Image de couverture de livre

Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhao, Jiachen, Sun, Yiyou, Shi, Weiyan, Song, Dawn
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Divide-Fuse-Conquer: Eliciting "Aha Moments" in Multi-Scenario Games
par: Zhang, Xiaoqing, et autres
Publié: (2025)

Climbing the Ladder of Reasoning: What LLMs Can-and Still Can't-Solve after SFT?
par: Sun, Yiyou, et autres
Publié: (2025)

Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents
par: Li, Xu, et autres
Publié: (2026)

Aha Moment Revisited: Are VLMs Truly Capable of Self Verification in Inference-time Scaling?
par: Wu, Mingyuan, et autres
Publié: (2025)

Deep Thinking by Markov Chain of Continuous Thoughts
par: Liu, Jiayu, et autres
Publié: (2025)

How and Why LLMs Generalize: A Fine-Grained Analysis of LLM Reasoning from Cognitive Behaviors to Low-Level Patterns
par: Bai, Haoyue, et autres
Publié: (2025)

Temporal Chain of Thought: Long-Video Understanding by Thinking in Frames
par: Arnab, Anurag, et autres
Publié: (2025)

RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?
par: Sun, Yiyou, et autres
Publié: (2025)

When and How Does In-Distribution Label Help Out-of-Distribution Detection?
par: Du, Xuefeng, et autres
Publié: (2024)

R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model
par: Zhou, Hengguang, et autres
Publié: (2025)

Let Me Think! A Long Chain-of-Thought Can Be Worth Exponentially Many Short Ones
par: Mirtaheri, Parsa, et autres
Publié: (2025)

Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization
par: Zaman, Kerem, et autres
Publié: (2025)

SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning
par: Zhou, Kaiwen, et autres
Publié: (2025)

Output Supervision Can Obfuscate the Chain of Thought
par: Drori, Jacob, et autres
Publié: (2025)

ExpThink: Experience-Guided Reinforcement Learning for Adaptive Chain-of-Thought Compression
par: Bian, Tingcheng, et autres
Publié: (2026)

Where's the liability in the Generative Era? Recovery-based Black-Box Detection of AI-Generated Content
par: Bai, Haoyue, et autres
Publié: (2025)

Can Small Training Runs Reliably Guide Data Curation? Rethinking Proxy-Model Practice
par: Wang, Jiachen T., et autres
Publié: (2025)

Think When You Need: Self-Adaptive Chain-of-Thought Learning
par: Yang, Junjie, et autres
Publié: (2025)

Can Machines Learn the True Probabilities?
par: Kim, Jinsook
Publié: (2024)

Data Shapley in One Training Run
par: Wang, Jiachen T., et autres
Publié: (2024)

Transformers Provably Learn to Internalize Chain-of-Thought
par: Huang, Yixiao, et autres
Publié: (2026)

Dynamic Chain-of-Thought: Towards Adaptive Deep Reasoning
par: Wang, Libo
Publié: (2025)

Capturing the Temporal Dependence of Training Data Influence
par: Wang, Jiachen T., et autres
Publié: (2024)

Think Consistently, Reason Efficiently: Energy-Based Calibration for Implicit Chain-of-Thought
par: Chen, Zhikang, et autres
Publié: (2025)

SALT: Steering Activations towards Leakage-free Thinking in Chain of Thought
par: Batra, Shourya, et autres
Publié: (2025)

DFA-RAG: Conversational Semantic Router for Large Language Model with Definite Finite Automaton
par: Sun, Yiyou, et autres
Publié: (2024)

Revisiting Chain-of-Thought Prompting: Zero-shot Can Be Stronger than Few-shot
par: Cheng, Xiang, et autres
Publié: (2025)

Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models
par: Ye, Jiacheng, et autres
Publié: (2024)

Thought Cloning: Learning to Think while Acting by Imitating Human Thinking
par: Hu, Shengran, et autres
Publié: (2023)

Bridging Formal Language with Chain-of-Thought Reasoning to Geometry Problem Solving
par: Yang, Tianyun, et autres
Publié: (2025)

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression
par: Tang, Yuntian, et autres
Publié: (2026)

Quantifying True Robustness: Synonymity-Weighted Similarity for Trustworthy XAI Evaluation
par: Burger, Christopher
Publié: (2025)

Modern Hopfield Networks Require Chain-of-Thought to Solve $\mathsf{NC}^1$-Hard Problems
par: Cao, Yang, et autres
Publié: (2024)

DarkMind: Latent Chain-of-Thought Backdoor in Customized LLMs
par: Guo, Zhen, et autres
Publié: (2025)

Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens
par: Qin, Yiming, et autres
Publié: (2025)

On Learning Verifiers and Implications to Chain-of-Thought Reasoning
par: Balcan, Maria-Florina, et autres
Publié: (2025)

True Self-Avoiding Walk for Accelerating Markov-Chain Monte Carlo Integration
par: Qinghua, et autres
Publié: (2026)

Can DeepFake Speech be Reliably Detected?
par: Liu, Hongbin, et autres
Publié: (2024)

AhaRobot: A Low-Cost Open-Source Bimanual Mobile Manipulator for Embodied AI
par: Cui, Haiqin, et autres
Publié: (2025)

Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs
par: Cai, Will, et autres
Publié: (2025)