Image de couverture de livre

Geometric Analysis of Reasoning Trajectories: A Phase Space Approach to Understanding Valid and Invalid Multi-Hop Reasoning in LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Marin, Javier
Format:	Preprint
Publié:	2024
Sujets:	Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Fully Geometric Multi-Hop Reasoning on Knowledge Graphs with Transitive Relations
par: Zhapa-Camacho, Fernando, et autres
Publié: (2025)

What Makes Reasoning Invalid: Echo Reflection Mitigation for Large Language Models
par: He, Chen, et autres
Publié: (2025)

When Reasoning Meets Compression: Understanding the Effects of LLMs Compression on Large Reasoning Models
par: Zhang, Nan, et autres
Publié: (2025)

DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search
par: Yue, Murong, et autres
Publié: (2024)

ChemFixer: Correcting Invalid Molecules to Unlock Previously Unseen Chemical Space
par: Park, Jun-Hyoung, et autres
Publié: (2025)

Examining Two Hop Reasoning Through Information Content Scaling
par: Johnston, David, et autres
Publié: (2025)

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

Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty
par: Kim, Jeonghye, et autres
Publié: (2026)

Validity-Calibrated Reasoning Distillation
par: Saadi, Khouloud, et autres
Publié: (2026)

Effect of Document Packing on the Latent Multi-Hop Reasoning Capabilities of Large Language Models
par: Prato, Gabriele, et autres
Publié: (2025)

ActivationReasoning: Logical Reasoning in Latent Activation Spaces
par: Helff, Lukas, et autres
Publié: (2025)

Time Series Forecasting as Reasoning: A Slow-Thinking Approach with Reinforced LLMs
par: Zhou, Yitong, et autres
Publié: (2025)

The Geometric Reasoner: Manifold-Informed Latent Foresight Search for Long-Context Reasoning
par: Zhuang, Ren, et autres
Publié: (2026)

ReasonCACHE: Teaching LLMs To Reason Without Weight Updates
par: Gupta, Sharut, et autres
Publié: (2026)

RADAR: Reasoning-Ability and Difficulty-Aware Routing for Reasoning LLMs
par: Fernandez, Nigel, et autres
Publié: (2025)

Understanding Tool-Integrated Reasoning
par: Lin, Heng, et autres
Publié: (2025)

Leveraging Parameter Space Symmetries for Reasoning Skill Transfer in LLMs
par: Horoi, Stefan, et autres
Publié: (2025)

Beyond Generation: Multi-Hop Reasoning for Factual Accuracy in Vision-Language Models
par: Hossain, Shamima
Publié: (2025)

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

Probing the Trajectories of Reasoning Traces in Large Language Models
par: Ballon, Marthe, et autres
Publié: (2026)

Are Your Reasoning Models Reasoning or Guessing? A Mechanistic Analysis of Hierarchical Reasoning Models
par: Ren, Zirui, et autres
Publié: (2026)

Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models
par: Sakarvadia, Mansi, et autres
Publié: (2023)

Efficient Parallel Multi-Hop Reasoning: A Scalable Approach for Knowledge Graph Analysis
par: Tithi, Jesmin Jahan, et autres
Publié: (2024)

On the Empirical Complexity of Reasoning and Planning in LLMs
par: Kang, Liwei, et autres
Publié: (2024)

Temporal Sampling for Forgotten Reasoning in LLMs
par: Li, Yuetai, et autres
Publié: (2025)

CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs
par: Zeng, Yongcheng, et autres
Publié: (2025)

Knowledge Editing for Multi-Hop Question Answering Using Semantic Analysis
par: Simon, Dominic, et autres
Publié: (2025)

Quantization Meets Reasoning: Exploring and Mitigating Degradation of Low-Bit LLMs in Mathematical Reasoning
par: Li, Zhen, et autres
Publié: (2025)

Reshaping Reasoning in LLMs: A Theoretical Analysis of RL Training Dynamics through Pattern Selection
par: Chen, Xingwu, et autres
Publié: (2025)

Structural Reasoning Improves Molecular Understanding of LLM
par: Jang, Yunhui, et autres
Publié: (2024)

Quantifying and Understanding Uncertainty in Large Reasoning Models
par: Li, Yangyi, et autres
Publié: (2026)

Calibration-Aware Policy Optimization for Reasoning LLMs
par: Wang, Ziqi, et autres
Publié: (2026)

Broken Chains: The Cost of Incomplete Reasoning in LLMs
par: Su, Ian, et autres
Publié: (2026)

CARE: Turning LLMs Into Causal Reasoning Expert
par: Dong, Juncheng, et autres
Publié: (2025)

Post-Training as Reweighting: A Stochastic View of Reasoning Trajectories in Language Models
par: Bu, Dake, et autres
Publié: (2025)

Loss Given Default Prediction Under Measurement-Induced Mixture Distributions: An Information-Theoretic Approach
par: Marín, Javier
Publié: (2025)

Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards
par: Fan, Jiajun, et autres
Publié: (2025)

CIRCUIT: A Benchmark for Circuit Interpretation and Reasoning Capabilities of LLMs
par: Skelic, Lejla, et autres
Publié: (2025)

Can Stories Help LLMs Reason? Curating Information Space Through Narrative
par: Javadi, Vahid Sadiri, et autres
Publié: (2024)

A Implies B: Circuit Analysis in LLMs for Propositional Logical Reasoning
par: Hong, Guan Zhe, et autres
Publié: (2024)