GRAD: Generative Retrieval-Aligned Demonstration Sampler for Efficient Few-Shot Reasoning

• URL: http://arxiv.org/abs/2510.01165v1
• Date: Wed, 01 Oct 2025 17:52:41 GMT
• Title: GRAD: Generative Retrieval-Aligned Demonstration Sampler for Efficient Few-Shot Reasoning
• Authors: Oussama Gabouj, Kamel Charaf, Ivan Zakazov, Nicolas Baldwin, Robert West,
• Abstract summary: Large Language Models (LLMs) achieve strong performance across diverse tasks.<n>Retrieval-Augmented Generation (RAG) enriches prompts with external information, but its reliance on static databases constrains adaptability.<n>We propose a Generative Retrieval-Aligned Demonstrator (GRAD) to generate input-specific concise demonstrations.
• Score: 6.371118178107715
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) achieve strong performance across diverse tasks, but their effectiveness often depends on the quality of the provided context. Retrieval-Augmented Generation (RAG) enriches prompts with external information, but its reliance on static databases constrains adaptability and can result in irrelevant demonstrations. In this work, we propose a Generative Retrieval-Aligned Demonstrator (GRAD), a dynamic demonstration-based approach where an LLM model is trained to generate input-specific concise demonstrations. By tailoring demonstrations to each input, our method offers better contextual support than traditional RAG approaches. We demonstrate the superiority of GRAD under budget constraints, where we limit both the number of tokens used per demonstration and the number of tokens used for the final output. Trained solely on a math dataset, GRAD consistently outperforms strong baselines on Qwen2.5-14B across mathematical reasoning and advanced STEM questions, highlighting GRAD's robust generalization to out-of-distribution (OOD) domains such as physics, chemistry, and computer science. Furthermore, we show that demonstrations generated by trained smaller models can effectively guide larger target models, reducing training costs while maintaining competitive accuracy. Overall, this work introduces a scalable demonstration generator model presenting the first step toward a dynamic few-shot learning paradigm in resource-constrained settings. We release the code used for the project.

Related papers

• Self-evolved Imitation Learning in Simulated World [16.459715139048367]
  Self-Evolved Imitation Learning (SEIL) is a framework that progressively improves a few-shot model through simulator interactions.<n>SEIL achieves a new state-of-the-art performance in few-shot imitation learning scenarios.
  arXiv  Detail & Related papers  (2025-09-23T18:15:32Z)
• Leveraging In-Context Learning for Language Model Agents [51.2996117207114]
  In-context learning (ICL) with dynamically selected demonstrations combines the flexibility of prompting large language models (LLMs) with the ability to leverage training data to improve performance.<n>We show that set-selection of trajectories of similar tasks as demonstrations significantly improves performance, reliability, robustness, and efficiency of LLM agents.<n>We find that demonstrations obtained from larger models (in the annotation phase) also improve smaller models, and that ICL agents can even rival costlier trained agents.
  arXiv  Detail & Related papers  (2025-06-16T05:37:49Z)
• Model Utility Law: Evaluating LLMs beyond Performance through Mechanism Interpretable Metric [99.56567010306807]
  Large Language Models (LLMs) have become indispensable across academia, industry, and daily applications.<n>One core challenge of evaluation in the large language model (LLM) era is the generalization issue.<n>We propose Model Utilization Index (MUI), a mechanism interpretability enhanced metric that complements traditional performance scores.
  arXiv  Detail & Related papers  (2025-04-10T04:09:47Z)
• D.Va: Validate Your Demonstration First Before You Use It [13.593191802452134]
  In-context learning (ICL) has demonstrated significant potential in enhancing the capabilities of large language models (LLMs) during inference.<n>Previous approaches have typically relied on intuitive metrics to evaluate the effectiveness of demonstrations.<n>We propose a novel method, textbfD.Va, which integrates a demonstration validation perspective into this field.
  arXiv  Detail & Related papers  (2025-02-19T11:41:40Z)
• Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model [41.55165760439727]
  Vision-language models (VLMs) have revolutionized machine learning by leveraging large pre-trained models to tackle various downstream tasks.<n>We propose a graph-based approach for label-efficient adaptation and inference.<n>Our method dynamically constructs a graph over text prompts, few-shot examples, and test samples, using label propagation for inference without task-specific tuning.
  arXiv  Detail & Related papers  (2024-12-24T09:15:00Z)
• Aligning Language Models with Demonstrated Feedback [58.834937450242975]
  Demonstration ITerated Task Optimization (DITTO) directly aligns language model outputs to a user's demonstrated behaviors.<n>We evaluate DITTO's ability to learn fine-grained style and task alignment across domains such as news articles, emails, and blog posts.
  arXiv  Detail & Related papers  (2024-06-02T23:13:56Z)
• Inverse-RLignment: Large Language Model Alignment from Demonstrations through Inverse Reinforcement Learning [62.05713042908654]
  We introduce Alignment from Demonstrations (AfD), a novel approach leveraging high-quality demonstration data to overcome these challenges.<n>We formalize AfD within a sequential decision-making framework, highlighting its unique challenge of missing reward signals.<n> Practically, we propose a computationally efficient algorithm that extrapolates over a tailored reward model for AfD.
  arXiv  Detail & Related papers  (2024-05-24T15:13:53Z)
• Efficient Prompting via Dynamic In-Context Learning [76.83516913735072]
  We propose DynaICL, a recipe for efficient prompting with black-box generalist models. DynaICL dynamically allocates in-context examples according to the input complexity and the computational budget. We find that DynaICL saves up to 46% token budget compared to the common practice that allocates the same number of in-context examples to each input.
  arXiv  Detail & Related papers  (2023-05-18T17:58:31Z)
• Robustness of Demonstration-based Learning Under Limited Data Scenario [54.912936555876826]
  Demonstration-based learning has shown great potential in stimulating pretrained language models' ability under limited data scenario. Why such demonstrations are beneficial for the learning process remains unclear since there is no explicit alignment between the demonstrations and the predictions. In this paper, we design pathological demonstrations by gradually removing intuitively useful information from the standard ones to take a deep dive of the robustness of demonstration-based sequence labeling.
  arXiv  Detail & Related papers  (2022-10-19T16:15:04Z)
• Self-Generated In-Context Learning: Leveraging Auto-regressive Language Models as a Demonstration Generator [22.532627423361177]
  Self-generated in-context learning (SG-ICL) generates demonstrations for in-context learning from PLM itself. We show SG-ICL significantly outperforms zero-shot learning and is generally worth approximately 0.6 gold training samples.
  arXiv  Detail & Related papers  (2022-06-16T10:52:13Z)

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.