Cover Image

Syntactic Blind Spots: How Misalignment Leads to LLMs Mathematical Errors

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Williamson, Dane, Ji, Yangfeng, Dwyer, Matthew
Format:	Preprint
Published:	2025
Subjects:	Computation and Language I.2.7; I.2.0
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LLMs and the Human Condition
by: Wallis, Peter
Published: (2024)

ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration
by: Deng, Minghang, et al.
Published: (2025)

TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation
by: Du, Bangde, et al.
Published: (2025)

ChemPro: A Progressive Chemistry Benchmark for Large Language Models
by: Baranwal, Aaditya, et al.
Published: (2026)

The Invisible Coalition Partner: How LLMs Vote When Democracy Gets Concrete
by: Barmettler, Joel
Published: (2026)

QuickSilver -- Speeding up LLM Inference through Dynamic Token Halting, KV Skipping, Contextual Token Fusion, and Adaptive Matryoshka Quantization
by: Khanna, Danush, et al.
Published: (2025)

Quo Vadis ChatGPT? From Large Language Models to Large Knowledge Models
by: Venkatasubramanian, Venkat, et al.
Published: (2024)

OpenAI Cribbed Our Tax Example, But Can GPT-4 Really Do Tax?
by: Blair-Stanek, Andrew, et al.
Published: (2023)

MATH-PT: A Math Reasoning Benchmark for European and Brazilian Portuguese
by: Teixeira, Tiago, et al.
Published: (2026)

Automated Circuit Interpretation via Probe Prompting
by: Birardi, Giuseppe
Published: (2025)

CopySpec: Accelerating LLMs with Speculative Copy-and-Paste Without Compromising Quality
by: Dumitru, Razvan-Gabriel, et al.
Published: (2025)

Layer-Wise Quantization: A Pragmatic and Effective Method for Quantizing LLMs Beyond Integer Bit-Levels
by: Dumitru, Razvan-Gabriel, et al.
Published: (2024)

Aspect-Based Sentiment Analysis for Future Tourism Experiences: A BERT-MoE Framework for Persian User Reviews
by: Taskooh, Hamidreza Kazemi, et al.
Published: (2026)

A Survey of Text and Speech Resources for Hausa and Fongbe: Availability, Quality, and Gaps for NLP Development
by: Adjovi, Mahounan Pericles, et al.
Published: (2026)

Pareto-Optimized Open-Source LLMs for Healthcare via Context Retrieval
by: Bayarri-Planas, Jordi, et al.
Published: (2024)

The Company You Keep: How LLMs Respond to Dark Triad Traits
by: Lu, Zeyi, et al.
Published: (2026)

ConciseRL: Conciseness-Guided Reinforcement Learning for Efficient Reasoning Models
by: Dumitru, Razvan-Gabriel, et al.
Published: (2025)

Correcting Gradient-Based Circuit Localization via Interaction-Aware Backpropagation
by: Edin, Joakim, et al.
Published: (2025)

NRR-Core: Non-Resolution Reasoning as a Computational Framework for Contextual Identity and Ambiguity Preservation
by: Saito, Kei
Published: (2025)

Next Token Prediction Is a Dead End for Creativity
by: Olatunji, Ibukun, et al.
Published: (2025)

RWKV-7 "Goose" with Expressive Dynamic State Evolution
by: Peng, Bo, et al.
Published: (2025)

Key-Value Means: Transformers with Expandable Block-Recurrent Compressed Memory
by: Goldstein, Daniel, et al.
Published: (2026)

Chatbots put to the test in math and logic problems: A preliminary comparison and assessment of ChatGPT-3.5, ChatGPT-4, and Google Bard
by: Plevris, Vagelis, et al.
Published: (2023)

Change Is the Only Constant: Dynamic LLM Slicing based on Layer Redundancy
by: Dumitru, Razvan-Gabriel, et al.
Published: (2024)

Prompt Tuned Embedding Classification for Multi-Label Industry Sector Allocation
by: Buchner, Valentin Leonhard, et al.
Published: (2023)

Benchmarking quantized LLaMa-based models on the Brazilian Secondary School Exam
by: Santos, Matheus L. O., et al.
Published: (2023)

ALISON: Fast and Effective Stylometric Authorship Obfuscation
by: Xing, Eric, et al.
Published: (2024)

NRR-Phi: Text-to-State Mapping for Ambiguity Preservation in LLM Inference
by: Saito, Kei
Published: (2026)

BabyReasoningBench: Generating Developmentally-Inspired Reasoning Tasks for Evaluating Baby Language Models
by: Dhole, Kaustubh D.
Published: (2026)

ACCORD: Closing the Commonsense Measurability Gap
by: Roewer-Després, François, et al.
Published: (2024)

Enhancing Transformer RNNs with Multiple Temporal Perspectives
by: Dumitru, Razvan-Gabriel, et al.
Published: (2024)

Reference-Guided Verdict: LLMs-as-Judges in Automatic Evaluation of Free-Form QA
by: Badshah, Sher, et al.
Published: (2024)

Diverse LLMs or Diverse Question Interpretations? That is the Ensembling Question
by: Rosales, Rafael, et al.
Published: (2025)

Incentives or Ontology? A Structural Rebuttal to OpenAI's Hallucination Thesis
by: Ackermann, Richard, et al.
Published: (2025)

Behavioural vs. Representational Systematicity in End-to-End Models: An Opinionated Survey
by: Vegner, Ivan, et al.
Published: (2025)

The Drill-Down and Fabricate Test (DDFT): A Protocol for Measuring Epistemic Robustness in Language Models
by: Baxi, Rahul
Published: (2025)

Perturbation Dose Responses in Recursive LLM Loops: Raw Switching, Stochastic Floors, and Persistent Escape under Append, Replace, and Dialog Updates
by: Kaplanski, Pawel
Published: (2026)

Graph Language Models
by: Plenz, Moritz, et al.
Published: (2024)

Beyond Recall: Behavioral Specification as an Interpretive Layer for AI Personalization
by: Gulaya, Aarik
Published: (2026)

LLMs Aren't Human: A Critical Perspective on LLM Personality
by: Zierahn, Kim, et al.
Published: (2026)