论文检索

Deep Learning · Large Language Models

Patrick Leask, Neel Nanda, Noura Al Moubayed

Sparse Autoencoders (SAEs) are a popular method for decomposing Large Language Model (LLM) activations into interpretable latents, however they have a substantial training cost and SAEs learned on different models are not directly comparable. Motivated by relative representation similarity measures, we introduce Inference-Time Decomposition of Activation models (ITDAs). ITDAs are constructed by greedily sampling activations into a dictionary based on an error threshold on their matching pursuit reconstruction. ITDAs can be trained in 1% of the time of SAEs, allowing us to cheaply train them on Llama-3.1 70B and 405B. ITDA dictionaries also enable cross-model comparisons, and outperform existing methods like CKA, SVCCA, and a relative representation method on a benchmark of representation similarity. Code available at https://github.com/pleask/itda.

Deep Learning · Attention Mechanisms

Jianliang He, Xintian Pan, Siyu Chen, Zhuoran Yang

We study how multi-head softmax attention models are trained to perform in-context learning on linear data. Through extensive empirical experiments and rigorous theoretical analysis, we demystify the emergence of elegant attention patterns: a diagonal and homogeneous pattern in the key-query weights, and a last-entry-only and zero-sum pattern in the output-value weights. Remarkably, these patterns consistently appear from gradient-based training starting from random initialization. Our analysis reveals that such emergent structures enable multi-head attention to approximately implement a debiased gradient descent predictor --- one that outperforms single-head attention and nearly achieves Bayesian optimality up to proportional factor. We also extend our study to scenarios with anisotropic covariates and multi-task linear regression. Our results reveal that in-context learning ability emerges from the trained transformer as an aggregated effect of its architecture and the underlying data distribution, paving the way for deeper understanding and broader applications of in-context learning.

Social Aspects · Accountability, Transparency, and Interpretability

Connor Lawless, Lily Weng, Berk Ustun, Madeleine Udell

Machine learning models can assign fixed predictions that preclude individuals from changing their outcome. Existing approaches to audit fixed predictions do so on a pointwise basis, which requires access to an existing dataset of individuals and may fail to anticipate fixed predictions in out-of-sample data. This work presents a new paradigm to identify fixed predictions by finding confined regions of the feature space in which all individuals receive fixed predictions. This paradigm enables the certification of recourse for out-of-sample data, works in settings without representative datasets, and provides interpretable descriptions of individuals with fixed predictions. We develop a fast method to discover confined regions for linear classifiers using mixed-integer quadratically constrained programming. We conduct a comprehensive empirical study of confined regions across diverse applications. Our results highlight that existing pointwise verification methods fail to anticipate future individuals with fixed predictions, while our method both identifies them and provides an interpretable description.

Social Aspects · Privacy

Guopeng Lin, Ruisheng Zhou, Shuyu Chen, Weili Han, Jin Tan, Wenjing Fang, Lei Wang, Tao Wei

K-nearest neighbors (KNN) classification plays a significant role in various applications due to its interpretability. The accuracy of KNN classification relies heavily on large amounts of high-quality data, which are often distributed among different parties and contain sensitive information. Dozens of privacy-preserving frameworks have been proposed for performing KNN classification with data from different parties while preserving data privacy. However, existing privacy-preserving frameworks for KNN classification demonstrate communication inefficiency in the online phase due to two main issues: (1) They suffer from huge communication size for secure Euclidean square distance computations. (2) They require numerous communication rounds to select the $k$ nearest neighbors. In this paper, we present $\texttt{Kona}$, an efficient privacy-preserving framework for KNN classification. We resolve the above communication issues by (1) designing novel Euclidean triples, which eliminate the online communication for secure Euclidean square distance computations, (2) proposing a divide-and-conquer bubble protocol, which significantly reduces communication rounds for selecting the $k$ nearest neighbors. Experimental results on eight real-world datasets demonstrate that $\texttt{Kona}$ significantly outperforms the state-of-the-art framework by $1.1\times \sim 3121.2\times$ in communication size, $19.1\times \sim 5783.2\times$ in communication rounds, and $1.1\times \sim 232.6\times$ in runtime.

General Machine Learning · Unsupervised and Semi-supervised Learning

Adam Breuer

In this paper, we provide the first practical algorithms with provable guarantees for the problem of inferring the topics assigned to each document in an LDA topic model. This is the primary inference problem for many applications of topic models in social science, data exploration, and causal inference settings. We obtain this result by showing a novel non-gradient-based, combinatorial approach to estimating topic models. This yields algorithms that converge to near-optimal posterior probability in logarithmic parallel computation time (adaptivity)---exponentially faster than any known LDA algorithm. We also show that our approach can provide interpretability guarantees such that each learned topic is formally associated with a known keyword. Finally, we show that unlike alternatives, our approach can maintain the independence assumptions necessary to use the learned topic model for downstream causal inference methods that allow researchers to study topics as treatments. In terms of practical performance, our approach consistently returns solutions of higher semantic quality than solutions from state-of-the-art LDA algorithms, neural topic models, and LLM-based topic models across a diverse range of text datasets and evaluation parameters.

Deep Learning · Sequential Models, Time series

Rom N. Parnichkun, Neehal Tumma, Armin Thomas, Alessandro Moro, Qi An, Taiji Suzuki, Atsushi Yamashita, Michael Poli, Stefano Massaroli

As the space of causal sequence modeling architectures continues to grow, the need to develop a general framework for their analysis becomes increasingly important. With this aim, we draw insights from classical signal processing and control theory, to develop a quantitative measure of *memory utilization*: the internal mechanisms through which a model stores past information to produce future outputs. This metric, which we call ***effective state-size*** (ESS), is tailored to the fundamental class of systems with *input-invariant* and *input-varying linear operators*, encompassing a variety of computational units such as variants of attention, convolutions, and recurrences. Unlike prior work on memory utilization, which either relies on raw operator visualizations (e.g. attention maps), or simply the total *memory capacity* (i.e. cache size) of a model, our metrics provide highly interpretable and actionable measurements. In particular, we show how ESS can be leveraged to improve initialization strategies, inform novel regularizers and advance the performance-efficiency frontier through model distillation. Furthermore, we demonstrate that the effect of context delimiters (such as end-of-speech tokens) on ESS highlights cross-architectural differences in how large language models utilize their available memory to recall information. Overall, we find that ESS provides valuable insights into the dynamics that dictate memory utilization, enabling the design of more efficient and effective sequence models.

Applications · Everything Else

Aoran Wang, Xinnan Dai, Jun Pang

Existing methods for inferring latent relational structures struggle to integrate partial prior knowledge, such as known edges, node-degree constraints, and global sparsity, without destabilizing training or conflicting with probabilistic assumptions. We propose Soft-Gated Structural Inference (SGSI), a VAE framework that seamlessly incorporates domain constraints via (1) soft gating with learnable edge masks to preserve gradients, (2) cloning-clamping of deterministic edges to avoid distributional conflicts, and (3) adaptive regularization to balance data-driven learning with domain constraints. By excluding known edges from stochastic inference, SGSI reallocates capacity to uncertain interactions, optimizing the information bottleneck trade-off. Experiments on 16 datasets show SGSI improves edge recovery by up to $9$\% AUROC over baselines, scales to larger graphs ($94.2$\% AUROC), and maintains stable training. SGSI bridges domain expertise with data-driven learning, enabling interpretable and robust structural discovery in dynamical systems.

Applications · Computer Vision

Woohyeon Park, Woojin Kim, Jaeik Kim, Jaeyoung Do

Despite significant advancements in Vision-Language Models (VLMs), the performance of existing VLMs remains hindered by object hallucination, a critical challenge to achieving accurate visual understanding. To address this issue, we propose SECOND: Selective and Contrastive Decoding, a novel approach that enables VLMs to effectively leverage multi-scale visual information with an object-centric manner, closely aligning with human visual perception. SECOND progressively selects and integrates multi-scale visual information, facilitating a more precise interpretation of images. By contrasting these visual information iteratively, SECOND significantly reduces perceptual hallucinations and outperforms a wide range of benchmarks. Our theoretical analysis and experiments highlight the largely unexplored potential of multi-scale application in VLMs, showing that prioritizing and contrasting across scales outperforms existing methods.

Deep Learning · Sequential Models, Time series

Jiecheng Lu, Shihao Yang

Autoregressive attention-based time series forecasting (TSF) has drawn increasing interest, with mechanisms like linear attention often outperforming vanilla attention. However, deeper Transformer architectures frequently misalign with autoregressive objectives, obscuring the underlying VAR structure embedded within linear attention and hindering their ability to capture the data generative processes in TSF. In this work, we first show that a single linear attention layer can be interpreted as a dynamic vector autoregressive (VAR) structure. We then explain that existing multi-layer Transformers have structural mismatches with the autoregressive forecasting objective, which impair interpretability and generalization ability. To address this, we show that by rearranging the MLP, attention, and input-output flow, multi-layer linear attention can also be aligned as a VAR model. Then, we propose Structural Aligned Mixture of VAR (SAMoVAR), a linear Transformer variant that integrates interpretable dynamic VAR weights for multivariate TSF. By aligning the Transformer architecture with autoregressive objectives, SAMoVAR delivers improved performance, interpretability, and computational efficiency, comparing to SOTA TSF models.

Applications · Neuroscience, Cognitive Science

Weikang Qiu, Zheng Huang, Haoyu Hu, Aosong Feng, Yujun Yan, ZHITAO YING

Decoding functional magnetic resonance imaging (fMRI) signals into text has been a key challenge in the neuroscience community, with the potential to advance brain-computer interfaces and uncover deeper insights into brain mechanisms. However, existing approaches often struggle with suboptimal predictive performance, limited task variety, and poor generalization across subjects. In response to this, we propose MindLLM, a model designed for subject-agnostic and versatile fMRI-to-text decoding. MindLLM consists of an fMRI encoder and an off-the-shelf LLM. The fMRI encoder employs a neuroscience-informed attention mechanism, which is capable of accommodating subjects with varying input shapes and thus achieves high-performance subject-agnostic decoding. Moreover, we introduce Brain Instruction Tuning (BIT), a novel approach that enhances the model's ability to capture diverse semantic representations from fMRI signals, facilitating more versatile decoding. We evaluate MindLLM on comprehensive fMRI-to-text benchmarks. Results demonstrate that our model outperforms the baselines, improving downstream tasks by $12.0\%$, unseen subject generalization by $24.5\%$, and novel task adaptation by $25.0\%$. Furthermore, the attention patterns in MindLLM provide interpretable insights into its decision-making process.

Applications · Computer Vision

Pierrick Leroy, Antonio Mastropietro, Marco Nurisso, Francesco Vaccarino

Face Recognition (FR) tasks have made significant progress with the advent of Deep Neural Networks, particularly through margin-based triplet losses that embed facial images into high-dimensional feature spaces. During training, these contrastive losses focus exclusively on identity information as labels. However, we observe a multiscale geometric structure emerging in the embedding space, influenced by interpretable facial (e.g., hair color) and image attributes (e.g., contrast).We propose a geometric approach to describe the dependence or invariance of FR models to these attributes and introduce a physics-inspired alignment metric. We evaluate the proposed metric on controlled, simplified models and widely used FR models fine-tuned with synthetic data for targeted attribute augmentation. Our findings reveal that the models exhibit varying degrees of invariance across different attributes, providing insight into their strengths and weaknesses and enabling deeper interpretability.Code available here: https://github.com/mantonios107/attrs-fr-embs.

Social Aspects · Accountability, Transparency, and Interpretability

Xinyue Xu, Yueying Hu, Hui Tang, Yi Qin, Lu Mi, Hao Wang, Xiaomeng Li

Concept Bottleneck Models (CBMs) enhance interpretability by explaining predictions through human-understandable concepts but typically assume that training and test data share the same distribution. This assumption often fails under domain shifts, leading to degraded performance and poor generalization. To address these limitations and improve the robustness of CBMs, we propose the Concept-based Unsupervised Domain Adaptation (CUDA) framework. CUDA is designed to: (1) align concept representations across domains using adversarial training, (2) introduce a relaxation threshold to allow minor domain-specific differences in concept distributions, thereby preventing performance drop due to over-constraints of these distributions, (3) infer concepts directly in the target domain without requiring labeled concept data, enabling CBMs to adapt to diverse domains, and (4) integrate concept learning into conventional domain adaptation (DA) with theoretical guarantees, improving interpretability and establishing new benchmarks for DA. Experiments demonstrate that our approach significantly outperforms the state-of-the-art CBM and DA methods on real-world datasets.

Applications · Neuroscience, Cognitive Science

Timothy Doyeon Kim, Thomas Luo, Tankut Can, Kamesh Krishnamurthy, Jonathan Pillow, Carlos Brody

Neural computations underlying processes such as decision-making, working memory, and motor control are thought to emerge from neural population dynamics. But estimating these dynamics remains a significant challenge. Here we introduce Flow-field Inference from Neural Data using deep Recurrent networks (FINDR), an unsupervised deep learning method for inferring low-dimensional, nonlinear, stochastic dynamics underlying neural population activity. Using spike train data from frontal brain regions of rats performing an auditory decision-making task, we demonstrate that FINDR performs competitively with existing methods in capturing the heterogeneous responses of individual neurons. When trained to disentangle task-relevant and irrelevant activity, FINDR uncovers interpretable low-dimensional dynamics. These dynamics can be visualized as flow fields and attractors, enabling direct tests of attractor-based theories of neural computation. We suggest FINDR as a powerful method for revealing the low-dimensional task-relevant dynamics of neural populations and their associated computations.

Social Aspects · Accountability, Transparency, and Interpretability

Gouki Minegishi, Hiroki Furuta, Shohei Taniguchi, Yusuke Iwasawa, Yutaka Matsuo

Transformer-based language models exhibit In-Context Learning (ICL), where predictions are made adaptively based on context. While prior work links induction heads to ICL through a sudden jump in accuracy, this can only account for ICL when the answer is included within the context.However, an important property of practical ICL in large language models is the ability to meta-learn how to solve tasks from context, rather than just copying answers from context; how such an ability is obtained during training is largely unexplored.In this paper, we experimentally clarify how such meta-learning ability is acquired by analyzing the dynamics of the model's circuit during training. Specifically, we extend the copy task from previous research into an In-Context Meta Learning setting, where models must infer a task from examples to answer queries.Interestingly, in this setting, we find that there are multiple phases in the process of acquiring such abilities, and that a unique circuit emerges in each phase, contrasting with the single-phases change in induction heads. The emergence of such circuits can be related to several phenomena known in large language models, and our analysis lead to a deeper understanding of the source of the transformer's ICL ability.

Social Aspects · Accountability, Transparency, and Interpretability

Junwei Su, Chuan Wu

This paper investigates the convergence behavior of score-based graph generative models (SGGMs). Unlike common score-based generative models (SGMs) that are governed by a single stochastic differential equation (SDE), SGGMs utilize a system of dependent SDEs, where the graph structure and node features are modeled separately, while accounting for their inherent dependencies. This distinction makes existing convergence analyses from SGMs inapplicable for SGGMs. In this work, we present the first convergence analysis for SGGMs, focusing on the convergence bound (the risk of generative error) across three key graph generation paradigms: (1) feature generation with a fixed graph structure, (2) graph structure generation with fixed node features, and (3) joint generation of both graph structure and node features. Our analysis reveals several unique factors specific to SGGMs (e.g., the topological properties of the graph structure) which significantly affect the convergence bound. Additionally, we offer theoretical insights into the selection of hyperparameters (e.g., sampling steps and diffusion length) and advocate for techniques like normalization to improve convergence. To validate our theoretical findings, we conduct a controlled empirical study using a synthetic graph model. The results in this paper contribute to a deeper theoretical understanding of SGGMs and offer practical guidance for designing more efficient and effective SGGMs.

Deep Learning · Large Language Models

Itay Yona, Ilia Shumailov, Jamie Hayes, Yossi Gandelsman

Large Language Models (LLMs), despite their impressive capabilities, often fail to accurately repeat a single word when prompted to, and instead output unrelated text. This unexplained failure mode represents a *vulnerability*, allowing even end users to diverge models away from their intended behavior. We aim to explain the causes for this phenomenon and link it to the concept of "attention sinks", an emergent LLM behavior crucial for fluency, in which the initial token receives disproportionately high attention scores. Our investigation identifies the neural circuit responsible for attention sinks and shows how long repetitions disrupt this circuit. We extend this finding to other nonrepeating sequences that exhibit similar circuit disruptions. To address this, we propose a targeted patch that effectively resolves the issue without negatively impacting the overall performance of the model. This study provides a mechanistic explanation for an LLM vulnerability, demonstrating how interpretability can diagnose and address issues, and offering insights that pave the way for more secure and reliable models.

Social Aspects · Accountability, Transparency, and Interpretability

Harrish Thasarathan, Julian Forsyth, Thomas Fel, Matthew Kowal, Konstantinos Derpanis

We present Universal Sparse Autoencoders (USAEs), a framework for uncovering and aligning interpretable concepts spanning multiple pretrained deep neural networks. Unlike existing concept-based interpretability methods, which focus on a single model, USAEs jointly learn a universal concept space that can reconstruct and interpret the internal activations of multiple models at once. Our core insight is to train a single, overcomplete sparse autoencoder (SAE) that ingests activations from any model and decodes them to approximate the activations of any other model under consideration. By optimizing a shared objective, the learned dictionary captures common factors of variation—concepts—across different tasks, architectures, and datasets. We show that USAEs discover semantically coherent and important universal concepts across vision models; ranging from low-level features (e.g., colors and textures) to higher-level structures (e.g., parts and objects). Overall, USAEs provide a powerful new method for interpretable cross-model analysis and offers novel applications—such as coordinated activation maximization—that open avenues for deeper insights in multi-model AI systems.

Deep Learning · Sequential Models, Time series

Marten Lienen, Abdullah Saydemir, Stephan Günnemann

State space models are emerging as a dominant model class for sequence problems with many relying on the HiPPO framework to initialize their dynamics. However, HiPPO fundamentally assumes data to be noise-free; an assumption often violated in practice. We extend the HiPPO theory with measurement noise and derive an uncertainty-aware initialization for state space model dynamics. In our analysis, we interpret HiPPO as a linear stochastic control problem where the data enters as a noise-free control signal. We then reformulate the problem so that the data become noisy outputs of a latent system and arrive at an alternative dynamics initialization that infers the posterior of this latent system from the data without increasing runtime. Our experiments show that our initialization improves the resistance of state-space models to noise both at training and inference time.

General Machine Learning · Supervised Learning

Xinyan Liang, Shijie Wang, Yuhua Qian, Qian Guo, Liang Du, Bingbing Jiang, Tingjin Luo, Feijiang Li

Multi-view classification (MVC) based on the Dempster-Shafer theory has gained significant recognition for its reliability in safety-critical applications. However, existing methods predominantly focus on providing confidence levels for decision outcomes without explaining the reasoning behind these decisions. Moreover, the reliance on first-order statistical magnitudes of belief masses often inadequately capture the intrinsic uncertainty within the evidence. To address these limitations, we propose a novel framework termed Trusted Multi-view Classification Constrained with Expert Knowledge (TMCEK). TMCEK integrates expert knowledge to enhance feature-level interpretability and introduces a distribution-aware subjective opinion mechanism to derive more reliable and realistic confidence estimates. The theoretical superiority of the proposed uncertainty measure over conventional approaches is rigorously established. Extensive experiments conducted on three multi-view datasets for sleep stage classification demonstrate that TMCEK achieves state-of-the-art performance while offering interpretability at both the feature and decision levels. These results position TMCEK as a robust and interpretable solution for MVC in safety-critical domains. The code is available at https://github.com/jie019/TMCEK_ICML2025.

Social Aspects · Accountability, Transparency, and Interpretability

Yu-Neng Chuang, Prathusha Sarma, Parikshit Gopalan, John Boccio, Sara Bolouki, Xia Hu, Helen Zhou

Large language models (LLMs) have demonstrated impressive performance on several tasks and are increasingly deployed in real-world applications. However, especially in high-stakes settings, it becomes vital to know when the output of an LLM may be unreliable. Depending on whether an answer is trustworthy, a system can then choose to route the question to another expert, or otherwise fall back on a safe default behavior. In this work, we study the extent to which LLMs can reliably indicate confidence in their answers, and how this notion of confidence can translate into downstream accuracy gains. We propose Self-Reflection with Error-based Feedback (Self-REF), a lightweight training strategy to teach LLMs to express confidence in whether their answers are correct in a reliable manner. Self-REF introduces confidence tokens into the LLM, from which a confidence score can be extracted. Compared to conventional approaches such as verbalizing confidence and examining token probabilities, we demonstrate empirically that confidence tokens show significant improvements in downstream routing and rejection learning tasks.