Token-Level Marginalization for Multi-Label LLM Classifiers

• URL: http://arxiv.org/abs/2511.22312v1
• Date: Thu, 27 Nov 2025 10:43:26 GMT
• Title: Token-Level Marginalization for Multi-Label LLM Classifiers
• Authors: Anjaneya Praharaj, Jaykumar Kasundra,
• Abstract summary: Three novel token-level probability estimation approaches are proposed.<n>The aim is to enhance model interpretability and accuracy, and evaluate the generalizability of this framework across different instruction-tuned models.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper addresses the critical challenge of deriving interpretable confidence scores from generative language models (LLMs) when applied to multi-label content safety classification. While models like LLaMA Guard are effective for identifying unsafe content and its categories, their generative architecture inherently lacks direct class-level probabilities, which hinders model confidence assessment and performance interpretation. This limitation complicates the setting of dynamic thresholds for content moderation and impedes fine-grained error analysis. This research proposes and evaluates three novel token-level probability estimation approaches to bridge this gap. The aim is to enhance model interpretability and accuracy, and evaluate the generalizability of this framework across different instruction-tuned models. Through extensive experimentation on a synthetically generated, rigorously annotated dataset, it is demonstrated that leveraging token logits significantly improves the interpretability and reliability of generative classifiers, enabling more nuanced content safety moderation.

Related papers

• Deconstructing Instruction-Following: A New Benchmark for Granular Evaluation of Large Language Model Instruction Compliance Abilities [2.9203730377983654]
  Existing benchmarks fail to reflect real-world use or isolate compliance from task success.<n>We introduce MOSAIC, a modular framework that uses a dynamically generated dataset with up to 20 application-oriented generation constraints.<n>We show that compliance is not a monolithic capability but varies significantly with constraint type, quantity, and position.
  arXiv  Detail & Related papers  (2026-01-26T15:02:15Z)
• LLM-Centric RAG with Multi-Granular Indexing and Confidence Constraints [5.2604064919135896]
  This paper addresses the issues of insufficient coverage, unstable results, and limited reliability in retrieval-augmented generation under complex knowledge environments.<n>It proposes a confidence control method that integrates multi-granularity memory indexing with uncertainty estimation.<n>The results show that the method achieves superior performance over existing models in QA accuracy, retrieval recall, ranking quality, and factual consistency.
  arXiv  Detail & Related papers  (2025-10-30T23:48:37Z)
• Dynamic Evaluation for Oversensitivity in LLMs [68.27609301865174]
  Oversensitivity occurs when language models defensively reject prompts that are actually benign.<n>This behavior not only disrupts user interactions but also obscures the boundary between harmful and harmless content.<n>Existing benchmarks rely on static datasets that degrade overtime as models evolve.
  arXiv  Detail & Related papers  (2025-10-21T18:33:47Z)
• Advancing Neural Network Verification through Hierarchical Safety Abstract Interpretation [52.626086874715284]
  We introduce a novel problem formulation called Abstract DNN-Verification, which verifies a hierarchical structure of unsafe outputs.<n>By leveraging abstract interpretation and reasoning about output reachable sets, our approach enables assessing multiple safety levels during the formal verification process.<n>Our contributions include a theoretical exploration of the relationship between our novel abstract safety formulation and existing approaches.
  arXiv  Detail & Related papers  (2025-05-08T13:29:46Z)
• Bridging Interpretability and Robustness Using LIME-Guided Model Refinement [0.0]
  Local Interpretable Model-Agnostic Explanations (LIME) systematically enhance model robustness.<n> Empirical evaluations on multiple benchmark datasets demonstrate that LIME-guided refinement not only improves interpretability but also significantly enhances resistance to adversarial perturbations and generalization to out-of-distribution data.
  arXiv  Detail & Related papers  (2024-12-25T17:32:45Z)
• Erasing Conceptual Knowledge from Language Models [24.63143961814566]
  We introduce Erasure of Language Memory (ELM), a principled approach to concept-level unlearning.<n>ELM operates by matching distributions defined by the model's own introspective classification capabilities.<n>We demonstrate ELM's efficacy on biosecurity, cybersecurity, and literary domain erasure tasks.
  arXiv  Detail & Related papers  (2024-10-03T17:59:30Z)
• Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models [104.55763564037831]
  We train a regression model that leverages attention maps, probabilities on the current generation step, and recurrently computed uncertainty scores from previously generated tokens.<n>Our evaluation shows that the proposed method is highly effective for selective generation, achieving substantial improvements over rivaling unsupervised and supervised approaches.
  arXiv  Detail & Related papers  (2024-08-20T09:42:26Z)
• DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanation [18.77296551727931]
  We propose DECIDER, a novel approach that leverages priors from large language models (LLMs) and vision-language models (VLMs) to detect failures in image models. DECIDER consistently achieves state-of-the-art failure detection performance, significantly outperforming baselines in terms of the overall Matthews correlation coefficient.
  arXiv  Detail & Related papers  (2024-08-01T07:08:11Z)
• Cycles of Thought: Measuring LLM Confidence through Stable Explanations [53.15438489398938]
  Large language models (LLMs) can reach and even surpass human-level accuracy on a variety of benchmarks, but their overconfidence in incorrect responses is still a well-documented failure mode. We propose a framework for measuring an LLM's uncertainty with respect to the distribution of generated explanations for an answer.
  arXiv  Detail & Related papers  (2024-06-05T16:35:30Z)
• Model Stealing Attack against Graph Classification with Authenticity, Uncertainty and Diversity [80.16488817177182]
  GNNs are vulnerable to the model stealing attack, a nefarious endeavor geared towards duplicating the target model via query permissions. We introduce three model stealing attacks to adapt to different actual scenarios.
  arXiv  Detail & Related papers  (2023-12-18T05:42:31Z)
• Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling [69.83976050879318]
  In large language models (LLMs), identifying sources of uncertainty is an important step toward improving reliability, trustworthiness, and interpretability. In this paper, we introduce an uncertainty decomposition framework for LLMs, called input clarification ensembling. Our approach generates a set of clarifications for the input, feeds them into an LLM, and ensembles the corresponding predictions.
  arXiv  Detail & Related papers  (2023-11-15T05:58:35Z)
• Trust but Verify: Assigning Prediction Credibility by Counterfactual Constrained Learning [123.3472310767721]
  Prediction credibility measures are fundamental in statistics and machine learning. These measures should account for the wide variety of models used in practice. The framework developed in this work expresses the credibility as a risk-fit trade-off.
  arXiv  Detail & Related papers  (2020-11-24T19:52:38Z)

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.