论文检索

Social Aspects · Accountability, Transparency, and Interpretability

David Rundel, Fabian Fumagalli, Maximilian Muschalik, Bernd Bischl, Matthias Feurer

Shapley values are a principled attribution measure widely used in interpretable machine learning, but their exact computation scales exponentially with the number of players, motivating a wide range of approximation methods based on value-function evaluations of sampled coalitions. This raises the question of whether approximation accuracy can be improved by *adaptively* selecting coalitions for evaluation based on previous outcomes. This is particularly relevant in settings where the value function is costly, and the number of evaluations is severely limited, such as retraining-based feature importance, data valuation, and hyperparameter importance. For this purpose, we propose $\texttt{ShaplEIG}$, a Bayesian experimental design approach that approximates the expensive value function via a Gaussian process surrogate and adaptively selects coalitions based on their expected information gain about the Shapley values. Since Shapley values are a linear function of the value function, we show that the expected information gain is available in *closed form* and *efficiently* computable. In extensive experiments across diverse costly applications, our method consistently improves estimation accuracy over state-of-the-art baselines.

Social Aspects · Accountability, Transparency, and Interpretability

Joseph Paillard, Angel REYERO LOBO, Denis-Alexander Engemann, Thirion Bertrand

Feature-importance methods show promise for transforming machine learning (ML) models from predictive engines into tools for scientific discovery. However, expressive models can be unstable due to data sampling and algorithmic stochasticity, leading to inaccurate variable importance estimates, undermining their utility in critical biomedical applications. While ensembling offers a remedy, the choice between explaining a single ensemble model or aggregating individual model explanations is non-trivial due to the non-linearity of importance measures, and remains largely understudied. Our theoretical analysis, developed under assumptions accommodating complex state-of-the-art ML models, reveals that this choice is governed by a trade-off involving the model's excess risk. In contrast to prior literature, we show that ensembling at the model level provides more accurate variable-importance estimates, particularly for expressive models, by reducing this leading error term. We validate these findings on classical benchmarks and a large-scale proteomic study from the UK Biobank.

General Machine Learning · Representation Learning

Yuanyuan Wang, Wenjie Wang, Kun Zhang, Mingming Gong

Bridging the gap between visual realism and physical understanding is a core challenge for video-based world models. We study the structural identifiability of continuous-time physical laws from raw pixels, focusing on whether an encoder-only pipeline can uniquely recover the parameters of second-order linear ODEs. We prove that a level-set slope-coverage condition ensures the learned latent space is locally affine to the true physical state, enabling exact parameter recovery. Our theory provides the first characterization of minimal data requirements across damping regimes, establishing that underdamped systems are identifiable from a single video clip, whereas other regimes require three diverse trajectories. We further introduce a variance-floor regularizer to stabilize the decoder-free objective and prevent latent collapse. Validated on synthetic and real-world data, our approach demonstrates that interpretable physical constants can be reliably estimated from video without the need for compute-intensive pixel reconstruction, ensuring both physical correctness and transparency.

Theory · Deep Learning

Kaifei Wang, Binghui Li, Han Zhong, Pinyan Lu, Liwei Wang

Muon updates matrix parameters via the matrix sign of the gradient and has shown strong empirical gains, yet its dynamics and scaling behavior remain unclear in theory. We study Muon in a linear associative memory model with softmax retrieval and a hierarchical frequency spectrum over query–answer pairs, with and without label noise. In this setting, we show that Gradient Descent (GD) learns frequency components at highly imbalanced rates, leading to slow convergence bottlenecked by low-frequency components. In contrast, the Muon optimizer mitigates this imbalance, leading to faster and more uniform progress. Specifically, in the noiseless case, Muon achieves an exponential speedup over GD; in the noisy case with a power-decay frequency spectrum, we derive Muon's optimization scaling law and demonstrate its superior scaling efficiency over GD. Furthermore, we show that Muon can be interpreted as an implicit matrix preconditioner arising from adaptive task alignment and block-symmetric gradient structure. In contrast, the preconditioner with coordinate-wise sign operator could match Muon under oracle access to unknown task representations, which is infeasible for SignGD in practice. Experiments on synthetic long-tail classification and LLaMA-style pre-training corroborate the theory.

Applications · Computer Vision

Sheng Jiang, Lin Zhu, Runrui Li, Mei Wang, Qiannan Zhu, Yaoyao Zhong, Hua Huang

Handwritten mathematical expression recognition (HMER) remains challenging in real-world educational scenarios, even with recent advances in large vision-language models. While these models often achieve high accuracy in local symbol transcription, their reliability in capturing two-dimensional mathematical structure under realistic handwritten conditions is still poorly understood. We introduce a real-world handwritten benchmark covering 13 categories of structurally complex expressions with authentic writing artifacts. Evaluations on large models reveal a clear performance degradation as structural complexity increases, even when symbol-level accuracy is high. Most failures arise from structural mis-parsing and context-dependent symbol role confusion rather than pure visual perception errors. To mitigate this issue, we propose a training-free, schema-anchored structure-aware inference framework that decomposes recognition into schema identification, schema-constrained transcription, and context-driven disambiguation. Our method improves the ExpRate from 11.63\% to 24.52\% on Qwen-8B and generalizes well across multiple large models. Our benchmark provides a realistic evaluation for large models on handwritten mathematics, and our framework offers an effective and interpretable solution to structure-related failures in real-world HMER.

Deep Learning · Self-Supervised Learning

Woojun Jung, Susik Yoon

Tabular data within a domain often exhibit heterogeneous schemas yet shared semantics, posing a key challenge: determining what should remain invariant across tables and what should preserve instance-level distinctions. Existing token- or row-centric encoders conflate these roles, leading to schema sensitivity or weakened discriminability. We introduce the segment, a header–value pair, as an atomic unit that captures both functional roles and semantic content. Using value entropy, we treat low-entropy segments as domain anchors and high-entropy segments as entity-specific signals. We realize this design through Masked Segment Modeling and Entropy-driven Segment Alignment, which jointly enforce structured header–value coupling and selective semantic alignment. Experiments on in-domain heterogeneous tables demonstrate improved performance on discriminative and generative tasks, yielding stable and interpretable representations.

Esther Sun, Bo-Hao Su, Abinay Reddy Naini, Shinji Watanabe, Carlos Busso

Speech Large Language Models (SLLMs) enable high-level emotion reasoning, but often produce ungrounded, text-biased judgments without verifiable acoustic evidence. In contrast, SSL encoders such as WavLM yield strong acoustic representations yet remain opaque discriminative models that offer limited interpretability. To bridge this gap, we introduce the Agentic Decoding of Emotion via Probing Tools (ADEPT) framework, which reframes emotion recognition as a multi-turn inquiry process rather than a single-pass prediction. ADEPT transforms an SLLM into an agent that maintains an evolving candidate set and adaptively invokes dedicated semantic and acoustic probing tools within a structured pipeline of candidate generation, evidence collection, and adjudication. Crucially, ADEPT enables a paradigm shift from consensus learning to ambiguity-driven emotion reasoning. Since human affect exhibits complexity and co-occurrence of emotions, we leverage minority annotations as informative signals instead of discarding them as noise. Finally, we integrate Group Relative Policy Optimization (GRPO) with the Evidence Trust Gate to explicitly couple tool-usage behaviors with prediction quality and enforce evidence-based reasoning. Experiments demonstrate that ADEPT improves in most cases the primary emotion accuracy while substantially improving minor emotion characterization, producing explanations grounded in auditable evidence.

Yifei Li, Haixu Wu, Zeyi Xu, Tuur Stuyck, Wojciech Matusik

Learning-based methods have made significant progress in physics simulation, typically approximating dynamics with a monolithic end-to-end optimized neural network. Although these models offer an effective way to simulation, they may lose essential features compared to traditional numerical simulators, such as physical interpretability and reliability. Drawing inspiration from classical simulators that operate in a modular fashion, this paper presents Neural Modular Physics (NMP) for elastic simulation, which combines the approximation capacity of neural networks with the physical reliability of traditional simulators. Beyond the previous monolithic learning paradigm, NMP enables direct supervision of intermediate quantities and physical constraints by decomposing elastic dynamics into physically meaningful neural modules connected through intermediate physical quantities. With a specialized architecture and training strategy, our method transforms the numerical computation flow into a modular neural simulator, achieving improved physical consistency and generalizability. Experimentally, NMP demonstrates superior generalization to unseen initial conditions and resolutions, stable long-horizon simulation, better preservation of physical properties compared to other neural simulators, and greater feasibility in scenarios with unknown underlying dynamics than traditional simulators.

Social Aspects · Accountability, Transparency, and Interpretability

Mateo Espinosa Zarlenga

Concept-based models (CMs), deep neural networks that ground their predictions on representations aligned with human-understandable concepts (e.g., "round", "stripes", etc.), have been shown to learn representations that *leak* concept-irrelevant information. As the traditional narrative goes, this leakage is undesirable and should be eradicated as it leads to uninterpretable models. In this paper, we posit that this conventional view of leakage in CMs is not only ill-posed, as the evidence of how leakage makes a model less interpretable is often inconclusive, but also bound to lead to impractical CMs under common real-world constraints. Specifically, we argue that *in real-world settings where concept incompleteness is the norm, some leakage is often necessary for constructing accurate and intervenable CMs*. To this end, we propose that there is such a thing as *benign* leakage and show that, by optimizing a reframing of the typical CM training objective, CMs can encourage and exploit this form of leakage without sacrificing accuracy or intervenability.

Social Aspects · Accountability, Transparency, and Interpretability

Vacslav Glukhov

Treating the outcome of machine learning as a stable, identifiable artifact is implicit in language, tooling, and governance. This position paper examines whether a trained system admits context-appropriate criteria of identity. We show that neither functional behavior nor internal structure suffices: behavioral equivalence is underdetermined by finite data, while modern architectures admit multiple, structurally distinct realizations of the same function. Consequently, practices that treat learned systems as stable objects presuppose equivalence relations that are rarely made explicit. We do not propose abandoning such practices. Instead, we articulate the minimal conditions under which identity claims grounded in behavior, structure, or training process can be meaningfully interpreted, with implications for reproducibility, traceability, and governance.

General Machine Learning · Representation Learning

Diogo Soares, Pankhil Gawade, Andrea Dittadi, Ewa Szczurek

Evaluating representation similarity is fundamental to representation learning. However, existing metrics suffer from significant limitations: they are difficult to interpret due to shifting baselines, lack robustness to outliers, and are frequently computationally intractable for large datasets, forcing a reliance on heuristic approximations. To address these shortcomings, we develop an ordinal-similarity framework, instantiated by the Triplet (TSI) and Quadruplet (QSI) Similarity Indices, which measure alignment by quantifying the consistency of ordinal relationships. We provide a theoretical analysis demonstrating that this formulation is inherently interpretable, robust to outliers, and computationally efficient. Finally, we establish a formal equivalence between TSI alignment and the alignment of local neighborhood structures, as measured by Mutual Nearest Neighbors. Through empirical analysis, we validate these properties and show that ordinal similarity offers a scalable, practical approach to measuring alignment, enabling practitioners to better understand and design representations.

Social Aspects · Accountability, Transparency, and Interpretability

Emmy Liu, Varun Prashant Gangal, Chelsea Zou, Michael Yu, Xiaoqi Huang, Alex Chang, Zhuofu Tao, Karanpartap Singh, Sachin Kumar, Steven Feng

Despite numerous attempts at mitigation since the inception of language models, hallucinations remain a persistent problem even in today's frontier LLMs. Why is this? We review existing definitions of hallucination and fold them into a single, unified definition wherein prior definitions are subsumed. This position paper argues that hallucination can be unified by defining it as simply inaccurate (internal) world modeling, in a form where it is observable to the user. For example, stating a fact which contradicts a knowledge base OR producing a summary which contradicts the source. By varying the reference world model and conflict policy, our framework unifies prior definitions. We argue that this unified view is useful because it forces evaluations to clarify their assumed reference "world", distinguishes true hallucinations from planning or reward errors, and provides a common language for comparison across benchmarks and discussion of mitigation strategies. Building on this definition, we outline plans for a family of benchmarks using synthetic, fully specified reference world models to stress-test and improve world modeling components.

General Machine Learning · Representation Learning

Seonglae Cho, Zekun Wu, Adriano Koshiyama

Sparse Autoencoders (SAEs) decompose LLM activations into interpretable features, yet existing SAE-based steering methods require contrastive datasets or large activation stores. We introduce CorrSteer, which selects steering features by correlating task outcomes with SAE activations computed during generation, then validates these selections through intervention. This two-stage approach treats correlation as a selection heuristic and intervention as the causal test: features that both correlate with success and improve performance when amplified are retained. Coefficients derive from mean activations on correct samples, yielding a fully automated pipeline without task-specific tuning. On Gemma-2 2B and LLaMA-3.1 8B, CorrSteer achieves +3.3% on MMLU (4k samples) and +27.2% on HarmBench (108 samples), with lower side-effect ratios than fine-tuning despite comparable accuracy. Selected features cluster into interpretable categories: structured-output features for multiple-choice tasks, refusal features for safety, and domain-specific semantics for specialized benchmarks. The method scales to $10^5$ SAE features via streaming correlation ($O(1)$ in dataset size), requiring no backward passes or activation storage.

Social Aspects · Accountability, Transparency, and Interpretability

Zhuonan Yang, Jacob Xiaochen Li, Francisco Velez, Eric Todd, David Bau, Michael L. Littman, Stephen Bach, Ellie Pavlick

One of the most common complaints about large language models (LLMs) is their prompt sensitivity---i.e., the fact that their ability to perform a task or provide a correct answer to a question can depend unpredictably on the way the question is posed. We investigate this variation by comparing two very different but commonly-used styles of prompting: those using $\textit{instructions}$, which describe the task in natural language, and those using in-context $\textit{examples}$, which provide few-shot demonstration pairs to illustrate the task. We find that, despite large variation in performance as a function of the prompt, all the prompts we study engage the same common underlying mechanisms. Specifically, we identify task-specific heads that are interpretable in vocabulary space--- which we dub $\textit{lexical task heads}$---and show that these heads are shared across prompting styles and are essential to triggering subsequent answer production. We further find that behavioral variation between prompts can be explained by the degree to which these heads are activated, and that failures are at least sometimes due to competing task representations that dilute the signal of the target task. Our results together present an increasingly clear picture of how LLMs' internal representations can explain behavior that otherwise seems idiosyncratic to users and developers.

General Machine Learning · Transfer, Multitask and Meta-learning

Shuai Yi, Yixiong Zou, Yuhua Li, Ruixuan Li

Vision-Language Models (VLMs) such as CLIP demonstrate strong zero-shot generalization, but their performance significantly degrades in cross-domain scenarios with scarce target-domain training data (Cross-Domain Few-Shot Learning, CDFSL). In this paper, we focus on the target-domain few-shot finetuning in the CLIP-based CDFSL task. Prevailing finetuning paradigms uniformly align all image patch tokens with their corresponding textual embeddings. However, we find a counterintuitive phenomenon: actively pushing away certain low-similarity image tokens, termed “tail tokens”, from their textual embeddings consistently improves target-domain performance. We delve into this phenomenon and provide a novel interpretation: under great domain shifts and scarce training data, the model can hardly extract semantic information from visual inputs; therefore, the common belief of alignment is valid only for tokens already containing sufficient semantic information; for tail tokens, forcing the alignment would lead to excessive overfitting to the scarce training, while breaking the alignment is more useful. Motivated by this, we propose Adaptive Tail-Head Alignment (ATHA), a novel fine-tuning strategy for CLIP that transforms the conventional uniform alignment paradigm to an adaptive alignment paradigm, with both alignment strengthening and weakening. Extensive experiments on four challenging CDFSL benchmarks validate our state-of-the-art performance. Our codes will be released.

Deep Learning · Sequential Models, Time series

Qilin Wang

We argue that long-term forecasting requires learning local Jacobians with explicit spectral structure, going beyond simple conditional mean matching. Our method, \textsc{Fern}, invokes Brenier's theorem to directly parameterize the Jacobian as a symmetric positive semi-definite (SPD) factorization, treating forecasting as the optimal transport of probability mass from a fixed Gaussian source to data-dependent ellipsoids. This formulation reduces the computational cost of eigen-decomposition from cubic to linear time while providing interpretable, geometry-aware projections. To rigorously evaluate robustness, we introduce a synthetic benchmark with controlled non-stationary shocks alongside new metrics like Effective Prediction Time (EPT). \textsc{Fern} demonstrates exceptional stability, outperforming baselines like DLinear and Koopa by over two orders of magnitude (up to $790\times$) on nonstationary settings where standard benchmarks fail to expose model brittleness.

Social Aspects · Accountability, Transparency, and Interpretability

Hilal Aka, Joe Kwon, Noam Kolt

AI models readily refuse explicitly unlawful requests, but real-world illegality often depends on context. We evaluate frontier models on contextual illegality across four corporate law domains in which routine actions—editing documents, trading stock, requesting payment, approving communications—become unlawful due to triggers such as pending investigations or bankruptcy filings. We study both chat and agentic settings and compare results to a human baseline. The best-performing models achieved near-zero compliance with illegal requests while maintaining high compliance with legal ones, though performance varied sharply by domain. We also identify distinct failure modes such as excessive refusal of legal requests and find improved performance from reasoning models and agentic environments. By utilizing the structure of contextual illegality to create controlled evaluations, our methodology provides empirical grounding for emerging research on law-following AI and extends naturally to additional legal domains.

Applications · Robotics

Duc Nguyen, Nghiem Diep, Binh Nguyen Gia, Trong-Bao Ho, Doanh Le Thien, Quang Nguyen, Thien-Loc Ha, Tran Van Nhiem, Bao Thach, Tran Nhat 等

Vision–Language–Action (VLA) models enable general-purpose robotic control via large-scale multimodal pretraining, yet their effectiveness under few-shot imitation learning remains limited. We conduct a systematic stress test of state-of-the-art VLA models and show that performance degrades sharply as demonstrations are reduced, revealing a key weakness of existing adaptation strategies. To address this, we introduce FOCA, a future-oriented conditioning framework for data-efficient VLA adaptation. FOCA combines explicit prediction of task-grounded future interaction embeddings with implicit alignment to future goal observations, enabling long-horizon reasoning in latent space without pixel-level prediction. This formulation naturally supports action-free co-training with synthetic videos from video world models and can be interpreted as learning a future-conditioned value-like representation. Extensive experiments demonstrate FOCA achieves 95.7\% success with 20 demonstrations on LIBERO, improves 7–12\% on RoboCasa, and delivers up to 26\% absolute gains on real robots, establishing a new state of the art in few-shot VLA adaptation.

Theory · Probabilistic Methods

Yang Yang, Duo Zheng, Sandeep Jain, Kai Zhang, Ping-Shou Zhong

This paper introduces a new family of adaptive, distribution-free independence tests for multivariate random vectors based on binary expansion coefficients, supported by a tractable asymptotic theory. Our first key contribution establishes a general equivalence between independence testing and testing cross-covariances among exponentially many binary expansion interaction coefficients, applicable to broad sample spaces and not limited to kernel-induced representations. While this exponential interaction structure makes naive construction and computation infeasible, we overcome this challenge by reformulating the proposed tests as a class of U-statistics and deriving an explicit kernel representation that enables scalable and efficient computation. Exploiting the multiscale nature of binary expansions, the proposed framework automatically adapts to unknown dependence structures by selectively truncating higher-order interactions, yielding both strong power and clear interpretability. To further enhance power and computational efficiency, we introduce an adaptive weighted aggregation procedure, termed wa-dCoBET, which combines a baseline Covariance Binary Expansion Test (CoBET) with a distance-measure–based CoBET. Extensive simulations and a real-data application demonstrate that wa-dCoBET consistently matches or outperforms HSIC and distance covariance, particularly in higher-dimensional and non-monotone settings, while maintaining accurate type I error control.

Social Aspects · Accountability, Transparency, and Interpretability

Belinda Mo

AI systems are becoming autonomous research agents that generate hypotheses, design experiments, and produce discoveries at scales beyond human oversight. As seen by increased submissions to ML venues, the verification gap between scientific output and our ability to check it is already widening, and autonomous agents make it worse by magnitudes given human-agent asymmetry. We argue that science must evolve its verification infrastructure, as it has before with peer review. However, while historical adaptations assumed human contributors who could be questioned and sanctioned, AI agents break this assumption. We propose criteria for an adapted verification infrastructure that emphasizes observable-by-default workflows, scalable verification, and clear attribution. We argue that without adaptation, ML and any scientific domain using agents face dangerous failures: experimental results that no person can verify, optimization for metrics over understanding, and accountability vacuums that erode scientific trust.