Copertina

Iteration Head: A Mechanistic Study of Chain-of-Thought

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Cabannes, Vivien, Arnal, Charles, Bouaziz, Wassim, Yang, Alice, Charton, Francois, Kempe, Julia
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Touring sampling with pushforward maps
di: Cabannes, Vivien, et al.
Pubblicazione: (2023)

A Tale of Tails: Model Collapse as a Change of Scaling Laws
di: Dohmatob, Elvis, et al.
Pubblicazione: (2024)

Clustering Head: A Visual Case Study of the Training Dynamics in Transformers
di: Odonnat, Ambroise, et al.
Pubblicazione: (2024)

Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards
di: Arnal, Charles, et al.
Pubblicazione: (2025)

Emergent properties with repeated examples
di: Charton, François, et al.
Pubblicazione: (2024)

Provable Benefits of In-Tool Learning for Large Language Models
di: Houliston, Sam, et al.
Pubblicazione: (2025)

Learning with Hidden Factorial Structure
di: Arnal, Charles, et al.
Pubblicazione: (2024)

Unveiling Simplicities of Attention: Adaptive Long-Context Head Identification
di: Donhauser, Konstantin, et al.
Pubblicazione: (2025)

Easing Optimization Paths: a Circuit Perspective
di: Odonnat, Ambroise, et al.
Pubblicazione: (2025)

Understanding Chain-of-Thought in LLMs through Information Theory
di: Ton, Jean-Francois, et al.
Pubblicazione: (2024)

Instruction Diversity Drives Generalization To Unseen Tasks
di: Zhang, Dylan, et al.
Pubblicazione: (2024)

Mission Impossible: A Statistical Perspective on Jailbreaking LLMs
di: Su, Jingtong, et al.
Pubblicazione: (2024)

Efficient RL Training for LLMs with Experience Replay
di: Arnal, Charles, et al.
Pubblicazione: (2026)

Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification
di: Feng, Yunzhen, et al.
Pubblicazione: (2024)

From Concepts to Components: Concept-Agnostic Attention Module Discovery in Transformers
di: Su, Jingtong, et al.
Pubblicazione: (2025)

From Symbolic Tasks to Code Generation: Diversification Yields Better Task Performers
di: Zhang, Dylan, et al.
Pubblicazione: (2024)

$\textbf{Only-IF}$:Revealing the Decisive Effect of Instruction Diversity on Generalization
di: Zhang, Dylan, et al.
Pubblicazione: (2024)

Scaling Laws for Associative Memories
di: Cabannes, Vivien, et al.
Pubblicazione: (2023)

Enhancing Generalization in Chain of Thought Reasoning for Smaller Models
di: Yin, Maxwell J., et al.
Pubblicazione: (2025)

The Galerkin method beats Graph-Based Approaches for Spectral Algorithms
di: Cabannes, Vivien, et al.
Pubblicazione: (2023)

A Formal Comparison Between Chain of Thought and Latent Thought
di: Xu, Kevin, et al.
Pubblicazione: (2025)

Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization
di: Zaman, Kerem, et al.
Pubblicazione: (2025)

Fractured Chain-of-Thought Reasoning
di: Liao, Baohao, et al.
Pubblicazione: (2025)

Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models
di: Ye, Jiacheng, et al.
Pubblicazione: (2024)

Latent Chain-of-Thought? Decoding the Depth-Recurrent Transformer
di: Lu, Wenquan, et al.
Pubblicazione: (2025)

Demystifying Chains, Trees, and Graphs of Thoughts
di: Besta, Maciej, et al.
Pubblicazione: (2024)

Chain-of-Thought Unfaithfulness as Disguised Accuracy
di: Bentham, Oliver, et al.
Pubblicazione: (2024)

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

FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning
di: Xie, Zhuohan, et al.
Pubblicazione: (2025)

Verifying Chain-of-Thought Reasoning via Its Computational Graph
di: Zhao, Zheng, et al.
Pubblicazione: (2025)

Mechanistic Interpretability as Statistical Estimation: A Variance Analysis
di: Méloux, Maxime, et al.
Pubblicazione: (2025)

Think When You Need: Self-Adaptive Chain-of-Thought Learning
di: Yang, Junjie, et al.
Pubblicazione: (2025)

Fragile Thoughts: How Large Language Models Handle Chain-of-Thought Perturbations
di: Aravindan, Ashwath Vaithinathan, et al.
Pubblicazione: (2026)

Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
di: Arcuschin, Iván, et al.
Pubblicazione: (2025)

Compositional Reasoning with Transformers, RNNs, and Chain of Thought
di: Yehudai, Gilad, et al.
Pubblicazione: (2025)

Scalable Chain of Thoughts via Elastic Reasoning
di: Xu, Yuhui, et al.
Pubblicazione: (2025)

Long Chain-of-Thought Reasoning Across Languages
di: Barua, Josh, et al.
Pubblicazione: (2025)

Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens
di: Zhao, Chengshuai, et al.
Pubblicazione: (2025)

Learning to Rank Chain-of-Thought: Using a Small Model
di: Jiang, Eric Hanchen, et al.
Pubblicazione: (2025)

Soft Tokens, Hard Truths
di: Butt, Natasha, et al.
Pubblicazione: (2025)