Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jain, Abhinav, Yao, Xinyu, Reps, Thomas, Jermaine, Christopher
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Prompt Tuning Strikes Back: Customizing Foundation Models with Low-Rank Prompt Adaptation
by: Jain, Abhinav, et al.
Published: (2024)

RAG-Modulo: Solving Sequential Tasks using Experience, Critics, and Language Models
by: Jain, Abhinav, et al.
Published: (2024)

On The Finetuning of MLIPs Through the Lens of Iterated Maps With BPTT
by: Dramko, Evan, et al.
Published: (2025)

A-MHA*: Anytime Multi-Heuristic A*
by: Natarajan, Ramkumar, et al.
Published: (2025)

Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control
by: Zheng, Longtao, et al.
Published: (2023)

KLAS: Using Similarity to Stitch Neural Networks for Improved Accuracy-Efficiency Tradeoffs
by: Sanyal, Debopam, et al.
Published: (2026)

Beyond Self-Consistency: Ensemble Reasoning Boosts Consistency and Accuracy of LLMs in Cancer Staging
by: Chang, Chia-Hsuan, et al.
Published: (2024)

Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars
by: Wu, Zhaoxuan, et al.
Published: (2024)

Mixture of Attention Schemes (MoAS): Learning to Route Between MHA, GQA, and MQA
by: Gumaan, Esmail
Published: (2025)

Lateral Tree-of-Thoughts Surpasses ToT by Incorporating Logically-Consistent, Low-Utility Candidates
by: Madahar, Abhinav
Published: (2025)

COM-BOM: Bayesian Exemplar Search for Efficiently Exploring the Accuracy-Calibration Pareto Frontier
by: Luo, Gaoxiang, et al.
Published: (2025)

Improving the Reliability of LLMs: Combining CoT, RAG, Self-Consistency, and Self-Verification
by: Kumar, Adarsh, et al.
Published: (2025)

Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers
by: Sawarkar, Kunal, et al.
Published: (2024)

Soft Self-Consistency Improves Language Model Agents
by: Wang, Han, et al.
Published: (2024)

Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization
by: Wan, Xingchen, et al.
Published: (2024)

Automated Tensor-Relational Decomposition for Large-Scale Sparse Tensor Computation
by: Tang, Yuxin, et al.
Published: (2026)

Contradiction Detection in RAG Systems: Evaluating LLMs as Context Validators for Improved Information Consistency
by: Gokul, Vignesh, et al.
Published: (2025)

Whisper-MLA: Reducing GPU Memory Consumption of ASR Models based on MHA2MLA Conversion
by: Zhang, Sen, et al.
Published: (2026)

Improving Statistical Significance in Human Evaluation of Automatic Metrics via Soft Pairwise Accuracy
by: Thompson, Brian, et al.
Published: (2024)

E^2GraphRAG: Streamlining Graph-based RAG for High Efficiency and Effectiveness
by: Zhao, Yibo, et al.
Published: (2025)

DANA: Domain-Aware Neurosymbolic Agents for Consistency and Accuracy
by: Luong, Vinh, et al.
Published: (2024)

Compressed Causal Reasoning: Quantization and GraphRAG Effects on Interventional and Counterfactual Accuracy
by: Nwaiwu, Steve, et al.
Published: (2025)

Dual Prompt-Driven Feature Encoding for Nighttime UAV Tracking
by: Wang, Yiheng, et al.
Published: (2026)

FB-RAG: Improving RAG with Forward and Backward Lookup
by: Chawla, Kushal, et al.
Published: (2025)

Aligning LLMs for the Classroom with Knowledge-Based Retrieval -- A Comparative RAG Study
by: Jain, Amay, et al.
Published: (2025)

Learning to Rotate: Temporal and Semantic Rotary Encoding for Sequential Modeling
by: Cheng, Hailing, et al.
Published: (2026)

Consistent and Distinctive: LLM Benchmark Efficiency via Maximum Independent Set Prompt Selection on Similarity Graphs
by: Kjorvezir, Denica, et al.
Published: (2026)

Enhancing Retrieval and Managing Retrieval: A Four-Module Synergy for Improved Quality and Efficiency in RAG Systems
by: Shi, Yunxiao, et al.
Published: (2024)

PEA: Enhancing LLM Performance on Computational-Reasoning Tasks
by: Wang, Zi, et al.
Published: (2025)

Enhancing RAG Efficiency with Adaptive Context Compression
by: Guo, Shuyu, et al.
Published: (2025)

Learning to Love Edge Cases in Formative Math Assessment: Using the AMMORE Dataset and Chain-of-Thought Prompting to Improve Grading Accuracy
by: Henkel, Owen, et al.
Published: (2024)

Exemplar-condensed Federated Class-incremental Learning
by: Sun, Rui, et al.
Published: (2024)

From RAG to RICHES: Retrieval Interlaced with Sequence Generation
by: Jain, Palak, et al.
Published: (2024)

Enhancing LLM-Based Text Classification in Political Science: Automatic Prompt Optimization and Dynamic Exemplar Selection for Few-Shot Learning
by: Liu, Menglin, et al.
Published: (2024)

Behavior Cue Reasoning: Monitorable Reasoning Improves Efficiency and Safety through Oversight
by: Cui, Christopher Z., et al.
Published: (2026)

RaFe: Ranking Feedback Improves Query Rewriting for RAG
by: Mao, Shengyu, et al.
Published: (2024)

Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts
by: Li, Sha, et al.
Published: (2026)

Tactile Memory with Soft Robot: Robust Object Insertion via Masked Encoding and Soft Wrist
by: Kamijo, Tatsuya, et al.
Published: (2026)

Characterizing Motion Encoding in Video Diffusion Timesteps
by: Baherwani, Vatsal, et al.
Published: (2025)

Beyond Captioning: Task-Specific Prompting for Improved VLM Performance in Mathematical Reasoning
by: Singh, Ayush, et al.
Published: (2024)