Imagen de Portada

CRIT: Graph-Based Automatic Data Synthesis to Enhance Cross-Modal Multi-Hop Reasoning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Sung, Junyoung, Lyu, Seungwoo, Kim, Minjun, An, Sumin, Nagrani, Arsha, Seo, Paul Hongsuck
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

LCIRC: A Recurrent Compression Approach for Efficient Long-form Context and Query Dependent Modeling in LLMs
por: An, Sumin, et al.
Publicado: (2025)

ReTAG: Retrieval-Enhanced, Topic-Augmented Graph-Based Global Sensemaking
por: Kim, Boyoung, et al.
Publicado: (2025)

FCMR: Robust Evaluation of Financial Cross-Modal Multi-Hop Reasoning
por: Kim, Seunghee, et al.
Publicado: (2024)

BOK-VQA: Bilingual outside Knowledge-Based Visual Question Answering via Graph Representation Pretraining
por: Kim, Minjun, et al.
Publicado: (2024)

Direct Diffusion Score Preference Optimization via Stepwise Contrastive Policy-Pair Supervision
por: Kim, Dohyun, et al.
Publicado: (2025)

OMHBench: Benchmarking Balanced and Grounded Omni-Modal Multi-Hop Reasoning
por: Kim, Seunghee, et al.
Publicado: (2025)

ReSCORE: Label-free Iterative Retriever Training for Multi-hop Question Answering with Relevance-Consistency Supervision
por: Lee, Dosung, et al.
Publicado: (2025)

HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning
por: Wang, Shenzhi, et al.
Publicado: (2026)

FactCG: Enhancing Fact Checkers with Graph-Based Multi-Hop Data
por: Lei, Deren, et al.
Publicado: (2025)

MV-CLAM: Multi-View Molecular Interpretation with Cross-Modal Projection via Language Model
por: Ha, Sumin, et al.
Publicado: (2025)

Breaking the Visual Shortcuts in Multimodal Knowledge-Based Visual Question Answering
por: Lee, Dosung, et al.
Publicado: (2025)

HopWeaver: Cross-Document Synthesis of High-Quality and Authentic Multi-Hop Questions
por: Shen, Zhiyu, et al.
Publicado: (2025)

BioHopR: A Benchmark for Multi-Hop, Multi-Answer Reasoning in Biomedical Domain
por: Kim, Yunsoo, et al.
Publicado: (2025)

Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries
por: Kim, Minyoung, et al.
Publicado: (2025)

Making Long-Context Language Models Better Multi-Hop Reasoners
por: Li, Yanyang, et al.
Publicado: (2024)

Cross-Modal State-Space Graph Reasoning for Structured Summarization
por: Kim, Hannah, et al.
Publicado: (2025)

Automatic Inter-document Multi-hop Scientific QA Generation
por: Lee, Seungmin, et al.
Publicado: (2026)

SciNets: Graph-Constrained Multi-Hop Reasoning for Scientific Literature Synthesis
por: Dubey, Sauhard
Publicado: (2025)

DocHop-QA: Towards Multi-Hop Reasoning over Multimodal Document Collections
por: Park, Jiwon, et al.
Publicado: (2025)

Auto-Patching: Enhancing Multi-Hop Reasoning in Language Models
por: Jan, Aviv, et al.
Publicado: (2025)

Hierarchical Lexical Graph for Enhanced Multi-Hop Retrieval
por: Ghassel, Abdellah, et al.
Publicado: (2025)

Chat-TS: Enhancing Multi-Modal Reasoning Over Time-Series and Natural Language Data
por: Quinlan, Paul, et al.
Publicado: (2025)

Robust Image Self-Recovery against Tampering using Watermark Generation with Pixel Shuffling
por: Kim, Minyoung, et al.
Publicado: (2025)

P-RAG: Prompt-Enhanced Parametric RAG with LoRA and Selective CoT for Biomedical and Multi-Hop QA
por: Lyu, Xingda, et al.
Publicado: (2026)

MAGIC: A Multi-Hop and Graph-Based Benchmark for Inter-Context Conflicts in Retrieval-Augmented Generation
por: Lee, Jungyeon, et al.
Publicado: (2025)

More than a Moment: Towards Coherent Sequences of Audio Descriptions
por: Khandelwal, Eshika, et al.
Publicado: (2025)

Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models
por: Yu, Zeping, et al.
Publicado: (2025)

R2-KG: General-Purpose Dual-Agent Framework for Reliable Reasoning on Knowledge Graphs
por: Jo, Sumin, et al.
Publicado: (2025)

MoReVQA: Exploring Modular Reasoning Models for Video Question Answering
por: Min, Juhong, et al.
Publicado: (2024)

GOAT: A Training Framework for Goal-Oriented Agent with Tools
por: Min, Hyunji, et al.
Publicado: (2025)

KG-Reasoner: A Reinforced Model for End-to-End Multi-Hop Knowledge Graph Reasoning
por: Wang, Shuai, et al.
Publicado: (2026)

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

NovelHopQA: Diagnosing Multi-Hop Reasoning Failures in Long Narrative Contexts
por: Gupta, Abhay, et al.
Publicado: (2025)

Can David Beat Goliath? On Multi-Hop Reasoning with Resource-Constrained Agents
por: Han, Hojae, et al.
Publicado: (2026)

Few-Shot Data Synthesis for Open Domain Multi-Hop Question Answering
por: Chen, Mingda, et al.
Publicado: (2023)

HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation
por: Liu, Hao, et al.
Publicado: (2025)

PQ-GCN: Enhancing Text Graph Question Classification with Phrase Features
por: Lee, Junyoung, et al.
Publicado: (2024)

Semantic Bridge: Universal Multi-Hop Question Generation via AMR-Driven Graph Synthesis
por: Chen, Linqing, et al.
Publicado: (2025)

Cross-Lingual Multi-Hop Knowledge Editing
por: Khandelwal, Aditi, et al.
Publicado: (2024)

Reasoning Court: Combining Reasoning, Action, and Judgment for Multi-Hop Reasoning
por: Wu, Jingtian, et al.
Publicado: (2025)