Cover Image

Scaling Reasoning Hop Exposes Weaknesses: Demystifying and Improving Hop Generalization in Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Zhaoyi, Li, Jiatong, Jiang, Gangwei, Song, Linqi, Lian, Defu, Wei, Ying
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing
by: Wang, Weichuan, et al.
Published: (2024)

Understanding and Patching Compositional Reasoning in LLMs
by: Li, Zhaoyi, et al.
Published: (2024)

Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning
by: Jiang, Gangwei, et al.
Published: (2025)

Mitigate Negative Transfer with Similarity Heuristic Lifelong Prompt Tuning
by: Wu, Chenyuan, et al.
Published: (2024)

On the Role of Reasoning Patterns in the Generalization Discrepancy of Long Chain-of-Thought Supervised Fine-Tuning
by: Li, Zhaoyi, et al.
Published: (2026)

Refine Large Language Model Fine-tuning via Instruction Vector
by: Jiang, Gangwei, et al.
Published: (2024)

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

Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering
by: Shi, Yuling, et al.
Published: (2026)

Learning to Substitute Components for Compositional Generalization
by: Li, Zhaoyi, et al.
Published: (2025)

Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation
by: Zhong, Tianqi, et al.
Published: (2024)

Fact or Guesswork? Evaluating Large Language Models' Medical Knowledge with Structured One-Hop Judgments
by: Li, Jiaxi, et al.
Published: (2025)

Effect of Document Packing on the Latent Multi-Hop Reasoning Capabilities of Large Language Models
by: Prato, Gabriele, et al.
Published: (2025)

Scaling Multi-Hop Training Data via Graph-Constrained Path Selection
by: Chen, Pengyu, et al.
Published: (2026)

Towards Interpreting Language Models: A Case Study in Multi-Hop Reasoning
by: Sakarvadia, Mansi
Published: (2024)

Cognitive Load Limits in Large Language Models: Benchmarking Multi-Hop Reasoning
by: Adapala, Sai Teja Reddy
Published: (2025)

Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models
by: Sakarvadia, Mansi, et al.
Published: (2023)

What Makes a Good Reasoning Chain? Uncovering Structural Patterns in Long Chain-of-Thought Reasoning
by: Jiang, Gangwei, et al.
Published: (2025)

Demystifying Verbatim Memorization in Large Language Models
by: Huang, Jing, et al.
Published: (2024)

Fine-Tuning vs. RAG for Multi-Hop Question Answering with Novel Knowledge
by: Yang, Zhuoyi, et al.
Published: (2026)

Retrieval-enhanced Knowledge Editing in Language Models for Multi-Hop Question Answering
by: Shi, Yucheng, et al.
Published: (2024)

CRIT: Graph-Based Automatic Data Synthesis to Enhance Cross-Modal Multi-Hop Reasoning
by: Sung, Junyoung, et al.
Published: (2026)

Progressive-Hint Prompting Improves Reasoning in Large Language Models
by: Zheng, Chuanyang, et al.
Published: (2023)

CRAFT: Calibrated Reasoning with Answer-Faithful Traces via Reinforcement Learning for Multi-Hop Question Answering
by: Liu, Yu, et al.
Published: (2026)

Demystifying Embedding Spaces using Large Language Models
by: Tennenholtz, Guy, et al.
Published: (2023)

GTM: A General Time-series Model for Enhanced Representation Learning of Time-Series Data
by: He, Cheng, et al.
Published: (2025)

Internal Value Alignment in Large Language Models through Controlled Value Vector Activation
by: Jin, Haoran, et al.
Published: (2025)

The Illusionist's Prompt: Exposing the Factual Vulnerabilities of Large Language Models with Linguistic Nuances
by: Wang, Yining, et al.
Published: (2025)

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

Demystifying OPD: Length Inflation and Stabilization Strategies for Large Language Models
by: Luo, Feng, et al.
Published: (2026)

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

Reasoning is Periodicity? Improving Large Language Models Through Effective Periodicity Modeling
by: Dong, Yihong, et al.
Published: (2025)

Demystifying Low-Rank Knowledge Distillation in Large Language Models: Convergence, Generalization, and Information-Theoretic Guarantees
by: Soarez, Alberlucia Rafael, et al.
Published: (2026)

Enhancing Document-Level Question Answering via Multi-Hop Retrieval-Augmented Generation with LLaMA 3
by: Huang, Xinyue, et al.
Published: (2025)

MULTIVERSE: Exposing Large Language Model Alignment Problems in Diverse Worlds
by: Jin, Xiaolong, et al.
Published: (2024)

Examining Two Hop Reasoning Through Information Content Scaling
by: Johnston, David, et al.
Published: (2025)

Demystifying and Enhancing the Efficiency of Large Language Model Based Search Agents
by: Yang, Tiannuo, et al.
Published: (2025)

Demystifying Long Chain-of-Thought Reasoning in LLMs
by: Yeo, Edward, et al.
Published: (2025)

PromptCoT 2.0: Scaling Prompt Synthesis for Large Language Model Reasoning
by: Zhao, Xueliang, et al.
Published: (2025)

Scaling Trends for Multi-Hop Contextual Reasoning in Mid-Scale Language Models
by: Steele, Brady, et al.
Published: (2026)

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