Cover Image

Why LLMs Cannot Think and How to Fix It

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jahrens, Marius, Martinetz, Thomas
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Semantic Anchors in In-Context Learning: Why Small LLMs Cannot Flip Their Labels
by: Kumar, Anantha Padmanaban Krishna
Published: (2025)

Why Fine-Tuning Encourages Hallucinations and How to Fix It
by: Kaplan, Guy, et al.
Published: (2026)

Rethinking generalization of classifiers in separable classes scenarios and over-parameterized regimes
by: Martinetz, Julius, et al.
Published: (2024)

The Illusion of Superposition? A Principled Analysis of Latent Thinking in Language Models
by: Rizvi-Martel, Michael, et al.
Published: (2026)

SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It)
by: Meeus, Matthieu, et al.
Published: (2024)

OptimalThinkingBench: Evaluating Over and Underthinking in LLMs
by: Aggarwal, Pranjal, et al.
Published: (2025)

Asynchronous Reasoning: Training-Free Interactive Thinking LLMs
by: Yakushev, George, et al.
Published: (2025)

Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think?
by: Wang, Shouren, et al.
Published: (2025)

Nearest-Neighbor Density Estimation for Dependency Suppression
by: Anderson, Kathleen, et al.
Published: (2026)

Do LLMs Understand Romanian Driving Laws? A Study on Multimodal and Fine-Tuned Question Answering
by: Barbu, Eduard, et al.
Published: (2025)

Forecasting Downstream Performance of LLMs With Proxy Metrics
by: Patel, Arkil, et al.
Published: (2026)

CooperBench: Why Coding Agents Cannot be Your Teammates Yet
by: Khatua, Arpandeep, et al.
Published: (2026)

Unknown Unknowns: Why Hidden Intentions in LLMs Evade Detection
by: Srivastav, Devansh, et al.
Published: (2026)

Can We Count on LLMs? The Fixed-Effect Fallacy and Claims of GPT-4 Capabilities
by: Ball, Thomas, et al.
Published: (2024)

The Right Answer, the Wrong Direction: Why Transformers Fail at Counting and How to Fix It
by: Garcia, Gabriel
Published: (2026)

Do Multilingual LLMs Think In English?
by: Schut, Lisa, et al.
Published: (2025)

Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
by: Kim, Jeonghye, et al.
Published: (2026)

Rethinking Thinking Tokens: Understanding Why They Underperform in Practice
by: Vennam, Sreeram, et al.
Published: (2024)

Perplexity Cannot Always Tell Right from Wrong
by: Veličković, Petar, et al.
Published: (2026)

Reverse Thinking Makes LLMs Stronger Reasoners
by: Chen, Justin Chih-Yao, et al.
Published: (2024)

Measuring What LLMs Think They Do: SHAP Faithfulness and Deployability on Financial Tabular Classification
by: AlMarri, Saeed, et al.
Published: (2025)

Non-Halting Queries: Exploiting Fixed Points in LLMs
by: Hammouri, Ghaith, et al.
Published: (2024)

Multimodal Language Models Cannot Spot Spatial Inconsistencies
by: Khangaonkar, Om, et al.
Published: (2026)

MillStone: How Open-Minded Are LLMs?
by: Triedman, Harold, et al.
Published: (2025)

How Does Quantization Affect Multilingual LLMs?
by: Marchisio, Kelly, et al.
Published: (2024)

GRILE: A Benchmark for Grammar Reasoning and Explanation in Romanian LLMs
by: Dumitran, Adrian-Marius, et al.
Published: (2025)

On the Emergence of Thinking in LLMs I: Searching for the Right Intuition
by: Ye, Guanghao, et al.
Published: (2025)

Why Are Web AI Agents More Vulnerable Than Standalone LLMs? A Security Analysis
by: Chiang, Jeffrey Yang Fan, et al.
Published: (2025)

Why is "Chicago" Predictive of Deceptive Reviews? Using LLMs to Discover Language Phenomena from Lexical Cues
by: Qu, Jiaming, et al.
Published: (2025)

Reinforcement Learning for Latent-Space Thinking in LLMs
by: Özeren, Enes, et al.
Published: (2025)

Thinking in Latents: Adaptive Anchor Refinement for Implicit Reasoning in LLMs
by: Sheshanarayana, Disha, et al.
Published: (2026)

RLVR Training of LLMs Does Not Improve Thinking Ability for General QA: Evaluation Method and a Simple Solution
by: Li, Kaiyuan, et al.
Published: (2026)

Uncovering Gaps in How Humans and LLMs Interpret Subjective Language
by: Jones, Erik, et al.
Published: (2025)

Slot Machines: How LLMs Keep Track of Multiple Entities
by: Bogdan, Paul C., et al.
Published: (2026)

Think Before You Lie: How Reasoning Leads to Honesty
by: Yuan, Ann, et al.
Published: (2026)

Understanding How CodeLLMs (Mis)Predict Types with Activation Steering
by: Lucchetti, Francesca, et al.
Published: (2024)

What Makes the Preferred Thinking Direction for LLMs in Multiple-choice Questions?
by: Zhang, Yizhe, et al.
Published: (2025)

When Two LLMs Debate, Both Think They'll Win
by: Prasad, Pradyumna Shyama, et al.
Published: (2025)

False Fixed Points: Kantian Feedback, Stable Miscalibration, and Representational Compression in LLMs
by: Okutomi, Akira
Published: (2025)

SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding
by: Li, Sihang, et al.
Published: (2024)