Activation-Based Active Learning for In-Context Learning: Challenges and Insights

• URL: http://arxiv.org/abs/2606.05134v1
• Date: Wed, 03 Jun 2026 17:39:29 GMT
• Title: Activation-Based Active Learning for In-Context Learning: Challenges and Insights
• Abstract summary: In this paper, we test the hypothesis that model activations could provide a fine-grained signal to optimise the selection of in-context examples.<n>We present the most comprehensive analysis of activation-based deep active learning methods applied to in-context learning.
• Score: 4.090991964172345
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep active learning has previously been explored for LLM in-context sample selection, but not with methods that utilise recent advances in understanding of transformer activations. In this paper, we test the hypothesis that model activations could provide a fine-grained signal to optimise the selection of in-context examples. We present the most comprehensive analysis to date of MLP activation-based deep active learning methods applied to in-context learning, including how different attention masking strategies impact active learning across diverse classification and generative datasets, using both Llama-3.2-3B and Qwen2.5-3B base models. However, we find a negative result: MLP outputs, viewed through the lenses of massive activations or the first four moments, do not correlate with example quality or task performance. Specifically, the absolute Spearman correlation coefficient is at most 0.33 for all tasks and models we tested, showing that such activation-based sampling should not be used for in-context learning. We hypothesise that this may be due to superposition, whereby models represent more features than they have dimensionality, suggesting that methods like Sparse Autoencoders (SAEs) may be a promising future direction.

Related papers

• Cumulative Meta-Learning from Active Learning Queries for Robustness to Spurious Correlations [2.3234871809423585]
  Cumulative Active Meta-Learning (CAML) is an active-learning framework that uses queried examples to meta-learn the prior, or inductive bias, governing how the model adapts.<n>We show that CAML improves minority-group accuracy across spurious-correlation benchmarks and acquisition strategies.
  arXiv  Detail & Related papers  (2026-05-20T06:14:12Z)
• Active Prompt Learning with Vision-Language Model Priors [9.173468790066956]
  We introduce a class-guided clustering that leverages the pre-trained image and text encoders of vision-language models. We propose a budget-saving selective querying based on adaptive class-wise thresholds.
  arXiv  Detail & Related papers  (2024-11-23T02:34:33Z)
• Dissecting Representation Misalignment in Contrastive Learning via Influence Function [15.28417468377201]
  We introduce the Extended Influence Function for Contrastive Loss (ECIF), an influence function crafted for contrastive loss.<n>ECIF considers both positive and negative samples and provides a closed-form approximation of contrastive learning models.<n>Building upon ECIF, we develop a series of algorithms for data evaluation, misalignment detection, and misprediction trace-back tasks.
  arXiv  Detail & Related papers  (2024-11-18T15:45:41Z)
• C-ICL: Contrastive In-context Learning for Information Extraction [54.39470114243744]
  c-ICL is a novel few-shot technique that leverages both correct and incorrect sample constructions to create in-context learning demonstrations. Our experiments on various datasets indicate that c-ICL outperforms previous few-shot in-context learning methods.
  arXiv  Detail & Related papers  (2024-02-17T11:28:08Z)
• AQA-Bench: An Interactive Benchmark for Evaluating LLMs' Sequential Reasoning Ability [25.96556671801114]
  This paper introduces AQA-Bench, a novel benchmark to assess the sequential reasoning capabilities of large language models (LLMs) in algorithmic contexts.<n>We build AQA-Bench with three different algorithms, namely binary search, depth-first search, and breadth-first search, and to evaluate the sequential reasoning ability of 14 different LLMs.
  arXiv  Detail & Related papers  (2024-02-14T18:59:33Z)
• Querying Easily Flip-flopped Samples for Deep Active Learning [63.62397322172216]
  Active learning is a machine learning paradigm that aims to improve the performance of a model by strategically selecting and querying unlabeled data. One effective selection strategy is to base it on the model's predictive uncertainty, which can be interpreted as a measure of how informative a sample is. This paper proposes the it least disagree metric (LDM) as the smallest probability of disagreement of the predicted label.
  arXiv  Detail & Related papers  (2024-01-18T08:12:23Z)
• Learning Objective-Specific Active Learning Strategies with Attentive Neural Processes [72.75421975804132]
  Learning Active Learning (LAL) suggests to learn the active learning strategy itself, allowing it to adapt to the given setting. We propose a novel LAL method for classification that exploits symmetry and independence properties of the active learning problem. Our approach is based on learning from a myopic oracle, which gives our model the ability to adapt to non-standard objectives.
  arXiv  Detail & Related papers  (2023-09-11T14:16:37Z)
• NTKCPL: Active Learning on Top of Self-Supervised Model by Estimating True Coverage [3.4806267677524896]
  We propose a novel active learning strategy, neural tangent kernel clustering-pseudo-labels (NTKCPL) It estimates empirical risk based on pseudo-labels and the model prediction with NTK approximation. We validate our method on five datasets, empirically demonstrating that it outperforms the baseline methods in most cases.
  arXiv  Detail & Related papers  (2023-06-07T01:43:47Z)
• Active Learning Principles for In-Context Learning with Large Language Models [65.09970281795769]
  This paper investigates how Active Learning algorithms can serve as effective demonstration selection methods for in-context learning. We show that in-context example selection through AL prioritizes high-quality examples that exhibit low uncertainty and bear similarity to the test examples.
  arXiv  Detail & Related papers  (2023-05-23T17:16:04Z)
• Responsible Active Learning via Human-in-the-loop Peer Study [88.01358655203441]
  We propose a responsible active learning method, namely Peer Study Learning (PSL), to simultaneously preserve data privacy and improve model stability. We first introduce a human-in-the-loop teacher-student architecture to isolate unlabelled data from the task learner (teacher) on the cloud-side. During training, the task learner instructs the light-weight active learner which then provides feedback on the active sampling criterion.
  arXiv  Detail & Related papers  (2022-11-24T13:18:27Z)
• Gone Fishing: Neural Active Learning with Fisher Embeddings [55.08537975896764]
  There is an increasing need for active learning algorithms that are compatible with deep neural networks. This article introduces BAIT, a practical representation of tractable, and high-performing active learning algorithm for neural networks.
  arXiv  Detail & Related papers  (2021-06-17T17:26:31Z)

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.