Imagen de Portada

Dynamic Reasoning Chains through Depth-Specialized Mixture-of-Experts in Transformer Architectures

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Roy, Sampurna, Sar, Ayan, Kaushish, Anurag, Gupta, Kanav, Choudhury, Tanupriya, Kumar, Abhijit
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence Information Retrieval
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Hierarchical Resolution Transformers: A Wavelet-Inspired Architecture for Multi-Scale Language Understanding
por: Sar, Ayan, et al.
Publicado: (2025)

SwasthLLM: a Unified Cross-Lingual, Multi-Task, and Meta-Learning Zero-Shot Framework for Medical Diagnosis Using Contrastive Representations
por: Sar, Ayan, et al.
Publicado: (2025)

Adaptive Multi-Scale Correlation Meta-Network for Few-Shot Remote Sensing Image Classification
por: Kaushish, Anurag, et al.
Publicado: (2026)

Navigating Nuance: In Quest for Political Truth
por: Sar, Soumyadeep, et al.
Publicado: (2025)

Zero-Shot Visual Deepfake Detection: Can AI Predict and Prevent Fake Content Before It's Created?
por: Sar, Ayan, et al.
Publicado: (2025)

Is Architectural Complexity Overrated? Competitive and Interpretable Knowledge Graph Completion with RelatE
por: Chakraborty, Abhijit, et al.
Publicado: (2025)

Federated Retrieval-Augmented Generation: A Systematic Mapping Study
por: Chakraborty, Abhijit, et al.
Publicado: (2025)

ExpertGenQA: Open-ended QA generation in Specialized Domains
por: Shahgir, Haz Sameen, et al.
Publicado: (2025)

Evaluating Chain-of-Thought Reasoning through Reusability and Verifiability
por: Aggarwal, Shashank, et al.
Publicado: (2026)

Multilingual Information Retrieval with a Monolingual Knowledge Base
por: Zhuang, Yingying, et al.
Publicado: (2025)

Model Editing at Scale leads to Gradual and Catastrophic Forgetting
por: Gupta, Akshat, et al.
Publicado: (2024)

Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs
por: Jin, Bowen, et al.
Publicado: (2024)

Training Sparse Mixture Of Experts Text Embedding Models
por: Nussbaum, Zach, et al.
Publicado: (2025)

Cost-Aware Retrieval-Augmentation Reasoning Models with Adaptive Retrieval Depth
por: Hashemi, Helia, et al.
Publicado: (2025)

Routing Distilled Knowledge via Mixture of LoRA Experts for Large Language Model based Bundle Generation
por: Feng, Kaidong, et al.
Publicado: (2025)

ExpertRAG: Efficient RAG with Mixture of Experts -- Optimizing Context Retrieval for Adaptive LLM Responses
por: Gumaan, Esmail
Publicado: (2025)

Causal-Counterfactual RAG: The Integration of Causal-Counterfactual Reasoning into RAG
por: Khadilkar, Harshad, et al.
Publicado: (2025)

LM4OPT: Unveiling the Potential of Large Language Models in Formulating Mathematical Optimization Problems
por: Ahmed, Tasnim, et al.
Publicado: (2024)

Toward Effective Multi-Domain Rumor Detection in Social Networks Using Domain-Gated Mixture-of-Experts
por: Sheikhqoraei, Mohadeseh, et al.
Publicado: (2026)

Multi-Type Context-Aware Conversational Recommender Systems via Mixture-of-Experts
por: Zou, Jie, et al.
Publicado: (2025)

StepChain GraphRAG: Reasoning Over Knowledge Graphs for Multi-Hop Question Answering
por: Ni, Tengjun, et al.
Publicado: (2025)

Long Dialog Summarization: An Analysis
por: Mullick, Ankan, et al.
Publicado: (2024)

ADEQA: A Question Answer based approach for joint ADE-Suspect Extraction using Sequence-To-Sequence Transformers
por: Arannil, Vinayak, et al.
Publicado: (2024)

On The Persona-based Summarization of Domain-Specific Documents
por: Mullick, Ankan, et al.
Publicado: (2024)

A Language-Driven Framework for Improving Personalized Recommendations: Merging LLMs with Traditional Algorithms
por: Goldstein, Aaron, et al.
Publicado: (2025)

REFINE on Scarce Data: Retrieval Enhancement through Fine-Tuning via Model Fusion of Embedding Models
por: Gupta, Ambuje, et al.
Publicado: (2024)

MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
por: Huynh, Tuan-Luc, et al.
Publicado: (2025)

On the Biased Assessment of Expert Finding Systems
por: Decorte, Jens-Joris, et al.
Publicado: (2024)

DyG-RAG: Dynamic Graph Retrieval-Augmented Generation with Event-Centric Reasoning
por: Sun, Qingyun, et al.
Publicado: (2025)

Structure-R1: Dynamically Leveraging Structural Knowledge in LLM Reasoning through Reinforcement Learning
por: Wu, Junlin, et al.
Publicado: (2025)

Chain-of-Retrieval Augmented Generation
por: Wang, Liang, et al.
Publicado: (2025)

Navigating Through Paper Flood: Advancing LLM-based Paper Evaluation through Domain-Aware Retrieval and Latent Reasoning
por: Zheng, Wuqiang, et al.
Publicado: (2025)

Retrieval-Augmented Reasoning for Chartered Accountancy
por: Gupta, Jatin, et al.
Publicado: (2026)

Conversational Text Extraction with Large Language Models Using Retrieval-Augmented Systems
por: Roy, Soham, et al.
Publicado: (2025)

Ontology Matching with Large Language Models and Prioritized Depth-First Search
por: Taboada, Maria, et al.
Publicado: (2025)

FoodSEM: Large Language Model Specialized in Food Named-Entity Linking
por: Gjorgjevikj, Ana, et al.
Publicado: (2025)

MedEIR: A Specialized Medical Embedding Model for Enhanced Information Retrieval
por: Selvadurai, Anand, et al.
Publicado: (2025)

Stemming -- The Evolution and Current State with a Focus on Bangla
por: Paul, Abhijit, et al.
Publicado: (2025)

Evidence-Guided Schema Normalization for Temporal Tabular Reasoning
por: Thanga, Ashish, et al.
Publicado: (2025)

MODS: Moderating a Mixture of Document Speakers to Summarize Debatable Queries in Document Collections
por: Balepur, Nishant, et al.
Publicado: (2025)