Cover Image

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lai, Kunfeng, Tang, Zhenheng, Pan, Xinglin, Dong, Peijie, Liu, Xiang, Chen, Haolan, Shen, Li, Li, Bo, Chu, Xiaowen
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language 68T50
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach
by: Liu, Linyu, et al.
Published: (2024)

Response Uncertainty and Probe Modeling: Two Sides of the Same Coin in LLM Interpretability?
by: Wang, Yongjie, et al.
Published: (2025)

D-SMART: Enhancing LLM Dialogue Consistency via Dynamic Structured Memory And Reasoning Tree
by: Lei, Xiang, et al.
Published: (2025)

LLM-Assisted Crisis Management: Building Advanced LLM Platforms for Effective Emergency Response and Public Collaboration
by: Otal, Hakan T., et al.
Published: (2024)

Dynamic Parameter Memory: Temporary LoRA-Enhanced LLM for Long-Sequence Emotion Recognition in Conversation
by: Mai, Jialong, et al.
Published: (2025)

RHealthTwin: Towards Responsible and Multimodal Digital Twins for Personalized Well-being
by: Ferdousi, Rahatara, et al.
Published: (2025)

Prompt Engineering and the Effectiveness of Large Language Models in Enhancing Human Productivity
by: Anam, Rizal Khoirul
Published: (2025)

MetaCheckGPT -- A Multi-task Hallucination Detector Using LLM Uncertainty and Meta-models
by: Mehta, Rahul, et al.
Published: (2024)

Monetizing Currency Pair Sentiments through LLM Explainability
by: Limonad, Lior, et al.
Published: (2024)

MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare
by: Wang, Yihao, et al.
Published: (2026)

The Compression Paradox in LLM Inference: Provider-Dependent Energy Effects of Prompt Compression
by: Johnson, Warren
Published: (2026)

$δ$-STEAL: LLM Stealing Attack with Local Differential Privacy
by: Dang, Kieu, et al.
Published: (2025)

Multi-Agent-as-Judge: Aligning LLM-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluation
by: Chen, Jiaju, et al.
Published: (2025)

Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing
by: Wang, Huanqian, et al.
Published: (2024)

RoleRAG: Enhancing LLM Role-Playing via Graph Guided Retrieval
by: Wang, Yongjie, et al.
Published: (2025)

OPENXRD: A Comprehensive Benchmark Framework for LLM/MLLM XRD Question Answering
by: Vosoughi, Ali, et al.
Published: (2025)

Unsolvability Ceiling in Multi-LLM Routing: An Empirical Study of Evaluation Artifacts
by: Garg, Saloni, et al.
Published: (2026)

SAGE: Sign-Adaptive Gradient for Memory-Efficient LLM Optimization
by: Lee, Wooin, et al.
Published: (2026)

Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?
by: Pan, Leyi, et al.
Published: (2025)

Parameter Tuning of the Firefly Algorithm by Standard Monte Carlo and Quasi-Monte Carlo Methods
by: Joy, Geethu, et al.
Published: (2024)

Bridging the Language Gap: Enhancing Multilingual Prompt-Based Code Generation in LLMs via Zero-Shot Cross-Lingual Transfer
by: Li, Mingda, et al.
Published: (2024)

Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolution
by: Guo, Dongxin, et al.
Published: (2026)

Parameter-Efficient Transformer Embeddings
by: Ndubuaku, Henry, et al.
Published: (2025)

Knowledge Editing for Large Language Model with Knowledge Neuronal Ensemble
by: Li, Yongchang, et al.
Published: (2024)

Auto prompt sql: a resource-efficient architecture for text-to-sql translation in constrained environments
by: Tang, Zetong, et al.
Published: (2025)

Towards Probabilistic Question Answering Over Tabular Data
by: Shen, Chen, et al.
Published: (2025)

Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-training
by: Li, Shengrui, et al.
Published: (2026)

BayesRAG: Probabilistic Mutual Evidence Corroboration for Multimodal Retrieval-Augmented Generation
by: Li, Xuan, et al.
Published: (2026)

Improving Recursive Transformers with Mixture of LoRAs
by: Nouriborji, Mohammadmahdi, et al.
Published: (2025)

Tatarstan Toponyms: A Bilingual Dataset and Hybrid RAG System for Geospatial Question Answering
by: Arabov, Mullosharaf K.
Published: (2026)

Survey of Swarm Intelligence Approaches to Search Documents Based On Semantic Similarity
by: Muniyappa, Chandrashekar, et al.
Published: (2025)

LangMARL: Natural Language Multi-Agent Reinforcement Learning
by: Yao, Huaiyuan, et al.
Published: (2026)

DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models
by: Marjanović, Sara Vera, et al.
Published: (2024)

An Iterative Optimizing Framework for Radiology Report Summarization with ChatGPT
by: Ma, Chong, et al.
Published: (2023)

Ask Safely: Privacy-Aware LLM Query Generation for Knowledge Graphs
by: Tosi, Mauro Dalle Lucca, et al.
Published: (2025)

$\text{Memory}^3$: Language Modeling with Explicit Memory
by: Yang, Hongkang, et al.
Published: (2024)

When Does Content-Based Routing Work? Representation Requirements for Selective Attention in Hybrid Sequence Models
by: Basu, Abhinaba
Published: (2026)

Exploring and Reshaping the Weight Distribution in LLM
by: Ye, Chunming, et al.
Published: (2025)

ByteRover: Agent-Native Memory Through LLM-Curated Hierarchical Context
by: Nguyen, Andy, et al.
Published: (2026)

BMAM: Brain-inspired Multi-Agent Memory Framework
by: Li, Yang, et al.
Published: (2026)