论文检索

Deep Learning · Generative Models and Autoencoders

Leander Girrbach, Zeynep Akata

Sparse autoencoders (SAEs) are used to analyze embeddings, but their role and practical value are debated. We propose a new perspective on SAEs by demonstrating that they can be naturally understood as topic models. We extend Latent Dirichlet Allocation to embedding spaces and derive the SAE objective as a maximum a posteriori estimator under this model. This view implies SAE features are thematic components rather than steerable directions. Based on this, we introduce SAE-TM, a topic modeling framework that: (1) trains an SAE to learn reusable topic atoms, (2) interprets them as word distributions on downstream data, and (3) merges them into any number of topics without retraining. SAE-TM yields more coherent topics than strong baselines on text and image datasets while maintaining diversity. Finally, we analyze thematic structure in image datasets and trace topic changes over time in Japanese woodblock prints. Our work positions SAEs as effective tools for large-scale thematic analysis across modalities. Code and data will be released upon publication.

Deep Learning · Generative Models and Autoencoders

Rylan Schaeffer, Joshua Kazdan, Alvan Arulandu, Sanmi Koyejo

The proliferation of AI-generated content online has fueled concerns over \textit{model collapse}, a degradation in future generative models' performance when trained on synthetic data generated by earlier models. Industry leaders, premier research journals and popular science publications alike have prophesied catastrophic societal consequences stemming from model collapse. In this position piece, we contend this widespread narrative fundamentally misunderstands the scientific evidence. We highlight that research on model collapse actually encompasses eight distinct and at times conflicting definitions of model collapse, and argue that inconsistent terminology within and between papers has hindered building a comprehensive understanding of model collapse. To assess how significantly different interpretations of model collapse threaten future generative models, we posit what we believe are realistic conditions for studying model collapse and then conduct a rigorous assessment of the literature's methodologies through this lens. While we leave room for reasonable disagreement, our analysis of research studies, weighted by how faithfully each study matches real-world conditions, leads us to conclude that certain predicted claims of model collapse rely on assumptions and conditions that poorly match real-world conditions, and in fact several prominent collapse scenarios are readily avoidable. Altogether, this position paper argues that model collapse has been warped from a nuanced multifaceted consideration into an oversimplified threat, and that the evidence suggests specific harms more likely under society's current trajectory have received disproportionately less attention.

Deep Learning · Algorithms

Sannyuya Liu, Ao Chen, Lin Liu, Ruxia Liang, Xiaoxuan Shen, Jianwen Sun

Symbolic Regression aims to discover interpretable mathematical expressions from data. Equation Learner (EQL) is a gradient-based method with strong fitting capability and expressive potential, yet it often activates redundant operators as model complexity grows, leading to over-complex expressions and unstable equation recovery. We analyze a gradient residual issue induced by operators that do not vanish at zero, which can prevent the ideal sparse expression from being a local optimum and bias training toward unnecessarily complex structures, making exact recovery nearly unattainable in practice. To address this, we propose EQL-Z, a structurally controllable symbolic regression framework. EQL-Z enforces zero-point constraints via zero-point consistent operator transformations to eliminate residual gradients on silent paths, and performs an incremental small-to-large structure search that grows depth/width from a compact seed under a complexity-penalized validation score. After selecting a compact structure, we optionally apply BFGS fine-tuning to refine coefficients. Experiments on synthetic and real-world datasets show that EQL-Z substantially improves exact equation recovery and in-/out-of-distribution generalization over vanilla EQL, achieving performance close to the best existing symbolic regression baselines. The code is available at https://anonymous.4open.science/r/EQL-Z-BE6C/.

Social Aspects · Everything Else

Ujwal Kumar, Alice Saito, Hershraj Niranjani, Rayan Yessou, Tan Phan Xuan

Constitutional AI has focused on single-model alignment using fixed principles. However, multi-agent systems create novel alignment challenges through emergent social dynamics. We present Constitutional Evolution, a framework for automatically discovering behavioral norms in multi-agent LLM systems. Using a grid-world simulation with survival pressure, we study the tension between individual and collective welfare, quantified via a Societal Stability Score $\mathcal{S} \in [0,1]$ that combines productivity, survival, and conflict metrics. Adversarial constitutions lead to societal collapse ($\mathcal{S}=0$), while vague prosocial principles (''be helpful, harmless, honest'') produce inconsistent coordination ($\mathcal{S}=0.249$). Even constitutions designed by Claude 4.5 Opus with explicit knowledge of the objective achieve only moderate performance ($\mathcal{S}=0.332$). Using LLM-driven genetic programming with multi-island evolution, we evolve constitutions maximizing social welfare without explicit guidance toward cooperation. The evolved constitution $\mathcal{C}^*$ achieves $\mathcal{S}=0.556\pm0.008$ (123\% higher than human-designed baselines, $N=10$), eliminates conflict, and discovers that minimizing communication (0.9\% vs 62.2\% social actions) outperforms verbose coordination. Our interpretable rules demonstrate that cooperative norms can be discovered rather than prescribed.

Social Aspects · Security

Hongyi Zhou, Jianfeng Pan, Min Peng, Shaomang Huang, Xuling Zhang

Endpoint Detection and Response (EDR) systems are crucial for identifying malicious activities on endpoint devices, yet existing methods struggle to efficiently model ultra-long log sequences and to provide interpretable reasoning for security analysts. We propose WatchLog, a novel framework that represents raw logs as video-structured data, enabling scalable and expressive video-language modeling of endpoint behaviors. Each event is encoded as a key–value-guided image, and the resulting images are temporally organized into a video sequence. To capture long-range dependencies, WatchLog employs a temporal cross-attention adapter that enables pixel-wise interaction across time. The adapter acts as an auxiliary temporal reasoning pathway, aligning spatial representations with relevant temporal contexts while preserving the original behavioral semantics. We adopt a two-stage pre-training strategy followed by supervised fine-tuning to generate behavior explanations grounded in event-level semantics and detection outcomes. Experiments on our newly constructed EDR8M-20R dataset and a public benchmark demonstrate that WatchLog consistently outperforms state-of-the-art methods in detection accuracy and recall, while offering more interpretable reasoning traces and significantly improved inference efficiency. Extensive ablation studies further support the robustness and interpretability of the proposed method.

Social Aspects · Accountability, Transparency, and Interpretability

Maty Bohacek, Nino Scherrer, Nicholas Dufour, Thomas Leung, Christoph Bregler, Stephanie Chan

The evaluation of large language models relies heavily on standardized benchmarks. These benchmarks provide useful aggregated metrics, but can obscure (i) particular sub-areas where the models are weak ("model gaps") (ii) imbalanced coverage in the benchmarks themselves ("benchmark gaps"). To automatically uncover both types of gaps, we propose a simple new method using concept activations from sparse autoencoders, to identify fine-grained gaps on a per-concept basis. The method also benefits from grounding evaluation in the model's internal representations, as well as easy comparison across benchmarks. We applied the method to two popular open-source models and ten benchmarks, as illustrative examples. As validation of the approach, we found that our automatic, unsupervised method was able to recover model gaps that have been previously documented in the literature (e.g. relating to sycophancy), in addition to identifying novel model gaps. We were also able to automatically uncover benchmark gaps: core concepts that should fall within the scope of a given benchmark. Our ``competency gaps'' method can be used to complement existing benchmarks, by providing a concept-level decomposition of model behavior, and by helping benchmark developers iterate upon benchmark design. Code is available at [anonymized].

Social Aspects · Accountability, Transparency, and Interpretability

Sophie Hanna Langbein, Hubert Baniecki, Fabian Fumagalli, Niklas Koenen, Marvin N. Wright, Julia Herbinger

Hazard and survival functions are natural, interpretable targets in time-to-event prediction, but their inherent non-additivity fundamentally limits standard additive explanation methods. We introduce Survival Functional Decomposition (SurvFD), a principled approach for analyzing feature interactions in machine learning survival models. By separating higher-order effects into time-dependent and time-independent components, SurvFD offers a previously unrecognized perspective on survival explanations, explicitly characterizing when and why additive explanations fail. Building on this theoretical decomposition, we propose SurvSHAP-IQ, which extends Shapley interactions to time-indexed functions, providing a practical estimator for higher-order, time-dependent interactions. Together, SurvFD and SurvSHAP-IQ establish a interaction- and time-aware interpretability framework for survival modeling, with broad applicability across time-to-event prediction tasks.

Social Aspects · Accountability, Transparency, and Interpretability

R. Teal Witter, Álvaro Parafita, Tomas Garriga, Maximilian Muschalik, Fabian Fumagalli, Axel Brando, Lucas Rosenblatt

Structural Causal Models (SCM) are a powerful framework for describing complicated dynamics across the natural sciences. A particularly elegant way of interpreting SCMs is do-Shapley, a game-theoretic method of quantifying the average effect of $d$ variables across exponentially many interventions. Like Shapley values, computing do-Shapley values generally requires evaluating exponentially many terms. The foundation of our work is a reformulation of do-Shapley values in terms of the \text{irreducible sets} of the underlying SCM. Leveraging this insight, we can exactly compute do-Shapley values in time linear in the number of irreducible sets $r$, which itself can range from $d$ to $2^d$ depending on the graph structure of the SCM. Since $r$ is unknown a priori, we complement the exact algorithm with an estimator that, like general Shapley value estimators, can be run with any query budget. As the query budget approaches $r$, our estimators can produce more accurate estimates than prior methods by several orders of magnitude, and, when the budget reaches $r$, return the Shapley values up to machine precision. Beyond computational speed, we also reduce the identification burden: we prove that non-parametric identifiability of do-Shapley values requires only the identification of interventional effects for the $d$ singleton coalitions, rather than all classes.

Social Aspects · Accountability, Transparency, and Interpretability

Wenbo Pan, Zhichao Liu, Xianlong Wang, Yu Haining, Xiaohua Jia

Token attribution methods provide intuitive explanations for language model outputs by identifying causally important input tokens. However, as modern LLMs increasingly rely on extended reasoning chains, existing schemes face two critical challenges: (1) efficiency bottleneck, where attributing a sequence of $|\mathbf{S}|$ tokens requires $\mathcal{O}(|\mathbf{S}|^2)$ operations, making long-context attribution prohibitively slow; and (2) faithfulness drop, where intermediate reasoning tokens absorb attribution mass, preventing importance from propagating back to the original input. To address these, we introduce **FlashTrace**, an efficient multi-token attribution method that employs span-wise aggregation to compute attribution over *multi-token targets in a single pass*, reducing complexity to $\mathcal{O}(|\mathbf{S}|)$. Moreover, we design a recursive attribution mechanism that traces importance through intermediate reasoning chains back to source inputs. Extensive experiments on long-context retrieval (RULER) and multi-step reasoning (MATH, MorehopQA) tasks demonstrate that FlashTrace achieves over 130× speedup over existing baselines while maintaining superior faithfulness. We further analyze the dynamics of recursive attribution, showing that even a single recursive hop substantially improves faithfulness by tracing importance through the reasoning chain.

Applications · Time Series

Difei Hou, Jiaqi Yue, Chunhui Zhao

Explainability is essential for applying time series analysis in high-stakes domains. While Time Series Captioning (TSC) offers a pathway to enhance temporal explainability, achieving reliable caption generation usually necessitates high-quality textual annotations. However, as interpreting abstract temporal dynamics requires specialized domain knowledge, acquiring such caption annotations is challenging, thereby impeding the advancement of TSC. To address this challenge, we introduce a novel Caption Label-Free Learning (CLFL) paradigm. Departing from the supervised learning tradition of imitating human annotations, CLFL formulates captioning as an agentic exploration task optimized by feedback from a proxy reward. Specifically, we propose a Dual Loop Agentic Captioning (DLAC) framework to achieve such an exploration-feedback mechanism. In the inner loop, a Time Series Captioning LLM Agent (TSCAgent) reflectively explores potential semantic captions. In turn, the outer loop evaluates these captions via downstream reasoning to derive a proxy reward, which feeds back to optimize the TSCAgent. Empirical results validate the effectiveness of the CLFL, proving that the exploration-feedback mechanism is sufficient for learning complex temporal semantics and autonomously generating captions, without any caption label supervision. Furthermore, we release TFTSC, an industrial expert-level time series caption dataset, which is available at: \url{https://anonymous.4open.science/r/TFTSC-05ED/}.

General Machine Learning · Representation Learning

Zixuan Qin, Qi Shen, Liu Yang, Qilong Wang, Qinghua Hu

Federated learning often face both data and model heterogeneity, with the latter often more challenging. Architectural differences yield incompatible representation, making the knowledge-sharing carrier central to heterogeneous collaboration. Using proxy model enables distillation-based collaboration but incurs high communication and computation costs. Prototype-based carriers are lighter yet cause semantic confusion when incompatible features are mixed. Therefore, we propose rule-based federated learning (RFL) that shares interpretable, class-discriminative rules to enable heterogeneous collaboration, avoid feature confusion, and keep communication lightweight. RFL uses a rule network to unify clients’ decision features and collaborates at the rule level, avoiding forcible averaging of incompatible representations. RFL selects sparse, high-coverage, beneficial rules for broadcasting, compressing shared knowledge into an interpretable class-rule set and reducing communication and computation costs. Each client selectively activates only rules relevant to its local classes, mitigating negative transfer while preserving personalization. Across heterogeneous settings, RFL achieves a better accuracy–communication trade-off.

General Machine Learning · Representation Learning

Alexandre Chaussard, Anna Bonnet, Sylvain Le Corff

Advances in data collection are producing growing volumes of temporal count observations, making adapted modeling increasingly necessary. In this work, we introduce a generative framework for independent component analysis of temporal count data, combining regime-adaptive dynamics with Poisson log-normal emissions. The model identifies disentangled components with regime-dependent contributions, enabling representation learning and perturbations analysis. Notably, we establish the identifiability of the model, supporting principled interpretation. To learn the parameters, we propose an efficient amortized variational inference procedure. Experiments on simulated data evaluate recovery of the mixing function and latent sources across diverse settings, while an *in vivo* longitudinal gut microbiome study reveals microbial co-variation patterns and regime shifts consistent with clinical perturbations.

General Machine Learning · Evaluation

Zhengshuyuan Tian, Chuanxin Lan, Chenxi Wang, Lei Wang, Guoxin Kang, Zhengxin Yang, Yunyou Huang, Xuehai Hong, Wanling Gao, Jianfeng Zhan

Current LLM evaluations often conflate benchmark performance with intrinsic model capability. This is misleading, as observed outcomes arise from the entire evaluation system, including datasets, prompting methods, decoding parameters, and the software–hardware stack, rather than the model alone. When this system is underspecified, attribution becomes unreliable; in practice, evaluation choices alone can induce accuracy swings of up to 70\%. This attribution challenge is compounded by the open-ended nature of LLM evaluation. Questions span languages, domains, and usage styles, forming highly variable and implicitly shifting datasets. Consequently, strong performance on static benchmarks may reflect alignment with surface patterns rather than robust underlying capability. Prior studies either focus on individual components, overlooking their interactions, or investigate manually curated and small-scale question variants, lacking a holistic perspective, precluding precise attribution of intrinsic model capabilities amidst the confounding influences. To address these limitations, we propose LLM evaluatology, a principled framework that grounds LLM evaluation in a causally informed system design. By jointly modeling evaluation components and structured question variations, it enables interpretable, reproducible, and causally faithful assessment of model capability, establishing clear conditions under which evaluation results are meaningful and trustworthy.

General Machine Learning · Methodology

Daisuke Yamada, Qijun Zhang, Travis Pence, Barbara Bendlin, Federico Rey, Vikas Singh

Compositional data---vectors encoding relative proportions---arise across scientific domains, including ecology, geochemistry, and genomics. The features in these data often come with known hierarchical structure (e.g., taxonomies, phylogenies, ontologies), yet existing methods either ignore this structure, discard the intrinsic Aitchison geometry, require assumptions such as binary trees, or yield incomplete coordinate systems. We describe *PolyILR*, a canonical orthonormal decomposition of the Aitchison tangent space aligned with any tree topology. Our construction defines a weighted local geometry at each internal node capturing full branching structure, then lifts these to a global orthonormal basis where every coordinate corresponds to a specific tree location. On microbiome and single-cell benchmarks, PolyILR yields stable, interpretable features and enables inference at multiscale tree resolution. We also establish a novel theoretical connection to softmax classifiers, suggesting possible applications to probabilistic modeling.

Theory · Deep Learning

George Wang, Daniel Murfet

Mechanistic interpretability aims to understand how neural networks generalize beyond their training data by reverse-engineering their internal structures. We introduce patterning as the dual problem: given a desired form of generalization, determine what training data produces it. Our approach is based on susceptibilities, which measure how posterior expectation values of observables respond to infinitesimal shifts in the data distribution. Inverting this linear response relationship yields the data intervention that steers the model toward a target internal configuration. We demonstrate patterning in a small language model, showing that re-weighting training data along principal susceptibility directions can accelerate or delay the formation of structure, such as the induction circuit. In a synthetic parentheses balancing task where multiple algorithms achieve perfect training accuracy, we show that patterning can select which algorithm the model learns by targeting the local learning coefficient of each solution. These results establish that the same mathematical framework used to read internal structure can be inverted to write it.

Social Aspects · Accountability, Transparency, and Interpretability

Rebecca Salganik, Guillaume Salha-Galvan, Adelaida Afilipoaie, Gustavo Ferreira, Valdy Wiratama, Anson Kahng, Jian Kang, Heritiana Ranaivoson

Recent AI regulation has largely focused on algorithmic components such as recommender models, ranking systems, and profiling mechanisms. At the same time, cultural and digital policy agendas increasingly frame discovery as a key objective, aiming to promote exposure diversity and cultural representation. We argue that these outcomes cannot be effectively governed through algorithm-centric approaches alone. Discovery does not arise from individual algorithms in isolation, but from interactions among models, interfaces, user behavior, economic incentives, and cultural norms. We introduce the Cultural Expressions Discovery Circuit (CEDC), an interdisciplinary framework that models discovery as an emergent socio-technical process. Through this lens, we illustrate how certain regulatory approaches struggle to align with broader cultural objectives. Furthermore, we highlight how socio-technical analysis can help inform both technical research and the governance of cultural expressions in online platforms.

Diego Granziol, Ulugbek Abdimanabov

Backdoor and data-poisoning attacks can achieve high attack success while evading existing spectral and optimisation-based defences. We show that this behaviour is not incidental, but arises from a fundamental geometric mechanism in input space. Using kernel ridge regression as an exact model of wide neural networks, we prove that clustered dirty-label poisons induce a rank-one spike in the input Hessian whose magnitude scales quadratically with attack efficacy. Crucially, for nonlinear kernels we identify a near-clone regime in which poison efficacy remains order-one while the induced input curvature vanishes, making the attack provably spectrally undetectable. We further show that input-gradient regularisation contracts poison-aligned Fisher and Hessian eigenmodes under gradient flow, yielding an explicit and unavoidable safety–efficacy trade-off by reducing data-fitting capacity. For exponential kernels, this defence admits a precise interpretation as an anisotropic high-pass filter that increases the effective length scale and suppresses near-clone poisons. Extensive experiments on linear models and deep convolutional networks across MNIST and CIFAR-10/100 validate the theory, demonstrating consistent lags between attack success and spectral visibility, and showing that regularisation and data augmentation jointly suppress poisoning. Our results establish when backdoors are inherently invisible, and provide the first end-to-end characterisation of poisoning, detectability, and defence through input-space curvature.

Social Aspects · Accountability, Transparency, and Interpretability

Yu Zhang, Jinlong Ma, Yongshuai Hou, Xuefeng Bai, Kehai Chen, Yang Xiang, Jun Yu, Min zhang

Multi-modal large language models (MLLMs) have achieved remarkable success on complex multi-modal tasks. However, it remains insufficiently explored whether they exhibit \textit{modality preference}, a tendency to favor one modality over another when processing multi-modal contexts. To study this question, we introduce $\textbf{MC}^2$ benchmark, which constructs controlled evidence-conflict scenarios to systematically evaluate modality preference in decision-making. Extensive experiments reveal that all 20 tested MLLMs generally demonstrate clear modality preferences, and such preferences can serve as a useful indicator of downstream task performance of MLLMs. Further analysis shows that modality preference can be controlled by instruction guidance and captured within the latent representations of MLLMs. Built on these insights, we propose a probing and steering method based on representation engineering to explicitly control modality preference without requiring additional fine-tuning. This method effectively amplifies modality preference toward a desired direction and demonstrates promising improvements across multiple multi-modal understanding and reasoning tasks.

Theory · Everything Else

Zachary Izzo, Iain Melvin

We study the problem of subgroup discovery for survival analysis, where the goal is to find an interpretable subset of the data on which a Cox model is highly accurate. We examine why existing quality functions are insufficient for this problem and introduce two technical innovations: the *expected prediction entropy (EPE)*, a novel metric for evaluating survival models that predict hazard functions, and the *conditional rank statistics (CRS)*, which quantifies individual point deviation from a subgroup's survival time distribution. We study the EPE and CRS theoretically and show they address problems with existing metrics. We then introduce seven algorithms for Cox subgroup discover. Our main algorithm is based on the DDGroup framework of Izzo et al. (2023) and leverages both the EPE and CRS, allowing theoretical correctness guarantees in well-specified settings. Empirical evaluation on synthetic and real data confirms our theory, showing our methods recover ground-truth subgroups in well-specified cases and achieve better model fit than naively fitting the Cox model to the entire dataset. A case study on NASA jet engine simulation data demonstrates that discovered subgroups uncover known nonlinearities in the data and suggest design choices mirrored in practice.

Reinforcement Learning · Policy Search

Zuyuan Zhang, Sizhe Tang, Tian Lan

Non-Markovian dynamics are commonly found in real-world environments due to long-range dependencies, partial observability, and memory effects. The Bellman equation that is the central pillar of Reinforcement learning (RL) becomes only approximately valid under Non-Markovian. Existing work often focus on practical algorithm designs and offer limited theoretical treatment to address key questions, such as what dynamics are indeed capturable by the Bellman framework and how to inspire new algorithm classes with optimal approximations. In this paper, we present a novel topological viewpoint on temporal-difference (TD) based RL. We show that TD errors can be viewed as 1-cochain in the topological space of state transitions, while Markov dynamics are then interpreted as topological integrability. This novel view enables us to obtain a Hodge-type decomposition of TD errors into an integrable component and a topological residual, through a Bellman–de Rham projection. We further propose HodgeFlow Policy Search (HFPS) by fitting a {potential network} to minimize the non-integrable projection residual in RL, achieving stability/sensitivity guarantees. In numerical evaluations, HFPS is shown to significantly improve RL performance under non-Markovian.