Buchumschlag

Understanding Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Wang, Xinyi, Amayuelas, Alfonso, Zhang, Kexun, Pan, Liangming, Chen, Wenhu, Wang, William Yang
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Machine Learning Artificial Intelligence Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Knowledge of Knowledge: Exploring Known-Unknowns Uncertainty with Large Language Models
von: Amayuelas, Alfonso, et al.
Veröffentlicht: (2023)

Investigating the Transferability of Code Repair for Low-Resource Programming Languages
von: Wong, Kyle, et al.
Veröffentlicht: (2024)

Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data
von: Wang, Xinyi, et al.
Veröffentlicht: (2024)

MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debate
von: Amayuelas, Alfonso, et al.
Veröffentlicht: (2024)

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

How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmark
von: Yang, Minglai, et al.
Veröffentlicht: (2025)

Towards Reasoning Ability of Small Language Models
von: Srivastava, Gaurav, et al.
Veröffentlicht: (2025)

Guiding Language Model Reasoning with Planning Tokens
von: Wang, Xinyi, et al.
Veröffentlicht: (2023)

DebUnc: Improving Large Language Model Agent Communication With Uncertainty Metrics
von: Yoffe, Luke, et al.
Veröffentlicht: (2024)

On the Reasoning Abilities of Masked Diffusion Language Models
von: Svete, Anej, et al.
Veröffentlicht: (2025)

Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths
von: Chia, Yew Ken, et al.
Veröffentlicht: (2024)

Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism
von: Wang, Zhiwei, et al.
Veröffentlicht: (2024)

Understanding Emergent Abilities of Language Models from the Loss Perspective
von: Du, Zhengxiao, et al.
Veröffentlicht: (2024)

Atomic Skills are the Prerequisite: When Reinforcement Learning Synthesizes Compositional Reasoning, and When It Only Amplifies
von: Cheng, Sitao, et al.
Veröffentlicht: (2025)

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

SpaRC and SpaRP: Spatial Reasoning Characterization and Path Generation for Understanding Spatial Reasoning Capability of Large Language Models
von: Rizvi, Md Imbesat Hassan, et al.
Veröffentlicht: (2024)

Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization
von: Ji, Kaixuan, et al.
Veröffentlicht: (2024)

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

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

$π^2$: Structure-Originated Reasoning Data Improves Long-Context Reasoning Ability of Large Language Models
von: Do, Quyet V., et al.
Veröffentlicht: (2026)

Eliciting Causal Abilities in Large Language Models for Reasoning Tasks
von: Wang, Yajing, et al.
Veröffentlicht: (2024)

SciAgent: Tool-augmented Language Models for Scientific Reasoning
von: Ma, Yubo, et al.
Veröffentlicht: (2024)

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

ConciseRL: Conciseness-Guided Reinforcement Learning for Efficient Reasoning Models
von: Dumitru, Razvan-Gabriel, et al.
Veröffentlicht: (2025)

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

Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning
von: Yang, Wang, et al.
Veröffentlicht: (2025)

LEDOM: Reverse Language Model
von: Yin, Xunjian, et al.
Veröffentlicht: (2025)

Variational Reasoning for Language Models
von: Zhou, Xiangxin, et al.
Veröffentlicht: (2025)

An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning
von: Chen, Zui, et al.
Veröffentlicht: (2024)

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

MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining
von: Xiaomi, LLM-Core, et al.
Veröffentlicht: (2025)

A Survey on Enhancing Causal Reasoning Ability of Large Language Models
von: Li, Xin, et al.
Veröffentlicht: (2025)

Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld's Episode Theory
von: Li, Ming, et al.
Veröffentlicht: (2025)

Reducing Credit Assignment Variance via Counterfactual Reasoning Paths
von: Ding, Fei, et al.
Veröffentlicht: (2026)

MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations
von: Huang, Kaixuan, et al.
Veröffentlicht: (2025)

AQA-Bench: An Interactive Benchmark for Evaluating LLMs' Sequential Reasoning Ability
von: Yang, Siwei, et al.
Veröffentlicht: (2024)

Pre-trained Language Models Improve the Few-shot Prompt Ability of Decision Transformer
von: Yang, Yu, et al.
Veröffentlicht: (2024)

Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time
von: Zhang, Zhenyu, et al.
Veröffentlicht: (2025)

Understanding Reasoning in Chain-of-Thought from the Hopfieldian View
von: Hu, Lijie, et al.
Veröffentlicht: (2024)

Assessing the Emergent Symbolic Reasoning Abilities of Llama Large Language Models
von: Petruzzellis, Flavio, et al.
Veröffentlicht: (2024)