The Silent Vote: Improving Zero-Shot LLM Reliability by Aggregating Semantic Neighborhoods

• URL: http://arxiv.org/abs/2605.09739v1
• Date: Sun, 10 May 2026 20:22:10 GMT
• Title: The Silent Vote: Improving Zero-Shot LLM Reliability by Aggregating Semantic Neighborhoods
• Abstract summary: We propose an inference-time layer that recovers lost information by aggregating the scores of the semantic neighborhood surrounding each target label.<n>Our results demonstrate consistent improvements across all evaluation metrics: Expected Error (ECE) and Brier Score, while simultaneously enhancing discriminative performance in terms of AUROC and Macro-F1.
• Score: 0.0
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Large Language Models are increasingly used as zero-shot classifiers in complex reasoning tasks. However, standard constrained decoding suffers from a phenomenon we define as Renormalization Bias. When a model is restricted to a small set of target labels, the standard softmax operation discards the probability mass assigned to semantic synonyms in the original distribution. This loss of information, which we call the Silent Vote, results in artificial overconfidence and poor calibration. We propose Semantic Softmax, an inference-time layer that recovers this lost information by aggregating the scores of the semantic neighborhood surrounding each target label. We evaluate this approach on Qwen-3 and Phi-4-mini models using GoEmotions and Civil Comments datasets. Our results demonstrate consistent improvements across all evaluation metrics: Semantic Softmax substantially reduces Expected Calibration Error (ECE) and Brier Score, while simultaneously enhancing discriminative performance in terms of AUROC and Macro-F1. By accounting for linguistic nuances, our method provides a more calibrated and accurate alternative for zero-shot classification.

Related papers

• Anchoring Bias in LLM-as-a-Judge Systems: Prior Scores Compromise Evaluation Independence [0.7340017786387767]
  We show that prior scores, even when included only as context metadata, anchor judgments and systematically shift ratings toward their values.<n>On categorical industry data with human-labeled ground truth, anchored metadata blocks 48% of error corrections and flips 10.18% of correct judgments toward an assigned wrong label.
  arXiv  Detail & Related papers  (2026-08-26T14:41:24Z)
• Provable Sparse Inversion and Token Relabel Enhanced One-shot Federated Learning with ViTs [77.42033827176806]
  One-Shot Federated Learning, where a central server learns a global model in a single communication round, has emerged as a promising paradigm.<n>We propose a novel Federated Model Inversion and Token Relabel framework, which trains the global model by fully exploiting all patches of synthetic images.
  arXiv  Detail & Related papers  (2026-05-11T15:49:08Z)
• CORE: Context-Robust Remasking for Diffusion Language Models [51.59514489363897]
  We propose Context-Robust Remasking (CORE), a training-free framework for inference-time revision.<n>Rather than trusting static token probabilities, CORE identifies context-brittle tokens by probing their sensitivity to targeted masked-context perturbations.<n>On LLaDA-8B-Base, CORE delivers consistent improvements across reasoning and code benchmarks, outperforming compute-matched baselines and improving MBPP by up to 9.2 percentage points.
  arXiv  Detail & Related papers  (2026-02-04T00:12:30Z)
• VocSim: A Training-free Benchmark for Zero-shot Content Identity in Single-source Audio [1.0791267046450075]
  VocSim is a training-free benchmark probing the intrinsic geometric alignment of frozen embeddings.<n>VocSim aggregates 125k single-source clips from 19 corpora spanning human speech, animal vocalizations, and environmental sounds.
  arXiv  Detail & Related papers  (2025-12-10T22:13:12Z)
• Universal Adversarial Suffixes Using Calibrated Gumbel-Softmax Relaxation [9.099589602551573]
  We study universal adversarial suffixes that, when appended to any input, broadly reduce accuracy across tasks and models.<n>Our approach learns the suffix in a differentiable "soft" form using Gumbel-Softmax relaxation and then discretizes it for inference.<n>A single suffix trained on one model transfers effectively to others, consistently lowering both accuracy and calibrated confidence.
  arXiv  Detail & Related papers  (2025-12-09T00:03:39Z)
• SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models [74.40683913645731]
  Zero-shot multi-label recognition (MLR) with Vision-Language Models (VLMs) faces significant challenges without training data, model tuning, or architectural modifications.<n>Our work proposes a novel solution treating VLMs as black boxes, leveraging scores without training data or ground truth.<n>Analysis of these prompt scores reveals VLM biases and AND''/OR' signal ambiguities, notably that maximum scores are surprisingly suboptimal compared to second-highest scores.
  arXiv  Detail & Related papers  (2025-02-24T07:15:05Z)
• Dirichlet-Based Prediction Calibration for Learning with Noisy Labels [40.78497779769083]
  Learning with noisy labels can significantly hinder the generalization performance of deep neural networks (DNNs) Existing approaches address this issue through loss correction or example selection methods. We propose the textitDirichlet-based Prediction (DPC) method as a solution.
  arXiv  Detail & Related papers  (2024-01-13T12:33:04Z)
• Variational Classification [51.2541371924591]
  We derive a variational objective to train the model, analogous to the evidence lower bound (ELBO) used to train variational auto-encoders. Treating inputs to the softmax layer as samples of a latent variable, our abstracted perspective reveals a potential inconsistency. We induce a chosen latent distribution, instead of the implicit assumption found in a standard softmax layer.
  arXiv  Detail & Related papers  (2023-05-17T17:47:19Z)
• Self-Adaptive Label Augmentation for Semi-supervised Few-shot Classification [121.63992191386502]
  Few-shot classification aims to learn a model that can generalize well to new tasks when only a few labeled samples are available. We propose a semi-supervised few-shot classification method that assigns an appropriate label to each unlabeled sample by a manually defined metric. A major novelty of SALA is the task-adaptive metric, which can learn the metric adaptively for different tasks in an end-to-end fashion.
  arXiv  Detail & Related papers  (2022-06-16T13:14:03Z)
• Progressive Identification of True Labels for Partial-Label Learning [112.94467491335611]
  Partial-label learning (PLL) is a typical weakly supervised learning problem, where each training instance is equipped with a set of candidate labels among which only one is the true label. Most existing methods elaborately designed as constrained optimizations that must be solved in specific manners, making their computational complexity a bottleneck for scaling up to big data. This paper proposes a novel framework of classifier with flexibility on the model and optimization algorithm.
  arXiv  Detail & Related papers  (2020-02-19T08:35:15Z)

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.