MHA-RAG: Improving Efficiency, Accuracy, and Consistency by Encoding Exemplars as Soft Prompts

• URL: http://arxiv.org/abs/2510.05363v1
• Date: Mon, 06 Oct 2025 20:41:43 GMT
• Title: MHA-RAG: Improving Efficiency, Accuracy, and Consistency by Encoding Exemplars as Soft Prompts
• Authors: Abhinav Jain, Xinyu Yao, Thomas Reps, Christopher Jermaine,
• Abstract summary: Adapting Foundation Models to new domains with limited training data is challenging and computationally expensive.<n>We investigate whether representing exemplars purely as text is the most efficient, effective, and stable approach.<n>We explore an alternative: representing exemplars as soft prompts with an exemplar order invariant model architecture.
• Score: 3.631974475748162
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Adapting Foundation Models to new domains with limited training data is challenging and computationally expensive. While prior work has demonstrated the effectiveness of using domain-specific exemplars as in-context demonstrations, we investigate whether representing exemplars purely as text is the most efficient, effective, and stable approach. We explore an alternative: representing exemplars as soft prompts with an exemplar order invariant model architecture. To this end, we introduce Multi-Head Attention Retrieval-Augmented Generation (MHA-RAG), a framework with the number of attention heads serving as a simple hyperparameter to control soft prompt-generation across different tasks. Across multiple question-answering benchmarks and model scales, MHA-RAG achieves a 20-point performance gain over standard RAG, while cutting inference costs by a factor of 10X GFLOPs-delivering both higher accuracy and greater efficiency, invariant to exemplar order.

Related papers

• Benchmarking Few-shot Transferability of Pre-trained Models with Improved Evaluation Protocols [123.73663884421272]
  Few-shot transfer has been revolutionized by stronger pre-trained models and improved adaptation algorithms.<n>We establish FEWTRANS, a comprehensive benchmark containing 10 diverse datasets.<n>By releasing FEWTRANS, we aim to provide a rigorous "ruler" to streamline reproducible advances in few-shot transfer learning research.
  arXiv  Detail & Related papers  (2026-02-28T05:41:57Z)
• Predict the Retrieval! Test time adaptation for Retrieval Augmented Generation [66.36556189794526]
  TTARAG is a test-time adaptation method that dynamically updates the language model's parameters during inference to improve RAG system performance in specialized domains.<n>Our method introduces a simple yet effective approach where the model learns to predict retrieved content, enabling automatic parameter adjustment to the target domain.
  arXiv  Detail & Related papers  (2026-01-16T17:07:01Z)
• Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models [99.85131798240808]
  We introduce a novel generative framework called textitGuided Topology Diffusion (GTD)<n>Inspired by conditional discrete graph diffusion models, GTD formulates topology synthesis as an iterative construction process.<n>At each step, the generation is steered by a lightweight proxy model that predicts multi-objective rewards.<n>Experiments show that GTD can generate highly task-adaptive, sparse, and efficient communication topologies.
  arXiv  Detail & Related papers  (2025-10-09T05:28:28Z)
• GLAD: Generalizable Tuning for Vision-Language Models [41.071911050087586]
  We propose a simpler and more general framework called GLAD (Generalizable LoRA tuning with RegulArized GraDient)<n>We show that merely applying LoRA achieves performance in downstream tasks comparable to current state-of-the-art prompt-based methods.
  arXiv  Detail & Related papers  (2025-07-17T12:58:15Z)
• SPARE: Single-Pass Annotation with Reference-Guided Evaluation for Automatic Process Supervision and Reward Modelling [58.05959902776133]
  We introduce Single-Pass.<n>with Reference-Guided Evaluation (SPARE), a novel structured framework that enables efficient per-step annotation.<n>We demonstrate SPARE's effectiveness across four diverse datasets spanning mathematical reasoning (GSM8K, MATH), multi-hop question answering (MuSiQue-Ans), and spatial reasoning (SpaRP)<n>On ProcessBench, SPARE demonstrates data-efficient out-of-distribution generalization, using only $sim$16% of training samples compared to human-labeled and other synthetically trained baselines.
  arXiv  Detail & Related papers  (2025-06-18T14:37:59Z)
• Towards Transformer-Based Aligned Generation with Self-Coherence Guidance [51.42269790543461]
  We introduce a training-free approach for enhancing alignment in Transformer-based Text-Guided Diffusion Models (TGDMs)<n>Existing TGDMs often struggle to generate semantically aligned images, particularly when dealing with complex text prompts or multi-concept attribute binding challenges.<n>Our method addresses these challenges by directly optimizing cross-attention maps during the generation process.
  arXiv  Detail & Related papers  (2025-03-22T07:03:57Z)
• Chain-of-Retrieval Augmented Generation [72.06205327186069]
  This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer.<n>Our proposed method, CoRAG, allows the model to dynamically reformulate the query based on the evolving state.
  arXiv  Detail & Related papers  (2025-01-24T09:12:52Z)
• First Token Probability Guided RAG for Telecom Question Answering [15.854941373238226]
  Retrieval-Augmented Generation (RAG) has shown a distinct advantage in incorporating domain-specific information into Large Language Models (LLMs)<n>We propose a novel first token probability guided RAG framework to tackle the challenges of Multiple Choice Question Answering (MCQA) in telecommunications.
  arXiv  Detail & Related papers  (2025-01-11T07:47:31Z)
• Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting [107.4034346788744]
  Existing vehicle trajectory prediction models struggle with generalizability, prediction uncertainties, and handling complex interactions.<n>We propose Perceiver with Register queries (PerReg+), a novel trajectory prediction framework that introduces: (1) Dual-Level Representation Learning via Self-Distillation (SD) and Masked Reconstruction (MR), capturing global context and fine-grained details; (2) Enhanced Multimodality using register-based queries and pretraining, eliminating the need for clustering and suppression; and (3) Adaptive Prompt Tuning during fine-tuning, freezing the main architecture and optimizing a small number of prompts for efficient adaptation.
  arXiv  Detail & Related papers  (2025-01-08T20:11:09Z)
• Fine-Tuning or Fine-Failing? Debunking Performance Myths in Large Language Models [0.8399688944263842]
  Large Language Models (LLMs) have the capability to understand and generate human-like text from input queries. This study extends this concept to the integration of LLMs within Retrieval-Augmented Generation (RAG) pipelines. We evaluate the impact of fine-tuning on the LLMs' capacity for data extraction and contextual understanding.
  arXiv  Detail & Related papers  (2024-06-17T04:35:17Z)
• Self-Guided Adaptation: Progressive Representation Alignment for Domain Adaptive Object Detection [86.69077525494106]
  Unsupervised domain adaptation (UDA) has achieved unprecedented success in improving the cross-domain robustness of object detection models. Existing UDA methods largely ignore the instantaneous data distribution during model learning, which could deteriorate the feature representation given large domain shift. We propose a Self-Guided Adaptation (SGA) model, target at aligning feature representation and transferring object detection models across domains.
  arXiv  Detail & Related papers  (2020-03-19T13:30:45Z)

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.