Uncertainty Decomposition via Cyclical SG-MCMC and Soft-label Learning for Subjective NLP

• URL: http://arxiv.org/abs/2605.24773v1
• Date: Sat, 23 May 2026 23:22:59 GMT
• Title: Uncertainty Decomposition via Cyclical SG-MCMC and Soft-label Learning for Subjective NLP
• Abstract summary: We train a linear head on a frozen RoBERTa as a Markovnotator distribution with a soft-label objective under a five-axis evaluation.<n>On the 28-emotion GoEmotions benchmark, the proposed method outperforms Monte Carlo Dropout and Deep Ensemble simultaneously on three axes.<n>Posthoc temperature scaling exhibits a bidirectional effect, establishing hard-label calibration and annotator-JSD divergence independent dimensions.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Annotator disagreement in emotion classification reflects ambiguity intrinsic to emotion concepts and is essential for predictor-quality assessment in subjective NLP. Yet no prior work integrates soft-label learning with Bayesian deep learning to evaluate uncertainty along axes including annotator-distribution fidelity. We train a linear head on a frozen RoBERTa via cyclical stochastic gradient Markov chain Monte Carlo (cSG-MCMC), targeting the empirical annotator distribution with a soft-label objective under a five-axis evaluation. On the 28-emotion GoEmotions benchmark, the proposed method outperforms Monte Carlo Dropout and Deep Ensemble simultaneously on three axes -- Jensen-Shannon divergence (JSD) to the annotator distribution, Spearman correlation between per-emotion aleatoric uncertainty and disagreement, and selective-prediction Area Under the Risk-Coverage Curve (AURC) and Area Under the ROC Curve (AUROC) -- showing independent axes are jointly attainable from one posterior. Post-hoc temperature scaling exhibits a bidirectional effect, establishing hard-label calibration and annotator-JSD as independent dimensions and motivating joint reporting as an honest protocol.

Related papers

• A Controlled Audit of Architectural Complexity in Uncertainty-Aware Multi-Organ Ultrasound Classification [19.598719060464866]
  Multi-organ ultrasound classifiers increasingly combine attention, mixture-of-experts routing, uncertainty gating, and evidential deep learning (EDL) objectives.<n>We contribute a controlled complexity-audit framework, applied to the deployment decision between the maximal evidential candidate Full-EDL and simpler alternatives.
  arXiv  Detail & Related papers  (2026-08-28T08:30:43Z)
• AnchorMoE: Interpretable Time Series Classification via Anchor-Routed MoE [51.994752158953084]
  AnchorMoE is an interpretable-by-construction classification framework.<n>It encodes multi-view representations of local patches and routes them to specialized experts.<n>Experiments on real-world and synthetic benchmarks demonstrate that AnchorMoE achieves highly competitive classification performance.
  arXiv  Detail & Related papers  (2026-06-02T13:30:54Z)
• JointHRRP-Net: A Statistically Constrained Decoupling Network for Joint Target and Jamming Recognition in Composite Jamming [14.51679448895586]
  High-resolution range profile (HRRP)-based radar automatic target recognition suffers from severe performance degradation in jamming environments.<n>This paper proposes JointHRRP-Net, a unified framework for joint target-jamming recognition.
  arXiv  Detail & Related papers  (2026-05-19T08:58:31Z)
• Towards Trustworthy Depression Estimation via Disentangled Evidential Learning [50.22167852149165]
  We propose EviDep, an evidential learning framework that jointly quantifies depression severity.<n>EviDep enforces strict information integrity to guarantee robust evidence synthesis.<n>It achieves state-of-the-art predictive accuracy and superior uncertainty calibration, delivering a robust fail-safe mechanism for trustworthy clinical screening.
  arXiv  Detail & Related papers  (2026-04-17T13:27:11Z)
• SKANet: A Cognitive Dual-Stream Framework with Adaptive Modality Fusion for Robust Compound GNSS Interference Classification [47.20483076887704]
  Global Navigation Satellite Systems (GNSS) face growing threats from sophisticated jamming interference.<n>We propose a cognitive deep learning framework built upon a dual-stream architecture that integrates Time-Frequency Images (TFIs) and Power Spectral Density (PSD)<n>We show that SKANet achieves an overall accuracy of 96.99%, exhibiting superior robustness for compound jamming classification.
  arXiv  Detail & Related papers  (2026-01-19T07:42:45Z)
• Decoupling the Effect of Chain-of-Thought Reasoning: A Human Label Variation Perspective [60.45433515408158]
  We show that long Chain-of-Thought (CoT) serves as a decisive decision-maker for the top option but fails to function as a granular distribution calibrator for ambiguous tasks.<n>We observe a distinct "decoupled mechanism": while CoT improves distributional alignment, final accuracy is dictated by CoT content.
  arXiv  Detail & Related papers  (2026-01-06T16:26:40Z)
• Divergence-Minimization for Latent-Structure Models: Monotone Operators, Contraction Guarantees, and Robust Inference [5.373905622325275]
  We develop a divergence-minimization (DM) framework for robust and efficient inference in latent-mixture models.<n>By optimizing a residual-adjusted divergence, the DM approach recovers EM as a special case and yields robust alternatives.
  arXiv  Detail & Related papers  (2025-11-22T08:25:29Z)
• Reference-Free Rating of LLM Responses via Latent Information [53.463883683503106]
  We study the common practice of asking a judge model to assign Likert-scale scores to free-text responses.<n>We then propose and evaluate Latent Judges, which derive scalar ratings from internal model signals.<n>Across a broad suite of pairwise and single-rating benchmarks, latent methods match or surpass standard prompting.
  arXiv  Detail & Related papers  (2025-09-29T12:15:52Z)
• ERIS: An Energy-Guided Feature Disentanglement Framework for Out-of-Distribution Time Series Classification [51.07970070817353]
  An ideal time series classification (TSC) should be able to capture invariant representations.<n>Current methods are largely unguided, lacking the semantic direction required to isolate truly universal features.<n>We propose an end-to-end Energy-Regularized Information for Shift-Robustness framework to enable guided and reliable feature disentanglement.
  arXiv  Detail & Related papers  (2025-08-19T12:13:41Z)
• Uncertainty Estimation and Out-of-Distribution Detection for LiDAR Scene Semantic Segmentation [0.6144680854063939]
  Safe navigation in new environments requires autonomous vehicles and robots to accurately interpret their surroundings. We propose a method to distinguish in-distribution (ID) from out-of-distribution (OOD) samples. We quantify both epistemic and aleatoric uncertainties using the feature space of a single deterministic model.
  arXiv  Detail & Related papers  (2024-10-11T10:19:24Z)
• A Skewness-Based Criterion for Addressing Heteroscedastic Noise in Causal Discovery [47.36895591886043]
  We investigate heteroscedastic symmetric noise models (HSNMs)<n>We introduce a novel criterion for identifying HSNMs based on the skewness of the score (i.e., the gradient of the log density) of the data distribution.<n>We propose SkewScore, an algorithm that handles heteroscedastic noise without requiring the extraction of external noise.
  arXiv  Detail & Related papers  (2024-10-08T22:28:30Z)
• Distributional Shift-Aware Off-Policy Interval Estimation: A Unified Error Quantification Framework [8.572441599469597]
  We study high-confidence off-policy evaluation in the context of infinite-horizon Markov decision processes. The objective is to establish a confidence interval (CI) for the target policy value using only offline data pre-collected from unknown behavior policies. We show that our algorithm is sample-efficient, error-robust, and provably convergent even in non-linear function approximation settings.
  arXiv  Detail & Related papers  (2023-09-23T06:35:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.