From Haystack to Needle: Label Space Reduction for Zero-shot Classification

• URL: http://arxiv.org/abs/2502.08436v1
• Date: Wed, 12 Feb 2025 14:20:36 GMT
• Title: From Haystack to Needle: Label Space Reduction for Zero-shot Classification
• Authors: Nathan Vandemoortele, Bram Steenwinckel, Femke Ongenae, Sofie Van Hoecke,
• Abstract summary: We present Label Space Reduction (LSR), a novel method for improving zero-shot classification performance of Large Language Models (LLMs)<n>LSR iteratively refines the classification label space by systematically ranking and reducing candidate classes, enabling the model to concentrate on the most relevant options.<n>Our experiments across seven benchmarks demonstrate that LSR improves macro-F1 scores by an average of 7.0% (up to 14.2%) with Llama-3.1-70B and 3.3% (up to 11.1%) with Claude-3.5-Sonnet.
• Score: 0.8866275453081095
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We present Label Space Reduction (LSR), a novel method for improving zero-shot classification performance of Large Language Models (LLMs). LSR iteratively refines the classification label space by systematically ranking and reducing candidate classes, enabling the model to concentrate on the most relevant options. By leveraging unlabeled data with the statistical learning capabilities of data-driven models, LSR dynamically optimizes the label space representation at test time. Our experiments across seven benchmarks demonstrate that LSR improves macro-F1 scores by an average of 7.0% (up to 14.2%) with Llama-3.1-70B and 3.3% (up to 11.1%) with Claude-3.5-Sonnet compared to standard zero-shot classification baselines. To reduce the computational overhead of LSR, which requires an additional LLM call at each iteration, we propose distilling the model into a probabilistic classifier, allowing for efficient inference.

Related papers

• Tuning the Right Foundation Models is What you Need for Partial Label Learning [55.61644150441799]
  Partial label learning seeks to train generalizable classifiers from datasets with inexact supervision.<n>In this work, we empirically conduct evaluations of 11 foundation models across 13 approaches on 8 benchmark datasets under 3 scenarios.<n>Our findings reveal that current approaches tend to achieve significant performance gains when using foundation models, 2) exhibit remarkably similar performance to each other, 3) maintain stable performance across varying ambiguity levels, while 4) are susceptible to foundation model selection and adaptation strategies.
  arXiv  Detail & Related papers  (2025-06-05T13:37:33Z)
• Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning [76.50690734636477]
  We introduce Rank-R1, a novel LLM-based reranker that performs reasoning over both the user query and candidate documents before performing the ranking task. Our experiments on the TREC DL and BRIGHT datasets show that Rank-R1 is highly effective, especially for complex queries.
  arXiv  Detail & Related papers  (2025-03-08T03:14:26Z)
• Data Efficient Evaluation of Large Language Models and Text-to-Image Models via Adaptive Sampling [3.7467864495337624]
  SubLIME is a data-efficient evaluation framework for text-to-image models. Our approach ensures statistically aligned model rankings compared to full datasets. We leverage the HEIM leaderboard to cover 25 text-to-image models on 17 different benchmarks.
  arXiv  Detail & Related papers  (2024-06-21T07:38:55Z)
• Co-training for Low Resource Scientific Natural Language Inference [65.37685198688538]
  We propose a novel co-training method that assigns weights based on the training dynamics of the classifiers to the distantly supervised labels. By assigning importance weights instead of filtering out examples based on an arbitrary threshold on the predicted confidence, we maximize the usage of automatically labeled data. The proposed method obtains an improvement of 1.5% in Macro F1 over the distant supervision baseline, and substantial improvements over several other strong SSL baselines.
  arXiv  Detail & Related papers  (2024-06-20T18:35:47Z)
• Investigating the Emergent Audio Classification Ability of ASR Foundation Models [39.67769732947647]
  We show that Whisper and MMS, ASR foundation models trained primarily for speech recognition, can perform zero-shot audio classification. We demonstrate that Whisper shows promising zero-shot classification performance on a range of 8 audio-classification datasets, outperforming the accuracy of existing state-of-the-art zero-shot baselines by an average of 9%. We further show that performance increases with model size, implying that as ASR foundation models scale up, they may exhibit improved zero-shot performance.
  arXiv  Detail & Related papers  (2023-11-15T20:52:56Z)
• DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detection [72.25697820290502]
  This work introduces a straightforward and efficient strategy to identify potential novel classes through zero-shot classification. We refer to this approach as the self-training strategy, which enhances recall and accuracy for novel classes without requiring extra annotations, datasets, and re-training. Empirical evaluations on three datasets, including LVIS, V3Det, and COCO, demonstrate significant improvements over the baseline performance.
  arXiv  Detail & Related papers  (2023-10-02T17:52:24Z)
• LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections [30.875186985461063]
  Large-scale pre-trained Vision and Language (VL) models have set a new state-of-the-art (SOTA) in zero-shot visual classification. We show, for the first time, how to reduce this gap without any labels and without any paired VL data.
  arXiv  Detail & Related papers  (2023-05-29T17:56:35Z)
• Getting More Juice Out of Your Data: Hard Pair Refinement Enhances Visual-Language Models Without Extra Data [122.282521548393]
  Contrastive Language-Image Pre-training (CLIP) has become the standard for cross-modal image-text representation learning.<n>We introduce HELIP, a cost-effective strategy that improves CLIP models by exploiting challenging text-image pairs within existing datasets in continuous training.
  arXiv  Detail & Related papers  (2023-05-09T07:00:17Z)
• 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)
• Efficient, Uncertainty-based Moderation of Neural Networks Text Classifiers [8.883733362171034]
  We propose a framework for the efficient, in-operation moderation of classifiers' output. We suggest a semi-automated approach that uses prediction uncertainties to pass unconfident, probably incorrect classifications to human moderators. A series of benchmarking experiments show that our framework can improve the classification F1-scores by 5.1 to 11.2%.
  arXiv  Detail & Related papers  (2022-04-04T09:07:54Z)
• Class-Aware Contrastive Semi-Supervised Learning [51.205844705156046]
  We propose a general method named Class-aware Contrastive Semi-Supervised Learning (CCSSL) to improve pseudo-label quality and enhance the model's robustness in the real-world setting. Our proposed CCSSL has significant performance improvements over the state-of-the-art SSL methods on the standard datasets CIFAR100 and STL10.
  arXiv  Detail & Related papers  (2022-03-04T12:18:23Z)
• Self-Supervised Class Incremental Learning [51.62542103481908]
  Existing Class Incremental Learning (CIL) methods are based on a supervised classification framework sensitive to data labels. When updating them based on the new class data, they suffer from catastrophic forgetting: the model cannot discern old class data clearly from the new. In this paper, we explore the performance of Self-Supervised representation learning in Class Incremental Learning (SSCIL) for the first time.
  arXiv  Detail & Related papers  (2021-11-18T06:58:19Z)
• A new weakly supervised approach for ALS point cloud semantic segmentation [1.4620086904601473]
  We propose a deep-learning based weakly supervised framework for semantic segmentation of ALS point clouds. We exploit potential information from unlabeled data subject to incomplete and sparse labels. Our method achieves an overall accuracy of 83.0% and an average F1 score of 70.0%, which have increased by 6.9% and 12.8% respectively.
  arXiv  Detail & Related papers  (2021-10-04T14:00:23Z)
• Uncertainty-aware Self-training for Text Classification with Few Labels [54.13279574908808]
  We study self-training as one of the earliest semi-supervised learning approaches to reduce the annotation bottleneck. We propose an approach to improve self-training by incorporating uncertainty estimates of the underlying neural network. We show our methods leveraging only 20-30 labeled samples per class for each task for training and for validation can perform within 3% of fully supervised pre-trained language models.
  arXiv  Detail & Related papers  (2020-06-27T08:13:58Z)
• Generalized Zero-Shot Learning Via Over-Complete Distribution [79.5140590952889]
  We propose to generate an Over-Complete Distribution (OCD) using Conditional Variational Autoencoder (CVAE) of both seen and unseen classes. The effectiveness of the framework is evaluated using both Zero-Shot Learning and Generalized Zero-Shot Learning protocols.
  arXiv  Detail & Related papers  (2020-04-01T19:05:28Z)

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.