Classification

Follow this topic Ask about this topic

Momentum

45 papers in the last four weeks, up 137% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 254

Sep 22, 2026cs.CL

How to Estimate Whether You Have Found Several Needles in a Haystack: Measuring Calibration in Multi-Label Text Classification

A key factor in deciding whether to trust an automatic prediction is its confidence score, which should be calibrated to match the actual probability of the prediction being correct. Most confidence calibration metrics target binary or multi-class tasks, while multi-label calibration remains largely underexplored. Multi-label classification tasks, such as assigning medical codes to clinical notes or determining news topics, are usually dominated by a large number of negatives, i.e., labels that do not apply. We show that existing binning schemes to compute label-wise expected calibration error either underestimate the error, simply reflect label frequency, or suffer from many bins with very few instances. To achieve trustworthy label-wise calibration errors, we propose a new binning scheme that gives equal weight to positive and negative label assignments. Our empirical study demonstrates that in contrast to existing binning schemes, our new scheme results in meaningful estimates of calibration error in hierarchical and in extreme multi-label classification. We also show that calibrating confidence scores of large language models for multi-label predictions is an open challenge. Our detailed analysis lays the foundation for further research by providing a solid evaluation metric for measuring calibration in multi-label classification.

Sophie Henning, Georg Hofmann, Alexander Schulte +2

TU Munich · Munich Center for Machine Learning (MCML) · LMU Munich +3

Multi-Label Classification Language Model Calibration Model Calibration Classification

Sep 21, 2026cs.LG

An Exact Junction-Tree Extended Formulation for Optimal Classification Trees

We develop an exact linear programming (LP) formulation for bounded-depth classification trees with binary features, using a junction-tree representation. The formulation is integral and supports recursive subtree optimization. Exact reductions make the model smaller while preserving the optimal value and recovery of an optimal tree. The reduced model supports two solution methods: column generation and message passing. Column generation solves integral restricted LPs and uses bounds over the full feasible domain to certify optimality. Message passing recursively combines optimal subtree costs. Both methods solve common subtree problems that, once the preceding tree decisions are fixed, can be evaluated independently and in parallel. Computational experiments show that the exact reductions substantially reduce the size of the junction-tree formulation. The resulting linear programming formulation certifies instances for which the tested mixed-integer formulation does not establish optimality within the same computational budget, while the column-generation and message-passing methods certify more instances and achieve an order-of-magnitude reduction in geometric-mean runtime relative to an existing state-of-the-art exact method for optimal classification trees.

Jiancheng TU, WenqiFan

Department of Computing, The Hong Kong Polytechnic University · Department of Management and Marketing, The Hong Kong Polytechnic University

Decision Tree Learning Classification Linear Programming

Sep 21, 2026cs.CL

Evaluating Decision Models for Text Annotation in Computational Social Science

Computational social science increasingly relies on large language models for text annotation, and the validity of published findings now rests on the labels generated by such models. Decision models, a new model class built for categorical question answering, answer typed questions with a choice, a probability distribution over the label set, and a confidence score rather than free text, at a small fraction of frontier inference prices. Whether their answers are accurate, and whether that stated confidence can be trusted on social science constructs, are unknown. Here, we mirror the evaluation of Ziems et al. (2024) on 18 computational social science classification tasks (7,977 items), comparing the first commercial decision model and two open-weight counterparts against 19 frontier and open-weight language models under the same zero-shot protocol, and extending the decision-model comparison to eleven open-weight systems released in the week after it. The decision model trails the per-task best LLM on 14 of 15 evaluation tasks, with a median deficit of 11.6 macro-F1 points, at a median 44 times lower measured cost. Its confidence is better calibrated than the verbalized confidence of 16 of the 19 LLMs, yet three frontier models show lower median calibration error (0.157 against 0.066). While items above 0.9 confidence are typically labeled accurately (median accuracy 0.815), on one task, empathy in peer-support dialogues, the model reports high confidence while performing near chance. Nonetheless, our results suggest that decision models are useful as a first step in the annotation pipeline: routing low-confidence items to an LLM matches or exceeds the LLM alone at a quarter to half of its cost.

Hazem Ibrahim, Yasir Zaki

Computer Science, New York University Abu Dhabi, Abu Dhabi, UAE

LLM Evaluation LLM-Assisted Annotation Computational Social Science Language Model Calibration Classification

Sep 20, 2026stat.ML

Density-Ratio Rescoring for Imbalanced Classification Using Raking Duals and Classifier Scores

Density-Ratio Rescoring (DRR) augments a classifier trained at the original class prior with a survey-raking dual score. Raking reweights the majority sample to match minority feature moments within a tolerance. DRR marginally standardizes the dual and base scores and combines them with a fixed weight of one half, using the fitted dual directly for prediction without resampling or refitting the base classifier. Under exact population matching and a correctly specified log-linear tilt model, the dual equals the log density ratio up to an additive constant. A class-separation analysis characterizes the signal strength and correlation conditions under which fusion improves separation under common within-class covariance. On 24 tabular benchmarks, evaluated over 30 trials and five base learners, DRR at the D=128 random-feature setting improves average precision over the standardized base on every dataset, with a mean gain of 0.034. It exceeds the shared-dual raking-and-relabeling resampler on 22 of 24 datasets, with a mean gain of

0.092

, and on all eight one-versus-rest tasks of a shared gene-expression cohort. These results demonstrate the effectiveness of using raking duals as reusable scores for improving rare-class ranking while retaining classifiers trained at the original prior.

Dongha Kim, Seunghwan Park

School of Mathematics, Statistics and Data Science, Sungshin Women’s University, 2, Bomun-ro 34da-gil, Seongbuk-gu, Seoul, 02844, Republic of Korea · Department of Information Statistics, Kangwon National University, 1, Kangwondaehak-gil, Chuncheon-si, Gangwon-do, 24341, Republic of Korea

Class-Imbalanced Learning Density Ratio Estimation Binary Classification Classification

Sep 17, 2026cs.LG

Alliance Beats Isolation: Unifying Heterogeneous Allied Datasets Improves Classifier Performance

In many application domains, such as student dropout, insurance fraud, loan approval, and machine failures, several labelled public datasets are available where (i) data is about the same type of objects but the set of actual underlying objects are disjoint; and (ii) the class labels are same; and (iii) the feature spaces of the datasets are largely distinct (heterogeneous), with a few shared features. We call such datasets as allied. A single classifier cannot be trained on both datasets together, and one classifier trained on one dataset cannot be tested on the other. In this paper, we propose a method to merge the feature-spaces into a single feature-space for a pair of given allied heterogeneous datasets. We then use a matrix completion method to create a unified dataset based on the merged feature-space. The hypothesis is that the merged representation facilitates the transfer of classification knowledge from one dataset to another. We conduct experiments on several pairs of allied, heterogeneous datasets and several classifiers to demonstrate that any classifier trained on the unified representation always outperforms classifiers separately trained on the constituent allied datasets on several pairs of allied datasets. This work provides an easy way to substantially improve classifier performance by unifying and using multiple allied datasets together.

Girish Keshav Palshikar

Cross-Domain Transfer Learning Classification Feature Fusion Cross-Dataset Generalization

Sep 16, 2026cs.CV

Decodable but Misrouted: Sparse Features Uncover a Readout Gap in Vision-Language Models for Harmful Meme Detection

When large vision-language models misclassify harmful memes, the failure may reflect missing internal evidence or an inability to route represented evidence to their outputs. We distinguish these cases in Gemma-3 and Qwen3.5 using sparse autoencoders, role-conditioned probes, causal interventions, and recovery experiments across six harmful content benchmarks, with additional Spanish and Hindi-English code-mixed evaluations. Sparse readouts outperform native prediction on all six primary binary tasks: Qwen averages

0.740

versus

0.432

for native macro-F1, residual reconstruction reaches

0.486

, and Gemma improves from

0.532

to

0.714

. These gains measure how accessible the label is to a supervised readout; they do not show that the model's native generation already applies such a decision rule. Under the evaluated scales, Qwen silent-feature ablation is

24-63

times more probe-sensitive, whereas routed-feature patching on literal yes/no tasks is

16-140

times more output-sensitive. Native-only threshold calibration explains much, but not all of the gap: on five tasks with matched probe scores, it recovers

69.8

% of the raw native-to-probe difference, while direct routing adds

0.094

mean macro-F1 beyond calibrated native scoring. Joint gold-label, probe-KL, and pairwise LoRA supervision improves dedicated FHM prediction, but a gold-only adapter performs better on the shared seven-task mean. A case study of Gemma-3-12B on the Facebook Hateful Memes dataset finds a distributed rank-32 image-prompt interaction, reaching

0.756

versus

0.685

native macro-F1. Robustness controls show that the signal is not explained solely by accompanying OCR and depends on paired visual evidence, and that it extends beyond English. In many of the errors we study, the evidence is represented but does not reach the answer; therefore, routing is a common bottleneck in harmful meme classification.

Girish A. Koushik, Diptesh Kanojia, Helen Treharne

Nature-Inspired Computing & Engineering Department of Computer Science University of Surrey Guildford, United Kingdom · Surrey Centre for Cyber Security Department of Computer Science University of Surrey Guildford, United Kingdom

VLM Evaluation VLM Robustness VLM Interpretability Classification

Sep 16, 2026cs.CL

Fallacy Benchmarks Measure Scheme Recognition, Not Fallacy Detection

Fallacy-detection benchmarks pair fallacy classes with a single "valid" or "none" class that takes everything data collection did not label as a fallacy. A detector has two jobs, deciding whether an argument is fallacious and naming which fallacy it commits, and the false-positive rate is meant to measure the first. We show that what these benchmarks actually score is scheme recognition, the ability behind the second job. Their own test sets already show it: when a classifier misses a fallacy, the error lands on "none" rather than on another fallacy type, so detection is failing while classification holds. The reason is what the valid class lacks. The negatives that separate the two jobs are correct arguments using the same argumentation scheme as a fallacy, and they are scarce: nearly absent from the four benchmarks we examined, and rare even under deliberate search. A detector is therefore never tested where recognizing a scheme and judging its use come apart, and can pass on recognition alone. We construct the missing arguments, together with a control condition from the same pipeline that differs only in scheme, so whatever generation contributes, it contributes to both. The classifier labels the scheme-matched negatives as the source fallacy, and labels the wrong-scheme negatives as the scheme they actually use 85.9% of the time and as the source type 0.4%. The classifier has learned which scheme an argument uses, not whether it uses it correctly. The over-flagging follows: a model that scores 16.6% on CoCoLoFa's own valid class flags 58.9% of the constructed arguments. The same dissociation appears in three zero-shot LLM detectors that never saw these benchmarks. We release the items as Scheme Foils. A reported false-positive rate should not be trusted as a measure of detection until the valid class has been audited for scheme-matched coverage.

Navyansh Singh, Animesh Pathak, Aarav Singh

IIIT Naya Raipur

Argument Mining Computational Argumentation Classification Benchmark Validity

Sep 16, 2026cs.LG

How Many Labels Does Model Choice Need? Certificates and Budgets for Selective Prediction

Classifiers can make identical predictions yet require labels to compare their selective performance: confidence ranks weight the same errors differently. We quantify this requirement for the area under the generalized risk-coverage curve (AUGRC). A prelabel lower bound rules out insufficient budgets. With all labels known, a covering linear program bounds the minimum number of labels sufficient to fix the winner (the certificate size) within

K-1

labels for

K

candidates. For fixed

K

, independent uniform orders and identical predictions, the prelabel bound approaches one quarter of the pool. With iid Bernoulli errors independent of the orders, every exact acquisition policy reads almost all labels asymptotically, although a two-candidate certificate needs only half. Across 108 feature-panel comparisons on nine datasets, disagreement labels settle every accuracy choice but no AUGRC choice. A 20% budget is ruled out in 96 conditions; certificates need 56-57% on average. On ten conditions with pretrained image classifiers, confidence-score choice reads 68-91% of 10,000 labels for exact selection and 50-67% with AUGRC tolerance

5\times10^{-4}

. An exact stopping test works with any acquisition order. Together, these results link confidence ranks to label budgets and certified model comparison.

Tetsuji Kuboyama

Computer Centre, Gakushuin University

Model Selection Selective Prediction Classification Statistical Learning Theory

Sep 14, 2026stat.ML

Learned Look-Ahead Splitting Rule for CART

Classification and regression trees are typically constructed using a greedy splitting rule that maximizes the immediate reduction in prediction error at each node. Although this strategy is computationally efficient, it can miss splits that yield small short-term gains but create substantial downstream improvements after further partitioning. We propose a look-ahead tree-building method that evaluates each candidate split by the prediction error reduction achieved after growing a conventional CART subtree below that split. Because the full look-ahead procedure can be computationally expensive, we also describe a smart look-ahead algorithm that learns downstream split values using node-level features. The proposed framework preserves the interpretability of recursive partitioning while improving split selection in hierarchical or interaction-driven settings. We conduct a simulation study comparing conventional, full look-ahead, and smart look-ahead methods under several settings and apply the proposed methods to analyze two real data examples demonstrating the merit of the new methods.

Andrew Gao, Tianlin Liu, Ruichen Han +1

Thomas Jefferson High School for Science and Technology, Alexandria, VA 22312, USA · Lynbrook High School, San Jose, CA 95129, USA · Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, USA

Decision Tree Learning Classification

Sep 14, 2026cs.CV

HemaHier: Chain-Conditioned Ordinal Hierarchies for Lineage-Aware Bone-Marrow Cytology

Bone-marrow cytology is inherently structured: each cell belongs to a hematopoietic lineage, and many cell types lie on ordered maturation trajectories. Standard flat classifiers ignore this structure, treating a mild same-lineage confusion the same as a severe cross-lineage mistake and predicting only discrete labels. We propose HemaHier, an ordinal-hierarchical prediction head for a frozen or lightly adapted cytology foundation model. Its central component is a chain-conditioned maturity score that reads a single maturity value under a per-chain query, supervised only on biologically valid healthy chains, while dysplastic and off-chain cell types remain classes but are excluded from maturity supervision. Fine and lineage predictions are coupled through a shared posterior that guarantees hierarchical consistency, and a staged objective first stabilizes recognition, then adds lineage and maturity supervision. On three bone-marrow datasets under a shared ontology, HemaHier achieves competitive recognition while reducing biologically severe errors and adding a within-lineage maturity ordering that flat classifiers lack. Code is available at https://github.com/xmindflow/HemaHier.

Afshin Bozorgpour, Peter Schüffler, Edgar Jost +1

Faculty of Informatics and Data Science, University of Regensburg, Germany · Institute of Pathology, TUM School of Medicine and Health, Technical University of Munich, Germany · Munich Center for Machine Learning, Germany +4

Computational Pathology Hierarchical Classification Ordinal Regression Classification

Sep 14, 2026cs.CV

Learning Sign Language Recognition under Label Noise: A Study of Noise-Robust Losses for Isolated and Continuous Settings

In sign language recognition, the isolated (ISLR) classification loss treats a single label as ground truth, as does the frame-level auxiliary classifier over pseudo-labels we add to continuous (CSLR) methods, which lack one. Stylistic variation blurs ISLR annotation and the lack of temporal boundaries in CSLR forces pseudo-labels; both are noisy. We therefore apply symmetric and generalized cross entropy (SCE, GCE), robust alternatives to cross entropy (CE) from image classification, not to connectionist temporal classification but to the preceding single-label classifier. On ASL Citizen with injected symmetric noise on three backbones (three seeds for ST-GCN), robust losses cost at most 2.5 pt when labels are clean and beat CE by 2.9-10.0 pt in all six conditions at noise rate 0.2, one of which only after q was re-selected on dev. GCE gains more, but its optimal q does not transfer across backbones, whereas one SCE setting works in all nine conditions; both vary 2-11 times more than CE across runs, so a favorable point estimate does not establish stability. For CSLR (PHOENIX-2014) we report no gain; our frame-level targets carry a systematic assignment bias, making that study a diagnosis of a single configuration. At lambda_aux = 25 the pseudo-label CE auxiliary raises word error rate above the no-auxiliary baseline on VAC, CorrNet and SlowFastSign, and GCE/SCE improve on CE by 1.7-3.2 pt (three of six conditions return below that baseline). However, the three losses differ by more than an order of magnitude in effective gradient at a common lambda_aux: matching the initial gradient shrinks the gap to 0.4-0.9 pt, and lowering the CE weight alone already beats that baseline, so neither the degradation nor the improvement can be separated from the effect of the weight. We use only symmetric noise; multi-seed evaluation covers only ST-GCN and VAC isolated.

Akihisa Shitara, Yoichi Ochiai

R&D Center for Digital Nature, University of Tsukuba · Faculty of Library, Information and Media Science, University of Tsukuba · Pixie Dust Technologies, Inc.

Noisy-Label Learning Robust Loss Functions Classification Sign Language Recognition

Sep 12, 2026cs.LG

Adaptive Margin Ordinal Loss: Penalizing Center-Class Hedging in Ordinal Classification

Standard cross-entropy loss causes neural networks trained on ordinal classification tasks to hedge predictions toward center classes, a failure mode we term \emph{center-class hedging}. This occurs because predicting the middle class minimizes expected symmetric loss, making it the path of least resistance regardless of the true label. Existing ordinal losses address related problems such as large-error penalization and rank consistency, but none directly suppresses center-class hedging as a function of where the true label lies relative to the ordinal center. We propose the Adaptive Margin Ordinal Loss (AMOL), a multiplicative weight applied to per-class loss terms of the form

m(k,y) = 1 + \alpha \cdot (1 - |k-c|/c) \cdot (|y-c|/c)

, where

c

is the center class,

k

is the candidate class, and

y

is the true label. The weight encodes a joint condition: it is large only when the candidate class is near center and the true label is far from center, collapsing to standard behavior otherwise. We further introduce the Center-Hedging Rate (CHR) as a diagnostic metric that directly quantifies this failure mode. Across four ordinal classification benchmarks and five random seeds, AMOL achieves the best or tied-best Quadratic Weighted Kappa (QWK) on all four datasets compared to cross-entropy, OLL, and SORD baselines. An asymmetric variant (AMOL-asym) eliminates center-class hedging entirely on the Abalone dataset (

\text{CHR} = 0.000 \pm 0.000

across all five seeds,

n \approx 266

extreme-class test samples per run), compared to

0.074 \pm 0.005

for standard cross-entropy.

Manisha Kandel

Data Science Institute & Department of Civil, Construction & Environmental Engineering University of Delaware Newark, DE, USA

Ordinal Regression Adaptive Loss Weighting Classification

Sep 12, 2026cs.LG

Counterfactual Marginalisation: Framework for Evaluating Robustness to Nuisance Variables

Machine learning models can achieve strong test performance while relying on demographic or acquisition-related shortcuts. We propose counterfactual (CF) marginalisation as a test-time evaluation procedure for assessing robustness of classification models to such variables. Given a CF image generator, we intervene on nuisance parent variables such as age or sex, generate CF versions of each test image, and average predictions over a target intervention distribution. This produces intervention-aware predictions that marginalise demographic effects while preserving patient-specific latent information. We use these predictions to define metrics for CF risk, calibration, stability and worst-case sensitivity. We demonstrate this framework's utility for quantitative robustness evaluation.

Yasin Ibrahim, Hermione Warr, Robin J. Evans +1

Department of Engineering Science, University of Oxford, Oxford, UK · Department of Statistics, University of Oxford, Oxford, UK

Counterfactual Evaluation Classification Spurious Correlation Robustness

Sep 11, 2026cs.LG

Relatively Smart II: Tractable or Semi-Supervised Instance-Optimal Learning

We continue the study of relatively smart learning, introduced by Dughmi and Pour (2026), which asks a supervised learner to compete, marginal by marginal, with every distribution-fixed error guarantee soundly certifiable from unlabeled data. They showed that the One-Inclusion Graph (OIG) learner is relatively smart with a quadratic sample-complexity blowup, and that no relatively smart learner can do better, leaving open whether ERM or another natural or tractable learner achieves comparable guarantees. They also left open whether the blowup can be restricted to unlabeled data. Our firs results shows that ERM---and in fact any proper consistent learner---is relatively smart for binary classification in the distribution-free setting. We show that a small certifiable error with

m

samples implies a similarly small error on the uniform distribution over a random sample of size

O(m^2)

, yielding a cover of size at most

2^{m+1}

on that sample. This suffices to control the error of proper consistent learners with

O(m^2)

samples. We then show that semi-supervised relatively smart learning is information-theoretically possible with a quadratic blowup only in unlabeled sample complexity and no blowup in labeled sample complexity. The learner uses a natural generalization of OIG to a leave-most-out transductive problem, where labels of part of a finite pool are revealed and the remaining labels are predicted. Finally, this label efficiency comes at a cost in simplicity and tractability. If the hypothesis class is accessed only through an agnostic ERM oracle, any semi-supervised relatively smart learner with substantially sub-quadratic labeled-sample blowup requires super-polynomially many oracle calls. This holds even when the marginal is given explicitly, and thus also yields an intractability result for distribution-fixed learning that may be of independent interest.

Shaddin Dughmi, Alireza F. Pour

University of Southern California · University of Waterloo

Classification Semi-Supervised Learning Statistical Learning Theory

Sep 9, 2026cs.LG

CoGe-GCD: Reframing Generalized Category Discovery with Compositional Generalization

Generalized Category Discovery (GCD) assigns unlabeled instances, mixed with labeled data, to known or novel categories, requiring human-like compositional reasoning: reusing primitives learned from known classes and deciding when new combinations imply new categories. Existing GCD methods operate on unstructured token features and struggle to extrapolate to novel compositions. We propose CoGe-GCD, which rethinks GCD through compositional generalization with two coupled stages. (i) Compositional Perception structures patch tokens by mapping them to a small vocabulary of primitives and refining token embeddings via competitive token-primitive assignment and information passing, yielding coherent groups for discovery. (ii) Generalizing Induction exploits the induced geometric structure and applies a structure-preserving calibration over spatial relations, maintaining probabilistic semantics while improving extrapolation to unseen primitive combinations. CoGe-GCD is implemented as an inductive-bias module between backbone and projection head, without modifying heads or losses, and can be plugged into diverse GCD frameworks. On standard benchmarks, it consistently improves all-class accuracy, unknown-class number estimation, and geometric quality, with marginal computational overhead. Code is available at https://github.com/lytang63/CoGe-GCD.

Luyao Tang, Jiewei Zheng, Kunze Huang +3

The University of Hong Kong, Hong Kong SAR, China · Xiamen University, Xiamen, China · Shenzhen University, Shenzhen, China.

Geometric Representation Learning Classification Compositional Generalization Generalized Category Discovery

Sep 9, 2026cs.CL

ProbPlug: A Plugin Uncertainty Network for Reliable Confidence in LLM Binary Classification

Large language models (LLMs) have achieved strong performance across a broad range of classification settings, yet the reliability of their predictions remains a major obstacle to deployment in high-stakes scenarios. Although confidence estimation for LLMs has been widely studied, confidence calibration for LLM-based classification remains underexplored. We introduce ProbPlug, a lightweight confidence estimation framework for LLM-based binary classification, which predicts whether an output is correct using internal token features extracted from a frozen LLM. ProbPlug employs a self-attention module to aggregate hidden representations and can be integrated into the original inference pipeline without modifying the base model. Experiments across multiple tasks involving both text-based and multimodal large models show that ProbPlug provides more reliable confidence estimates, improves classification performance with negligible additional overhead, and exhibits strong generalization across tasks. These results indicate that ProbPlug serves as a practical solution for confidence estimation in LLM-based classification. Our code is publicly available at Github.

Jianzong Wang, Chuhang Liu, Botao Zhao +6

Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, China · Tsinghua Shenzhen International Graduate School, Shenzhen, China · Hubei University of Technology, Hubei, China

Confidence Estimation in Language Models Language Model Calibration LLM Reliability Classification LLM Uncertainty Estimation

Sep 9, 2026cs.LG

Positional task conditioning for scalable defect detection across product families in large product catalogs

Product families in large product catalogs suffer from inconsistencies such as duplicates and unit mismatches that degrade customer experience. Detecting these requires reasoning over multiple error types across lengthy product listings, where LLM classification quality degrades due to long-context limitations. We address this by decomposing detection into focused sub-tasks that reduce context and isolate error types, improving F1 from 52% to 87%. For scalable deployment, we introduce Positional Task Conditioning (PTC), which distills this capability into a single smaller model by reinforcing task identity at structural prompt boundaries. PTC outperforms rationale-based distillation across five models and two architecture families, achieving within 1.79% F1 of the frontier at upto 98% lower cost. Our system is deployed across multiple countries processing 10+ million product families.

Soham Satyadharma, Gabriel Roccabruna, Suleiman A. Khan

Amazon Catalog AI

Language Model Distillation Classification E-Commerce

Sep 8, 2026cs.CV

Vision-language models know more about agriculture than they show and rubric-grounded verifications close the gap

Vision-language models (VLMs) show promise for agricultural classification, but zero-shot performance on disease, pest, damage, quality, and species identification remains poor, and it is unclear whether this reflects weak visual features or a failure to connect them to domain knowledge. We build a benchmark of 116 datasets, 834 classes, and 8,324 images spanning these tasks to isolate where the gap arises. Linear probing shows VLM vision encoders already encode agricultural features nearly as separable as a self-supervised DINOv3 baseline, ruling out weak visual representations as the primary bottleneck. Conditioning each model on an oracle reference description (an upper bound on its parametric knowledge) closes most of the gap left by an unaided lower bound, showing VLMs already know more about agriculture than they show. To close this gap without an oracle description at inference time, we structure test-time reasoning around a fixed, per-task diagnostic rubric: the model generates

K

candidate responses and a Probabilistic Pivot Tournament (PPT) verifier, scored pairwise against the rubric, selects the best one. This nearly doubles judged F1 over the lower bound and matches or exceeds the upper bound on several tasks, notably pushing Gemma 4 E4B-it's disease F1 to 0.71, above its own upper bound of 0.60. However, the verifier's letter-scale confidence score has the opposite of its intended effect: filtering to its most confident predictions does not improve accuracy and correlates negatively with correctness across every model and pool size tested, so the score cannot serve as a measure of predictive uncertainty, and most of the observed gain likely comes from rubric-grounded generation rather than pairwise verification.

Earl Ranario, Jared Smith, Lars Lundqvist +2

University of California, Davis

Agricultural Image Analysis Plant Disease Classification VLM Reasoning Classification Rubric-Based Evaluation VLM Calibration

Sep 8, 2026cs.LG

Certified Topological Interaction in Neural Representations: Class Disentanglement Is Mostly Pairwise

Class disentanglement (the separation of a representation's class-conditional point clouds along depth and over training) is usually read off descriptive curves. We measure it as certified topological interaction between labeled point clouds, using the recently introduced Intersection Euler Characteristic Profile: the Euler characteristic of the overlap of the clouds' ball unions as a function of scale, computed by one Alpha-complex sweep with no boundary-matrix reduction. Every number carries a test: exact permutation tests in both directions, a guarded separation certificate, and a paired test for the comparative claims applications make. Across 111 trained networks and 52,650 certified measurements, disentanglement is depth-graded and concentrated in the first epochs, and interaction quotients rank class pairs by confusability (Spearman rho=0.83), on par with cheap separability statistics. In a 96-model factorial population, augmentation is the one training choice that separates classes relative to chance; weight decay compresses the overlap without separating, and depth and width do nothing. The structural finding is one only a k-fold statistic can pose: the joint entanglement of a class triple sits below that of its strongest pair in 97% of triple-layer cells and 99.5% of deep cells, far below a measured null floor, in vision encoders and frozen language models alike. This pairwise dominance is a regularity, not a law: expected from the nesting of overlaps but not forced by geometry, present at initialization and in raw pixels, and manufactured in the last stage alone when a network memorizes random labels. The unnormalized profile mass predicts test accuracy (R^2=0.94), the quotient does not, and neither beats a linear probe. One lesson is reported in full: the paired test must use a scale-free statistic, or it certifies feature-norm dynamics as disentanglement.

Sushovan Majhi

Data Science Program, George Washington University, Washington, D.C., USA.

Disentangled Representation Learning Neural Representation Geometry Representation Disentanglement Classification

Sep 7, 2026cs.IT

A Fundamental Limit in Decentralized Decision-Making

In decentralized decision-making, several agents connected according to a network graph aim at solving a classification problem by collecting streaming observations. Due to decentralization, they run an iterative algorithm where, at each iteration, they can only exchange information locally with their neighbors. While decentralized estimation solutions have been shown to match the performance of optimal centralized systems, we show here that surprisingly this conclusion does not hold for decentralized decision-making. Specifically, we prove that the error probability for the best decentralized decision strategy exhibits an irreducible loss with respect to the optimal centralized classifier. This result establishes a fundamental limit for the performance of any decentralized decision strategy. We obtain an analytical relation showing that this limit is related to the interplay between decentralization and classification. The first aspect appears through the distances between the nodes in the graph, while the second aspect plays through the moment generating functions of the likelihood ratios that describe the decision problem. By applying the derived closed-form relation to different network topologies and inference problems, we observe some interesting and perhaps unexpected behavior emerging. In particular, we characterize the scaling law (with the network size) for the loss over popular network topologies, showing that the error probabilities might differ by orders of magnitude; and we examine how performance is affected by the relative distance between informative and uninformative agents over the graph.

Marco Carpentiero, Felice Scala, Vincenzo Matta +1

Department of Information and Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, I-84084 Fisciano (SA), Italy · Institute of Electrical and Micro Engineering, EPFL, CH-1015 Lausanne, Switzerland

Classification Distributed Inference Information-Theoretic Lower Bounds

Sep 6, 2026cs.LG

Learning Kernels by Alignment for Multiclass Bayes Classification

Kernel methods separate data representation from decision-making, but typically require the kernel to be chosen in advance. We show that this kernel can instead be learned by alignment, and develop the resulting framework through the recently introduced Collaborative Learning and Inference (CLaI). We show that Collaborative Learning can be viewed as a kernel alignment process, in which an embedding is trained so that its induced similarity matches a label-derived target kernel. We also prove that Collaborative Inference is equivalent to kernel Bayes classification with Parzen-window density estimation. Motivated by these perspectives, we generalise CLaI by replacing cosine similarity with a learned Mahalanobis distance and extend it to multiclass classification. On CIFAR-10, PathMNIST, and SleepEDF, the Mahalanobis formulation improves accuracy, converges faster, and yields lower calibration error than the cosine-based variant. Auxiliary experiments further support these connections, showing that CLaI produces latent signals of the same form as a Gaussian process, while achieving competitive calibration on sepsis prediction. Together, these results establish a principled learned-kernel framework that unifies representation learning, kernel alignment, and Bayesian classification, and extends naturally to the multiclass setting.

Hollan Haule, Javier Escudero

Bayesian Inference Metric Learning Multiclass Classification Classification Kernel Methods

Sep 3, 2026cs.CL

Chiaroscuro for Emotions: A Contrastive Emotion Benchmark Grounded in Appraisal Theory

Emotion recognition benchmarks often predict one emotion per text, missing many real-world scenarios where two people arrive at opposing emotions from a single shared event. For example, a child kicks the seat in front of her in excitement while the passenger ahead grows angry. We introduce CHIARO, a 1,000 human-annotated sentence benchmark for contrastive emotion inference grounded in appraisal theory. Each scene describes one causal trigger eliciting a positive emotion in one person and a negative emotion in the other, drawn from a ten-class taxonomy. We benchmark seven frontier LLMs and four off-the-shelf emotion classifiers. The strongest LLM reaches 67.3 macro-F1, well below human agreement, while existing emotion classifiers score near chance. Beyond evaluation, CHIARO also serves as a training signal. When combined with an existing emotion corpus, the resulting downstream classifier improves on CHIARO itself and on six of ten external emotion benchmarks, which positions our dataset as a complementary signal for emotion recognition.

Divyesh Bommana, Mohammad Saim, Tianyu Jiang

University of Cincinnati

LLM Evaluation Classification Emotion Recognition

Sep 1, 2026cs.CL

From Confusion to Clarity: Confusion-Aware Retrieval and Knowledge Injection for Text Classification

Large language models (LLMs) struggle to classify text into taxonomies with many semantically similar labels, as the distinctions are domain-specific and not captured by pre-training. To handle large label spaces, a common approach retrieves top-

K

candidate labels by embedding similarity and prompt the LLM to choose among them. However, top-

K

retrieval reduces the number of candidates but does not help the model tell similar ones apart. When two similar labels both appear as candidates, the model lacks the signal to choose correctly between them. We propose a framework that (1) identifies which label pairs the model struggles to distinguish, (2) expands the candidate set to include confusable labels, and (3) generates targeted rules to differentiate between similar candidates. The framework requires no fine-tuning, and the generated rules transfer to smaller, cheaper models. On three benchmarks (WOS, Flipkart, LEDGAR), our approach improves Macro F1 by up to 10.0pp over retrieval baselines, with smaller models (2B--20B) gaining up to 11.5pp via cross-model transfer.

Manish Gupta, Chaitanya Giri, Jayasimha Talur

Amazon

Zero-Shot Text Classification Retrieval-Augmented Classification LLM Prompting Text Classification Classification

Sep 1, 2026cs.LG

One-Layer Transformer Provably Learns Multiclass One-Nearest Neighbor in Context

We extend recent work establishing an equivalence between one-layer transformers and nearest-neighbor classifiers in the binary setting to the multiclass case. By leveraging the simplex encoding, we show that one-layer transformers with an argmax classification head behave identically to a one-nearest-neighbor classifier in the multiclass setting. This closes a gap left by prior work, whose multiclass result relied on a non-standard rounding-based approach rather than the typical argmax head used in practice.

Skanda Athreya, Yutong Wang

James B. Conant High School · Hoffman Estates, IL · Illinois Institute of Technology +1

Transformer In-Context Learning Multiclass Classification Classification k-Nearest Neighbors

Sep 1, 2026cs.AI

Few-Shot Out of Domain Intent Detection with Covariance Corrected Mahalanobis Distance

Conversational agents like chatbots and voice assistants are trained to understand and respond to user intents. On encountering an utterance with an intent different from the ones they have been trained on, these agents are expected to classify the intent as unknown' or out of domain'. This problem is known as out of domain (OOD) intent detection. Podolskiy et al. (2021), showed that Mahalanobis distance can be used effectively for identifying OOD intents, outperforming competing approaches. However, their method fails to outperform the baselines in the practically important few-shot setting. In this paper we analyze the reason for low performance and propose a covariance corrected Mahalanobis distance for detecting out-of-domain intents.

Jayasimha Talur, Oleg Smirnov, Paul Missault

Amazon

Mahalanobis Distance Intent Classification Few-Shot Learning Classification OOD Detection

Sep 1, 2026stat.ML

Semi-Supervised Classification with Informative Missing Labels in Weibull Mixture Models

We consider semi-supervised classification from a partially classified sample arising from a two-component Weibull mixture. The feature is observed for all data, whereas some class labels are missing. The probability of a missing label is modelled as a function of classification uncertainty, giving a feature-dependent missing-at-random (MAR) mechanism that shares parameters with the Weibull-mixture classifier. The missing-label indicators can therefore provide information about the classifier in addition to the observed features and available class labels. Under a common Weibull shape, a Bayes' rule has at most one positive decision boundary, which is unique when the rule is nonconstant; under unequal shapes, it can have two. We characterise these decision regions, derive the Fisher information for the classifier after adjustment for nuisance parameters in the missingness model, and obtain a decision-boundary expansion of the expected error rate of the plug-in sample rule relative to the Bayes error. The expansion yields classification-specific asymptotic relative efficiency formulas for the one- and two-boundary cases and shows that a positive-definite increase in Fisher information is sufficient, but not necessary, for a smaller first-order expected error rate. Numerical studies and a semi-synthetic analysis based on hard-drive failure data illustrate potential reductions in expected error rate and improvements in decision-boundary estimation from modelling feature-dependent label missingness.

Jinran Wu, You-Gan Wang, Geoffrey J. McLachlan

The University of Queensland, Australia

Learning with Missing Data Binary Classification Classification Semi-Supervised Learning

Aug 31, 2026stat.ML

Informative Label Missingness in Multiclass Classification Information Geometry and Excess Risk

Informative label missingness can change the usual efficiency ordering between completely and partially labelled classifiers because the pattern of missing labels may itself carry information about the classification model. We develop a general likelihood-based theory for this phenomenon in parametric multiclass classification. An efficient-information decomposition separates information lost through unavailable class memberships from information contributed by the missing-label mechanism. We then derive a quadratic expansion of plug-in excess risk over the active pairwise faces of the multiclass Bayes boundary, showing that classification efficiency depends on how information gains and losses align with directions that perturb the decision boundary. This yields a classification-weighted generalized-eigenvalue criterion under which informative partial classification may have smaller asymptotic classification risk without globally dominating complete classification in Fisher information. Near missing completely at random, with the marginal missing-label proportion fixed, redistribution of missing labels changes lost class-label information at first order, whereas efficient information from the missingness pattern appears only at second order. Three-class quadratic discriminant calculations, finite-sample experiments, and a semi-synthetic multiclass application illustrate the resulting regime-dependent behaviour.

Fariborz Setoudehtazang, Geoffrey J. McLachlan

Dipartimento di Scienze Statistiche, Universit`a di Padova, Padova, Italy · School of Mathematics and Physics, The University of Queensland, Australia

Information Geometry Learning with Missing Data Multiclass Classification Classification Statistical Learning Theory

Aug 30, 2026cs.LG

Forget or Fine-tune? A Comparative Study of Machine Unlearning Strategies for Noisy Label Correction

Noisy labels remain a critical challenge for training deep neural networks, since memorizing incorrect labels degrades generalization. Once noisy samples are identified after training, the standard solution is to retrain the model from scratch on the cleaned dataset, which is increasingly expensive as datasets and models grow. Machine Unlearning (MU) has recently emerged as a computationally efficient alternative, but the relative effectiveness of different MU strategies for noisy-label correction remains poorly understood. In this work, we conduct a comparative empirical study of five MU methods (NegGrad, Fine-Tuning (FT), Random Labeling (RL), SalUn, and MUNBa) across symmetric, asymmetric, instance-dependent, and open-set noise on CIFAR-10, CIFAR-100, and the real-world noisy dataset Food-101N. Our central finding is that the appropriate unlearning strategy is conditioned on the noise structure. Simple FT is a strong baseline across most closed-set scenarios; RL and SalUn are the most consistently robust methods and, under instance-dependent noise, approach retraining accuracy at a fraction of the computational cost; MUNBa shows advantages mainly under extreme symmetric noise. Under open-set noise, in contrast, we show that retraining on the cleaned subset degrades accuracy relative to the noisy baseline, so approximating the retrained model is not an adequate objective in this regime. On Food-101N, all MU methods remain competitive and achieve accuracies close to retraining despite reducing runtime by an order of magnitude. These findings provide practical guidelines for selecting MU strategies for post-training noisy-label correction.

João L. P. Santana, Filipe R. Cordeiro

Department of Computing Universidade Federal Rural de Pernambuco, Brazil

Noisy-Label Learning Classification Learning with Noisy Labels Machine Unlearning Machine Unlearning Evaluation

Aug 30, 2026cs.LG

Multiclass Linear Perceptrons with Multiplicative Margins

This paper introduces a family of multiclass linear Perceptron classifiers with a multiplicative margin mechanism (MMPerc), as an alternative to standard margin-free and additive margin Perceptrons. The multiplicative formulation enforces classification confidence by requiring the true class score to exceed that of competing classes by a specified fraction of itself, rather than by a fixed additive threshold. This avoids dependence on score magnitudes arising from varied norms of data and class weight vectors. We propose several architectural and algorithmic variants of MMPerc, derive associated loss functions and mistake bounds for both linearly separable and non-separable data, and analyze key design considerations, including bias, margin threshold selection, and training modes. Extensive experiments on synthetic and real datasets show that MMPerc classifiers typically outperform the standard Perceptron, as well as classic baselines such as Support Vector Machines and Ridge classifiers. Owing to their simplicity, minimalistic design, and computational efficiency, MMPerc classifiers are promising candidates for conventional machine learning tasks, linear evaluation of Deep Neural Networks, integration with Hyperdimensional Computing / Vector Symbolic Architecture representations, and deployment in resource-constrained applications.

Dmitri Rachkovskij, Evgeny Osipov, Olexander Volkov +2

Department of Computer Science, Electrical and Space Engineering, Luleå University of Technology, 971 87 Luleå, Sweden · Institute of Information Technologies and Systems, 03187 Kyiv, Ukraine · Centre for Data Analytics and Cognition, La Trobe University, Melbourne, Australia +2

Multiclass Classification Classification

Aug 17, 2026cs.LG

J-Miner: Recovering the Decision Logic of Fine-Tuned LLM Classifiers as Compact Rules

Task-fine-tuned large language model (LLM) classifiers acquire task-specific decision knowledge, but this knowledge remains implicit in distributed internal computations, making their decision logic difficult to interpret. We introduce the Executable Decision Compression (EDC) framework and propose J-Miner, which mines vocabulary-named variables from internal readouts and learns rules shared across inputs to produce executable explanations. Analysis reveals that a small set of these variables captures much of the classifier's decision behavior, holding for both varying parameter scales within a family and distinct families. Across six binary tasks, a rule using just one variable reproduces 76.7% of source-classifier decisions on average, rising to 88.8% with 16 variables. Most of the decision information retained by these variables comes from internal activations beyond literal surface matching. A lightweight text reader predicts the variable states, allowing the same fixed rules to execute independently of the source classifier.

Yunfan Gao, Xinyi Huang, Tao Sheng +3

Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University · Shanghai Key Laboratory of Data Science, College of Computer Science and Artificial Intelligence, Fudan University · Meituan +1

LLM Interpretability Interpretable ML Classification