$Imagen de Portada$

Can LLMs Reason Abstractly Over Math Word Problems Without CoT? Disentangling Abstract Formulation From Arithmetic Computation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Cheng, Ziling, Cao, Meng, Pishdad, Leila, Cao, Yanshuai, Cheung, Jackie Chi Kit
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMs
por: Cheng, Ziling, et al.
Publicado: (2025)

PreSumm: Predicting Summarization Performance Without Summarizing
por: Koniaev, Steven, et al.
Publicado: (2025)

Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations
por: Yu, Lei, et al.
Publicado: (2024)

Thinking Without Words: Efficient Latent Reasoning with Abstract Chain-of-Thought
por: Ramji, Keshav, et al.
Publicado: (2026)

Can LLMs Solve longer Math Word Problems Better?
por: Xu, Xin, et al.
Publicado: (2024)

Solving the Challenge Set without Solving the Task: On Winograd Schemas as a Test of Pronominal Coreference Resolution
por: Porada, Ian, et al.
Publicado: (2024)

Towards Learning to Reason: Comparing LLMs with Neuro-Symbolic on Arithmetic Relations in Abstract Reasoning
por: Hersche, Michael, et al.
Publicado: (2024)

CoT-Pose: Chain-of-Thought Reasoning for 3D Pose Generation from Abstract Prompts
por: Cha, Junuk, et al.
Publicado: (2025)

Neither Valid nor Reliable? Investigating the Use of LLMs as Judges
por: Chehbouni, Khaoula, et al.
Publicado: (2025)

Ensemble Distillation for Unsupervised Constituency Parsing
por: Shayegh, Behzad, et al.
Publicado: (2023)

Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs
por: Li, Jianan, et al.
Publicado: (2026)

CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models
por: Qian, Cheng, et al.
Publicado: (2023)

The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation
por: Lan, Yifan, et al.
Publicado: (2026)

LLMs Faithfully and Iteratively Compute Answers During CoT: A Systematic Analysis With Multi-step Arithmetics
por: Kudo, Keito, et al.
Publicado: (2024)

A Controlled Reevaluation of Coreference Resolution Models
por: Porada, Ian, et al.
Publicado: (2024)

Does This Summary Answer My Question? Modeling Query-Focused Summary Readers with Rational Speech Acts
por: Piano, Cesare Spinoso-Di, et al.
Publicado: (2024)

Focus on Your Question! Interpreting and Mitigating Toxic CoT Problems in Commonsense Reasoning
por: Li, Jiachun, et al.
Publicado: (2024)

What Makes Math Word Problems Challenging for LLMs?
por: Srivatsa, KV Aditya, et al.
Publicado: (2024)

Self-consistent Reasoning For Solving Math Word Problems
por: Xiong, Jing, et al.
Publicado: (2022)

Long or short CoT? Investigating Instance-level Switch of Large Reasoning Models
por: Zhang, Ruiqi, et al.
Publicado: (2025)

Structured Reasoning with Tree-of-Thoughts for Bengali Math Word Problems
por: Mahmood, Aurprita, et al.
Publicado: (2025)

CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMs
por: Li, Li, et al.
Publicado: (2025)

Linear Half-Space Problems in Kinetic Theory: Abstract Formulation and Regime Transitions
por: Bernhoff, Niclas
Publicado: (2022)

Augmenting Math Word Problems via Iterative Question Composing
por: Liu, Haoxiong, et al.
Publicado: (2024)

Connecting the Dots: Evaluating Abstract Reasoning Capabilities of LLMs Using the New York Times Connections Word Game
por: Samadarshi, Prisha, et al.
Publicado: (2024)

A Unified View of Abstract Visual Reasoning Problems
por: Małkiński, Mikołaj, et al.
Publicado: (2024)

Understanding Formal Reasoning Failures in LLMs as Abstract Interpreters
por: Mitchell, Jacqueline L., et al.
Publicado: (2025)

Improving the Calibration of Confidence Scores in Text Generation Using the Output Distribution's Characteristics
por: Flores, Lorenzo Jaime Yu, et al.
Publicado: (2025)

$\texttt{COSMIC}$: Mutual Information for Task-Agnostic Summarization Evaluation
por: Darrin, Maxime, et al.
Publicado: (2024)

On the Morse Index with Constraints I: An Abstract Formulation
por: Tran, Hung, et al.
Publicado: (2020)

How Likely Do LLMs with CoT Mimic Human Reasoning?
por: Bao, Guangsheng, et al.
Publicado: (2024)

Knowledge-Augmented Long-CoT Generation for Complex Biomolecular Reasoning
por: Lyu, Tianwen, et al.
Publicado: (2025)

Adversarial Math Word Problem Generation
por: Xie, Roy, et al.
Publicado: (2024)

Can Vision Language Models Be Adaptive in Mathematics Education? A Learner Model-based Rubric Study
por: Gao, Jie, et al.
Publicado: (2026)

Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual Reasoning
por: Nai, Ruiqian, et al.
Publicado: (2024)

Solving Math Word Problems via Cooperative Reasoning induced Language Models
por: Zhu, Xinyu, et al.
Publicado: (2022)

Logic Contrastive Reasoning with Lightweight Large Language Model for Math Word Problems
por: Kai, Ding, et al.
Publicado: (2024)

Abstract Formulation of Mean-Field Models and Propagation of Chaos
por: Lim, Tau Shean, et al.
Publicado: (2025)

Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics
por: Nikankin, Yaniv, et al.
Publicado: (2024)

CoT-RVS: Zero-Shot Chain-of-Thought Reasoning Segmentation for Videos
por: Kao, Shiu-hong, et al.
Publicado: (2025)