Demonstration Selection for In-Context Learning via Reinforcement Learning

• URL: http://arxiv.org/abs/2412.03966v2
• Date: Sat, 24 May 2025 14:53:24 GMT
• Title: Demonstration Selection for In-Context Learning via Reinforcement Learning
• Authors: Xubin Wang, Jianfei Wu, Yichen Yuan, Deyu Cai, Mingzhe Li, Weijia Jia,
• Abstract summary: Relevance-Diversity Enhanced Selection (RDES) is an innovative approach to optimize the selection of diverse reference demonstrations.<n>RDES employs frameworks like Q-learning and a PPO-based variant to dynamically identify demonstrations that maximize diversity.<n>We demonstrate that RDES significantly enhances performance compared to ten established baselines.
• Score: 16.103533806505403
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diversity in demonstration selection is critical for enhancing model generalization by enabling broader coverage of structures and concepts. Constructing appropriate demonstration sets remains a key research challenge. This paper introduces the Relevance-Diversity Enhanced Selection (RDES), an innovative approach that leverages reinforcement learning (RL) frameworks to optimize the selection of diverse reference demonstrations for tasks amenable to in-context learning (ICL), particularly text classification and reasoning, in few-shot prompting scenarios. RDES employs frameworks like Q-learning and a PPO-based variant to dynamically identify demonstrations that maximize both diversity (quantified by label distribution) and relevance to the task objective. This strategy ensures a balanced representation of reference data, leading to improved accuracy and generalization. Through extensive experiments on multiple benchmark datasets, including diverse reasoning tasks, and involving 14 closed-source and open-source LLMs, we demonstrate that RDES significantly enhances performance compared to ten established baselines. Our evaluation includes analysis of performance across varying numbers of demonstrations on selected datasets. Furthermore, we investigate incorporating Chain-of-Thought (CoT) reasoning, which further boosts predictive performance. The results highlight the potential of RL for adaptive demonstration selection and addressing challenges in ICL.

Related papers

• DICE: Dynamic In-Context Example Selection in LLM Agents via Efficient Knowledge Transfer [50.64531021352504]
  Large language model-based agents, empowered by in-context learning (ICL), have demonstrated strong capabilities in complex reasoning and tool-use tasks.<n>Existing approaches typically rely on example selection, including in some agentic or multi-step settings.<n>We propose DICE, a theoretically grounded ICL framework for agentic tasks that selects the most relevant demonstrations at each step of reasoning.
  arXiv  Detail & Related papers  (2025-07-31T13:42:14Z)
• Feature-Based vs. GAN-Based Learning from Demonstrations: When and Why [50.191655141020505]
  This survey provides a comparative analysis of feature-based and GAN-based approaches to learning from demonstrations.<n>We argue that the dichotomy between feature-based and GAN-based methods is increasingly nuanced.
  arXiv  Detail & Related papers  (2025-07-08T11:45:51Z)
• Provoking Multi-modal Few-Shot LVLM via Exploration-Exploitation In-Context Learning [45.06983025267863]
  This paper investigates ICL on Large Vision-Language Models (LVLMs) and explores the policies of multi-modal demonstration selection.<n>We propose a new exploration-exploitation reinforcement learning framework, which explores policies to fuse multi-modal information and adaptively select adequate demonstrations as an integrated whole.
  arXiv  Detail & Related papers  (2025-06-11T07:38:12Z)
• Large Language Models are Demonstration Pre-Selectors for Themselves [57.101804269100185]
  In-context learning (ICL) with large language models (LLMs) delivers strong few-shot performance by choosing few-shot demonstrations from the entire training data.<n>FEw yet Essential Demonstration prE-selectoR is a novel pre-selection framework that identifies a representative subset of demonstrations.<n>FEw yet Essential Demonstration prE-selectoR can reduce training data size by over 20% while maintaining performance.
  arXiv  Detail & Related papers  (2025-06-06T12:29:03Z)
• Your Language Model May Think Too Rigidly: Achieving Reasoning Consistency with Symmetry-Enhanced Training [66.48331530995786]
  We propose syMmetry-ENhanceD (MEND) Data Augmentation, a data-centric approach that improves the model's ability to extract useful information from context. Unlike existing methods that emphasize reasoning chain augmentation, our approach improves model robustness at the knowledge extraction stage. Experiments on both logical and arithmetic reasoning tasks show that MEND enhances reasoning performance across diverse query variations.
  arXiv  Detail & Related papers  (2025-02-25T03:03:35Z)
• Affinity and Diversity: A Unified Metric for Demonstration Selection via Internal Representations [2.4866936275046405]
  We propose a unified metric--affinity and diversity--that leverages ICL model's internal representations. Our experiments show that both affinity and diversity strongly correlate with test accuracies, indicating their effectiveness for demonstration selection.
  arXiv  Detail & Related papers  (2025-02-20T09:12:51Z)
• Investigating the Impact of Data Selection Strategies on Language Model Performance [1.0013553984400492]
  This study explores the effects of different data selection methods and feature types on model performance. We evaluate whether selecting data subsets can influence downstream tasks, whether n-gram features improve alignment with target distributions, and whether embedding-based neural features provide complementary benefits.
  arXiv  Detail & Related papers  (2025-01-07T14:38:49Z)
• The Power of Adaptation: Boosting In-Context Learning through Adaptive Prompting [8.260097638532878]
  Large Language Models (LLMs) have demonstrated exceptional abilities across a broad range of language-related tasks.<n>We propose textscAdaptive-Prompt, a novel method that adaptively selects exemplars by leveraging model feedback.<n> Experimental results show that textscAdaptive-Prompt significantly enhances LLM performance across a variety of reasoning tasks.
  arXiv  Detail & Related papers  (2024-12-23T15:49:43Z)
• 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)
• Large Language Models Know What Makes Exemplary Contexts [42.90814615222177]
  In-context learning (ICL) has proven to be a significant capability with the advancement of Large Language models (LLMs) This paper presents a unified framework for LLMs that allows them to self-select influential in-context examples to compose their contexts.
  arXiv  Detail & Related papers  (2024-08-14T12:32:41Z)
• Effective Data Selection for Seismic Interpretation through Disagreement [14.11559987180237]
  The development of a novel data selection framework is inspired by established practices in seismic interpretation. We offer a specific implementation of our proposed framework, which we have named ATLAS. Our findings reveal that ATLAS achieves improvements of up to 12% in mean intersection-over-union.
  arXiv  Detail & Related papers  (2024-06-01T20:06:48Z)
• Leveraging vision-language models for fair facial attribute classification [19.93324644519412]
  General-purpose vision-language model (VLM) is a rich knowledge source for common sensitive attributes. We analyze the correspondence between VLM predicted and human defined sensitive attribute distribution. Experiments on multiple benchmark facial attribute classification datasets show fairness gains of the model over existing unsupervised baselines.
  arXiv  Detail & Related papers  (2024-03-15T18:37:15Z)
• Revisiting Demonstration Selection Strategies in In-Context Learning [66.11652803887284]
  Large language models (LLMs) have shown an impressive ability to perform a wide range of tasks using in-context learning (ICL) In this work, we first revisit the factors contributing to this variance from both data and model aspects, and find that the choice of demonstration is both data- and model-dependent. We propose a data- and model-dependent demonstration selection method, textbfTopK + ConE, based on the assumption that textitthe performance of a demonstration positively correlates with its contribution to the model's understanding of the test samples.
  arXiv  Detail & Related papers  (2024-01-22T16:25:27Z)
• Consistency Regularization for Generalizable Source-free Domain Adaptation [62.654883736925456]
  Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset. Existing SFDA methods ONLY assess their adapted models on the target training set, neglecting the data from unseen but identically distributed testing sets. We propose a consistency regularization framework to develop a more generalizable SFDA method.
  arXiv  Detail & Related papers  (2023-08-03T07:45:53Z)
• Iterative Forward Tuning Boosts In-Context Learning in Language Models [88.25013390669845]
  In this study, we introduce a novel two-stage framework to boost in-context learning in large language models (LLMs) Specifically, our framework delineates the ICL process into two distinct stages: Deep-Thinking and test stages. The Deep-Thinking stage incorporates a unique attention mechanism, i.e., iterative enhanced attention, which enables multiple rounds of information accumulation.
  arXiv  Detail & Related papers  (2023-05-22T13:18:17Z)
• Attitudes and Latent Class Choice Models using Machine learning [0.0]
  We present a method of efficiently incorporating attitudinal indicators in the specification of Latent Class Choice Models (LCCM) This formulation overcomes structural equations in its capability of exploring the relationship between the attitudinal indicators and the decision choice. We test our proposed framework for estimating a Car-Sharing (CS) service subscription choice with stated preference data from Copenhagen, Denmark.
  arXiv  Detail & Related papers  (2023-02-20T10:03:01Z)
• Using Representation Expressiveness and Learnability to Evaluate Self-Supervised Learning Methods [61.49061000562676]
  We introduce Cluster Learnability (CL) to assess learnability. CL is measured in terms of the performance of a KNN trained to predict labels obtained by clustering the representations with K-means. We find that CL better correlates with in-distribution model performance than other competing recent evaluation schemes.
  arXiv  Detail & Related papers  (2022-06-02T19:05:13Z)
• Adaptive Discrete Communication Bottlenecks with Dynamic Vector Quantization [76.68866368409216]
  We propose learning to dynamically select discretization tightness conditioned on inputs. We show that dynamically varying tightness in communication bottlenecks can improve model performance on visual reasoning and reinforcement learning tasks.
  arXiv  Detail & Related papers  (2022-02-02T23:54:26Z)
• MCDAL: Maximum Classifier Discrepancy for Active Learning [74.73133545019877]
  Recent state-of-the-art active learning methods have mostly leveraged Generative Adversarial Networks (GAN) for sample acquisition. We propose in this paper a novel active learning framework that we call Maximum Discrepancy for Active Learning (MCDAL) In particular, we utilize two auxiliary classification layers that learn tighter decision boundaries by maximizing the discrepancies among them.
  arXiv  Detail & Related papers  (2021-07-23T06:57:08Z)

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.