, Zachery Boner, Jon Donnelly, Margo Seltzer, Cynthia Rudin

Decision trees are widely used for interpretable machine learning due to their clearly structured reasoning process. However, this structure belies a challenge we refer to as predictive equivalence: a given tree's decision boundary can be represented by many different decision trees. The presence of models with identical decision boundaries but different evaluation processes makes model selection challenging. The models will have different variable importance and behave differently in the presence of missing values, but most optimization procedures will arbitrarily choose one such model to return. We present a boolean logical representation of decision trees that does not exhibit predictive equivalence and is faithful to the underlying decision boundary. We apply our representation to several downstream machine learning tasks. Using our representation, we show that decision trees are surprisingly robust to test-time missingness of feature values; we address predictive equivalence's impact on quantifying variable importance; and we present an algorithm to optimize the cost of reaching predictions.

Social Aspects · Accountability, Transparency, and Interpretability

Seokhun Park, Insung Kong, yongchan Choi, Chanmoo Park, Yongdai Kim

Interpretability for machine learning models is becoming more and more important as machine learning models become more complex. The functional ANOVA model, which decomposes a high-dimensional function into a sum of lower dimensional functions (commonly referred to as components), is one of the most popular tools for interpretable AI, and recently, various neural networks have been developed for estimating each component in the functional ANOVA model. However, such neural networks are highly unstable when estimating each component since the components themselves are not uniquely defined. That is, there are multiple functional ANOVA decompositions for a given function. In this paper, we propose a novel neural network which guarantees a unique functional ANOVA decomposition and thus is able to estimate each component stably. We call our proposed neural network ANOVA Tensor Product Neural Network (ANOVA-TPNN) sinceit is motivated by the tensor product basis expansion.Theoretically, we prove that ANOVA-TPNN can approximate any smooth function well.Empirically, we show that ANOVA-TPNN provide much more stable estimation of each component and thus much more stable interpretation when training data and initial values of the model parameters vary than existing neural networks do.Our source code is released at https://github.com/ParkSeokhun/ANOVA-TPNN

Deep Learning · Other Representation Learning

Damjan Kalajdzievski

The field of mechanistic interpretability in pre-trained transformer models has demonstrated substantial evidence supporting the ''linear representation hypothesis'', which is the idea that high level concepts are encoded as vectors in the space of activations of a model. Studies also show that model generation behavior can be steered toward a given concept by adding the concept's vector to the corresponding activations. We show how to leverage these properties to build a form of logical implication into models, enabling transparent and interpretable adjustments that induce a chosen generation behavior in response to the presence of any given concept. Our method, Logical Implication Model Steering (LIMS), unlocks new hand-engineered reasoning capabilities by integrating neuro-symbolic logic into pre-trained transformer models.

General Machine Learning · Everything Else

Paulius Rauba, Qiyao Wei, Mihaela van der Schaar

Consider the problem of testing whether the outputs of a large language model (LLM) system change under an arbitrary intervention, such as an input perturbation or changing the model variant. We cannot simply compare two LLM outputs since they might differ due to the stochastic nature of the system, nor can we compare the entire output distribution due to computational intractability. While existing methods for analyzing text-based outputs exist, they focus on fundamentally different problems, such as measuring bias or fairness. To this end, we introduce distribution-based perturbation analysis, a framework that reformulates LLM perturbation analysis as a frequentist hypothesis testing problem. We construct empirical null and alternative output distributions within a low-dimensional semantic similarity space via Monte Carlo sampling, enabling tractable inference without restrictive distributional assumptions. The framework is (i) model-agnostic, (ii) supports the evaluation of arbitrary input perturbations on any black-box LLM, (iii) yields interpretable p-values; (iv) supports multiple perturbations via controlled error rates; and (v) provides scalar effect sizes. We demonstrate the usefulness of the framework across multiple case studies, showing how we can quantify response changes, measure true/false positive rates, and evaluate alignment with reference models. Above all, we see this as a reliable frequentist hypothesis testing framework for LLM auditing.

Social Aspects · Accountability, Transparency, and Interpretability

Gonçalo Paulo, Alex Mallen, Caden Juang, Nora Belrose

While the activations of neurons in deep neural networks usually do not have a simple human-understandable interpretation, sparse autoencoders (SAEs) can be used to transform these activations into a higher-dimensional latent space which can be more easily interpretable. However, SAEs can have millions of distinct latents, making it infeasible for humans to manually interpret each one. In this work, we build an open-source automated pipeline to generate and evaluate natural language interpretations for SAE latents using LLMs. We test our framework on SAEs of varying sizes, activation functions, and losses, trained on two different open-weight LLMs. We introduce five new techniques to score the quality of interpretations that are cheaper to run than the previous state of the art. One of these techniques, intervention scoring, evaluates the interpretability of the effects of intervening on a latent, which we find explains latents that are not recalled by existing methods. We propose guidelines for generating better interpretations that remain valid for a broader set of activating contexts, and discuss pitfalls with existing scoring techniques. Our code is available at https://github.com/EleutherAI/delphi.

Social Aspects · Accountability, Transparency, and Interpretability

Narmeen Oozeer, Dhruv Nathawani, Nirmalendu Prakash, Michael Lan, Abir HARRASSE, Amirali Abdullah

The study of representation universality in AI models reveals growing convergence across domains, modalities, and architectures. However, the practical applications of representation universality remain largely unexplored. We bridge this gap by demonstrating that safety interventions can be transferred between models through learned mappings of their shared activation spaces. We demonstrate this approach on two well-established AI safety tasks: backdoor removal and refusal of harmful prompts, showing successful transfer of steering vectors that alter the models' outputs in a predictable way. Additionally, we propose a new task, corrupted capabilities, where models are fine-tuned to embed knowledge tied to a backdoor. This tests their ability to separate useful skills from backdoors, reflecting real-world challenges. Extensive experiments across Llama, Qwen and Gemma model families show that our method enables using smaller models to efficiently align larger ones. Furthermore, we demonstrate that autoencoder mappings between base and fine-tuned models can serve as reliable "lightweight safety switches", allowing dynamic toggling between model behaviors.

Applications · Health / Medicine

Minqi Yu, Jinduo Liu, Junzhong Ji

Deep models are increasingly used to analyze brain graphs for the diagnosis and understanding of brain diseases. However, due to the multi-site data aggregation and individual differences, brain graph datasets exhibit widespread distribution shifts, which impair the model’s generalization ability to the test set, thereby limiting the performance of existing methods. To address these issues, we propose a Causally Invariance-aware Augmentation for brain Graph Contrastive Learning, called CIA-GCL. This method first generates a brain graph by extracting node features based on the topological structure. Then, a learnable brain invariant subgraph is identified based on a causal decoupling approach to capture the maximum label-related invariant information with invariant learning. Around this invariant subgraph, we design a novel invariance-aware augmentation strategy to generate meaningful augmented samples for graph contrast learning. Finally, the extracted invariant subgraph is utilized for brain disease classification, effectively mitigating distribution shifts while also identifying critical local graph structures, enhancing the model’s interpretability. Experiments on three real-world brain disease datasets demonstrate that our method achieves state-of-the-art performance, effectively generalizes to multi-site brain datasets, and provides certain interpretability.

Social Aspects · Accountability, Transparency, and Interpretability

Zhan Qu, Daniel Gomm, Michael Färber

Temporal Graph Neural Networks (TGNNs) are widely used to model dynamic systems where relationships and features evolve over time. Although TGNNs demonstrate strong predictive capabilities in these domains, their complex architectures pose significant challenges for explainability. Counterfactual explanation methods provide a promising solution by illustrating how modifications to input graphs can influence model predictions. To address this challenge, we present CoDy—Counterfactual Explainer for Dynamic Graphs—a model-agnostic, instance-level explanation approach that identifies counterfactual subgraphs to interpret TGNN predictions. CoDy employs a search algorithm that combines Monte Carlo Tree Search with heuristic selection policies, efficiently exploring a vast search space of potential explanatory subgraphs by leveraging spatial, temporal, and local event impact information. Extensive experiments against state-of-the-art factual and counterfactual baselines demonstrate CoDy's effectiveness, with improvements of 16% in AUFSC+ over the strongest baseline. Our code is available at: https://github.com/daniel-gomm/CoDy

Theory · Everything Else

Stas Syrota, Yevgen Zainchkovskyy, Johnny Xi, Benjamin Bloem-Reddy, Søren Hauberg

Deep latent variable models learn condensed representations of data that, hopefully, reflect the inner workings of the studied phenomena. Unfortunately, these latent representations are not statistically identifiable, meaning they cannot be uniquely determined. Domain experts, therefore, need to tread carefully when interpreting these. Current solutions limit the lack of identifiability through additional constraints on the latent variable model, e.g. by requiring labeled training data, or by restricting the expressivity of the model. We change the goal: instead of identifying the latent variables, we identify relationships between them such as meaningful distances, angles, and volumes. We prove this is feasible under very mild model conditions and without additional labeled data. We empirically demonstrate that our theory results in more reliable latent distances, offering a principled path forward in extracting trustworthy conclusions from deep latent variable models.

Social Aspects · Accountability, Transparency, and Interpretability

Moritz Vandenhirtz, Julia Vogt

Understanding the decision-making process of machine learning models provides valuable insights into the task, the data, and the reasons behind a model's failures. In this work, we propose a method that performs inherently interpretable predictions through the instance-wise sparsification of input images. To align the sparsification with human perception, we learn the masking in the space of semantically meaningful pixel regions rather than on pixel-level. Additionally, we introduce an explicit way to dynamically determine the required level of sparsity for each instance. We show empirically on semi-synthetic and natural image datasets that our inherently interpretable classifier produces more meaningful, human-understandable predictions than state-of-the-art benchmarks.