Image de couverture de livre

Do LLMs Really Need 10+ Thoughts for "Find the Time 1000 Days Later"? Towards Structural Understanding of LLM Overthinking

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Xinliang Frederick, Mohananey, Anhad, Chronopoulou, Alexandra, Papalampidi, Pinelopi, Gupta, Somit, Munkhdalai, Tsendsuren, Wang, Lu, Upadhyay, Shyam
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Finding the Right Moment: Human-Assisted Trailer Creation via Task Composition
par: Papalampidi, Pinelopi, et autres
Publié: (2021)

What Matters for Model Merging at Scale?
par: Yadav, Prateek, et autres
Publié: (2024)

Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation
par: Krishna, Satyapriya, et autres
Publié: (2024)

Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
par: Munkhdalai, Tsendsuren, et autres
Publié: (2024)

Multi-Turn Puzzles: Evaluating Interactive Reasoning and Strategic Dialogue in LLMs
par: Badola, Kartikeya, et autres
Publié: (2025)

Memory Consolidation Enables Long-Context Video Understanding
par: Balažević, Ivana, et autres
Publié: (2024)

Hierarchical Recurrent Adapters for Efficient Multi-Task Adaptation of Large Speech Models
par: Munkhdalai, Tsendsuren, et autres
Publié: (2024)

TempCompass: Do Video LLMs Really Understand Videos?
par: Liu, Yuanxin, et autres
Publié: (2024)

Do We Really Even Need Data?
par: Hoffman, Kentaro, et autres
Publié: (2024)

PRIME: Large Language Model Personalization with Cognitive Dual-Memory and Personalized Thought Process
par: Zhang, Xinliang Frederick, et autres
Publié: (2025)

Narrative-of-Thought: Improving Temporal Reasoning of Large Language Models via Recounted Narratives
par: Zhang, Xinliang Frederick, et autres
Publié: (2024)

Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
par: Chen, Xingyu, et autres
Publié: (2024)

Do MLLMs Really Understand the Charts?
par: Zhang, Xiao, et autres
Publié: (2025)

What Do CD-ROM Users Really Need?
par: Clever, Elaine Cox, et autres
Publié: (1991)

Do You Really Need a Beer to Collaborate?
par: Britta S. von Ungern‐Sternberg, et autres
Publié: (2025)

Dynamic Classifier-Free Diffusion Guidance via Online Feedback
par: Papalampidi, Pinelopi, et autres
Publié: (2025)

The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis
par: Wei, Zihao, et autres
Publié: (2025)

Revisiting Overthinking in Long Chain-of-Thought from the Perspective of Self-Doubt
par: Peng, Keqin, et autres
Publié: (2025)

Do LLMs Overthink Basic Math Reasoning? Benchmarking the Accuracy-Efficiency Tradeoff in Language Models
par: Srivastava, Gaurav, et autres
Publié: (2025)

MambaOut: Do We Really Need Mamba for Vision?
par: Yu, Weihao, et autres
Publié: (2024)

Do LGBTQIA + Disabled Students Really Need Safe Spaces?
par: Konstantinos Drosos, et autres
Publié: (2026)

Do Large Language Models (Really) Need Statistical Foundations?
par: Su, Weijie
Publié: (2025)

Do GPUs Really Need New Tabular File Formats?
par: Luo, Jigao, et autres
Publié: (2026)

What Do They Really Need To Know? Adventures in Curriculum Writing.
par: Pritzl, Amy
Publié: (2000)

Failed schemes of relatedness in domestic work: Filipina domestic workers in Greece
par: Pinelopi Topali
Publié: (2024)

Do We Really Need a Large Number of Visual Prompts?
par: Kim, Youngeun, et autres
Publié: (2023)

We Need to Do This
par: Zabjek, Alexandra
Publié: (2023)

Large Language Models for Code Analysis: Do LLMs Really Do Their Job?
par: Fang, Chongzhou, et autres
Publié: (2023)

Do Vision-Language Models Really Understand Visual Language?
par: Hou, Yifan, et autres
Publié: (2024)

Your Models Have Thought Enough: Training Large Reasoning Models to Stop Overthinking
par: Han, Jinyi, et autres
Publié: (2025)

BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Models
par: Liu, Shuaitong, et autres
Publié: (2025)

Do LLMs Really Adapt to Domains? An Ontology Learning Perspective
par: Mai, Huu Tan, et autres
Publié: (2024)

Do LLMs Really Think Step-by-step In Implicit Reasoning?
par: Yu, Yijiong
Publié: (2024)

The Biology of the First 1,000 Days
Publié: (2023)

Do We Really Need to Design New Byzantine-robust Aggregation Rules?
par: Fang, Minghong, et autres
Publié: (2025)

Do We Really Need to Drop Items with Missing Modalities in Multimodal Recommendation?
par: Malitesta, Daniele, et autres
Publié: (2024)

Pedagogy for Practical Library Instruction: What Do We "Really" Need to Know?
par: Montgomery, Molly
Publié: (2015)

Do We Really Need Cultural Diversity in the Library and Information Science Curriculum?
par: Welburn, William C.
Publié: (1994)

Avoiding Overthinking and Underthinking: Curriculum-Aware Budget Scheduling for LLMs
par: Rahman, Amirul, et autres
Publié: (2026)

Do MLLMs Really Understand Space? A Mathematical Reasoning Evaluation
par: Lu, Shuo, et autres
Publié: (2026)