InSQuAD: In-Context Learning for Efficient Retrieval via Submodular Mutual Information to Enforce Quality and Diversity

• URL: http://arxiv.org/abs/2508.21003v1
• Date: Thu, 28 Aug 2025 17:04:43 GMT
• Title: InSQuAD: In-Context Learning for Efficient Retrieval via Submodular Mutual Information to Enforce Quality and Diversity
• Authors: Souradeep Nanda, Anay Majee, Rishabh Iyer,
• Abstract summary: We introduce InSQuAD, designed to enhance the performance of In-Context Learning (ICL) models.<n>We model the ICL task as a targeted selection problem and introduce a unified selection strategy based on Submodular Mutual Information (SMI)<n>InSQuAD introduces a training paradigm which learns the parameters of an SMI function to enforce both quality and diversity in the retrieval model through a novel likelihood-based loss.
• Score: 3.838191198142784
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we introduce InSQuAD, designed to enhance the performance of In-Context Learning (ICL) models through Submodular Mutual Information} (SMI) enforcing Quality and Diversity among in-context exemplars. InSQuAD achieves this through two principal strategies: First, we model the ICL task as a targeted selection problem and introduce a unified selection strategy based on SMIs which mines relevant yet diverse in-context examples encapsulating the notions of quality and diversity. Secondly, we address a common pitfall in existing retrieval models which model query relevance, often overlooking diversity, critical for ICL. InSQuAD introduces a combinatorial training paradigm which learns the parameters of an SMI function to enforce both quality and diversity in the retrieval model through a novel likelihood-based loss. To further aid the learning process we augment an existing multi-hop question answering dataset with synthetically generated paraphrases. Adopting the retrieval model trained using this strategy alongside the novel targeted selection formulation for ICL on nine benchmark datasets shows significant improvements validating the efficacy of our approach.

Related papers

• From Sparse Decisions to Dense Reasoning: A Multi-attribute Trajectory Paradigm for Multimodal Moderation [59.27094165576015]
  We propose a novel learning paradigm (UniMod) that transitions from sparse decision-making to dense reasoning traces.<n>By constructing structured trajectories encompassing evidence grounding, modality assessment, risk mapping, policy decision, and response generation, we reformulate monolithic decision tasks into a multi-dimensional boundary learning process.<n>We introduce specialized optimization strategies to decouple task-specific parameters and rebalance training dynamics, effectively resolving interference between diverse objectives in multi-task learning.
  arXiv  Detail & Related papers  (2026-01-28T09:29:40Z)
• CoT Referring: Improving Referring Expression Tasks with Grounded Reasoning [67.18702329644526]
  CoT Referring enhances model reasoning across modalities through a structured, chain-of-thought training data structure.<n>We restructure the training data to enforce a new output form, providing new annotations for existing datasets.<n>We also integrate detection and segmentation capabilities into a unified MLLM framework, training it with a novel adaptive weighted loss to optimize performance.
  arXiv  Detail & Related papers  (2025-10-03T08:50:21Z)
• Post-training Large Language Models for Diverse High-Quality Responses [32.92680825196664]
  Reinforcement learning (RL) has emerged as a popular method for post-training large language models (LLMs)<n>We propose a novel training method named DQO (Diversity Quality Optimization) based on determinantal point processes (DPPs)<n>Our approach samples and embeds a group of responses for each prompt, then uses the determinant of a kernel-based similarity matrix to measure diversity as the volume spanned by the embeddings of these responses.
  arXiv  Detail & Related papers  (2025-09-05T03:47:06Z)
• Multi-Level Aware Preference Learning: Enhancing RLHF for Complex Multi-Instruction Tasks [81.44256822500257]
  RLHF has emerged as a predominant approach for aligning artificial intelligence systems with human preferences.<n> RLHF exhibits insufficient compliance capabilities when confronted with complex multi-instruction tasks.<n>We propose a novel Multi-level Aware Preference Learning (MAPL) framework, capable of enhancing multi-instruction capabilities.
  arXiv  Detail & Related papers  (2025-05-19T08:33:11Z)
• Empowering Large Language Models in Wireless Communication: A Novel Dataset and Fine-Tuning Framework [81.29965270493238]
  We develop a specialized dataset aimed at enhancing the evaluation and fine-tuning of large language models (LLMs) for wireless communication applications.<n>The dataset includes a diverse set of multi-hop questions, including true/false and multiple-choice types, spanning varying difficulty levels from easy to hard.<n>We introduce a Pointwise V-Information (PVI) based fine-tuning method, providing a detailed theoretical analysis and justification for its use in quantifying the information content of training data.
  arXiv  Detail & Related papers  (2025-01-16T16:19:53Z)
• STAYKATE: Hybrid In-Context Example Selection Combining Representativeness Sampling and Retrieval-based Approach -- A Case Study on Science Domains [0.8296121350988481]
  Large language models (LLMs) demonstrate the ability to learn in-context, offering a potential solution for scientific information extraction.<n>We propose STAYKATE, a static-dynamic hybrid selection method that combines the principles of representativeness sampling from active learning with the prevalent retrieval-based approach.<n>The results across three domain-specific datasets indicate that STAYKATE outperforms both the traditional supervised methods and existing selection methods.
  arXiv  Detail & Related papers  (2024-12-28T06:13:50Z)
• 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)
• Demonstration Selection for In-Context Learning via Reinforcement Learning [16.103533806505403]
  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.
  arXiv  Detail & Related papers  (2024-12-05T08:33:52Z)
• Unified Generative and Discriminative Training for Multi-modal Large Language Models [88.84491005030316]
  Generative training has enabled Vision-Language Models (VLMs) to tackle various complex tasks. Discriminative training, exemplified by models like CLIP, excels in zero-shot image-text classification and retrieval. This paper proposes a unified approach that integrates the strengths of both paradigms.
  arXiv  Detail & Related papers  (2024-11-01T01:51:31Z)
• Model Composition for Multimodal Large Language Models [71.5729418523411]
  We propose a new paradigm through the model composition of existing MLLMs to create a new model that retains the modal understanding capabilities of each original model. Our basic implementation, NaiveMC, demonstrates the effectiveness of this paradigm by reusing modality encoders and merging LLM parameters.
  arXiv  Detail & Related papers  (2024-02-20T06:38:10Z)
• Retrieval-augmented Multi-modal Chain-of-Thoughts Reasoning for Large Language Models [56.256069117502385]
  Chain of Thought (CoT) approaches can be used to enhance the capability of Large Language Models (LLMs) on complex reasoning tasks. However, the selection of optimal CoT demonstration examples in multi-modal reasoning remains less explored. We introduce a novel approach that addresses this challenge by using retrieval mechanisms to automatically select demonstration examples.
  arXiv  Detail & Related papers  (2023-12-04T08:07:21Z)
• SEER : A Knapsack approach to Exemplar Selection for In-Context HybridQA [1.0323063834827413]
  In this work, we present Selection of Exmplars for hybrid Reasoning (SEER), a novel method for selecting a set of exemplars that is both representative and diverse. The effectiveness of SEER is demonstrated on FinQA and TAT-QA, two real-world benchmarks for HybridQA, where it outperforms previous exemplar selection methods.
  arXiv  Detail & Related papers  (2023-10-10T14:50:20Z)
• Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation [87.98063273826702]
  We propose a memory imitation meta-learning (MemIML) method that enhances the model's reliance on support sets for task adaptation. A theoretical analysis is provided to prove the effectiveness of our method.
  arXiv  Detail & Related papers  (2022-03-22T12:41:55Z)

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.