Copertina

Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hu, Yi, Gu, Jiaqi, Wang, Ruxin, Yao, Zijun, Peng, Hao, Wu, Xiaobao, Chen, Jianhui, Zhang, Muhan, Pan, Liangming
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units
di: Chen, Jianhui, et al.
Pubblicazione: (2026)

Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons
di: Chen, Jianhui, et al.
Pubblicazione: (2024)

Towards a Mechanistic Understanding of Propositional Logical Reasoning in Large Language Models
di: Chen, Danchun, et al.
Pubblicazione: (2026)

AKEW: Assessing Knowledge Editing in the Wild
di: Wu, Xiaobao, et al.
Pubblicazione: (2024)

Towards Intrinsic Interpretability of Large Language Models:A Survey of Design Principles and Architectures
di: Gao, Yutong, et al.
Pubblicazione: (2026)

RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios
di: Zhou, Ruiwen, et al.
Pubblicazione: (2024)

Modeling Dynamic Topics in Chain-Free Fashion by Evolution-Tracking Contrastive Learning and Unassociated Word Exclusion
di: Wu, Xiaobao, et al.
Pubblicazione: (2024)

Opening the Black Box: A Survey on the Mechanisms of Multi-Step Reasoning in Large Language Models
di: Pan, Liangming, et al.
Pubblicazione: (2026)

InfoCTM: A Mutual Information Maximization Perspective of Cross-Lingual Topic Modeling
di: Wu, Xiaobao, et al.
Pubblicazione: (2023)

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards
di: Wu, Xiaobao
Pubblicazione: (2025)

Understanding the Interplay between Parametric and Contextual Knowledge for Large Language Models
di: Cheng, Sitao, et al.
Pubblicazione: (2024)

What Affects the Effective Depth of Large Language Models?
di: Hu, Yi, et al.
Pubblicazione: (2025)

SubTokenTest: A Practical Benchmark for Real-World Sub-token Understanding
di: Hou, Shuyang, et al.
Pubblicazione: (2026)

Understanding LLMs: A Comprehensive Overview from Training to Inference
di: Liu, Yiheng, et al.
Pubblicazione: (2024)

SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation
di: Yao, Zijun, et al.
Pubblicazione: (2024)

Understanding Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation
di: Wang, Xinyi, et al.
Pubblicazione: (2024)

Faithful Logical Reasoning via Symbolic Chain-of-Thought
di: Xu, Jundong, et al.
Pubblicazione: (2024)

LooGLE: Can Long-Context Language Models Understand Long Contexts?
di: Li, Jiaqi, et al.
Pubblicazione: (2023)

CausalEval: Towards Better Causal Reasoning in Language Models
di: Yu, Longxuan, et al.
Pubblicazione: (2024)

Efficient Inference for Large Reasoning Models: A Survey
di: Liu, Yue, et al.
Pubblicazione: (2025)

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning
di: Zhu, Rongzhi, et al.
Pubblicazione: (2025)

Parrot Mind: Towards Explaining the Complex Task Reasoning of Pretrained Large Language Models with Template-Content Structure
di: Yang, Haotong, et al.
Pubblicazione: (2023)

Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models
di: Chen, Qiguang, et al.
Pubblicazione: (2025)

Do Latent-CoT Models Think Step-by-Step? A Mechanistic Study on Sequential Reasoning Tasks
di: Liang, Jia, et al.
Pubblicazione: (2026)

COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement
di: Xie, Yuxi, et al.
Pubblicazione: (2024)

Retrieval Head Mechanistically Explains Long-Context Factuality
di: Wu, Wenhao, et al.
Pubblicazione: (2024)

Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models
di: Wang, Rui, et al.
Pubblicazione: (2025)

Number Cookbook: Number Understanding of Language Models and How to Improve It
di: Yang, Haotong, et al.
Pubblicazione: (2024)

Towards the TopMost: A Topic Modeling System Toolkit
di: Wu, Xiaobao, et al.
Pubblicazione: (2023)

Large Language Models for Subjective Language Understanding: A Survey
di: Song, Changhao, et al.
Pubblicazione: (2025)

Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
di: Xu, Fengli, et al.
Pubblicazione: (2025)

Towards Verifiable Generation: A Benchmark for Knowledge-aware Language Model Attribution
di: Li, Xinze, et al.
Pubblicazione: (2023)

TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning
di: Lu, Xinyuan, et al.
Pubblicazione: (2024)

Towards Understanding the Cognitive Habits of Large Reasoning Models
di: Dong, Jianshuo, et al.
Pubblicazione: (2025)

TokMem: One-Token Procedural Memory for Large Language Models
di: Wu, Zijun, et al.
Pubblicazione: (2025)

Answering the Unanswerable Is to Err Knowingly: Analyzing and Mitigating Abstention Failures in Large Reasoning Models
di: Liu, Yi, et al.
Pubblicazione: (2025)

Are Reasoning Models More Prone to Hallucination?
di: Yao, Zijun, et al.
Pubblicazione: (2025)

The Knowledge Alignment Problem: Bridging Human and External Knowledge for Large Language Models
di: Zhang, Shuo, et al.
Pubblicazione: (2023)

Diagnosing Training Inference Mismatch in LLM Reinforcement Learning
di: Zhong, Tianle, et al.
Pubblicazione: (2026)

Tracking the Feature Dynamics in LLM Training: A Mechanistic Study
di: Xu, Yang, et al.
Pubblicazione: (2024)