Skip to content
conftrace_

arithmetic reasoning

45 papers

Papers

Language Models Learn Universal Representations of Numbers and Here’s Why You Should Care ACL 2026 Punctuation-Steered Representation Fine-Tuning ACL 2026 Reflect, Rewrite, Repeat: How Simple Arithmetic Enables Advanced Reasoning in Small Language Models EACL 2026 Arithmetic Without Algorithms: Language Models Solve Math with a Bag of Heuristics ICLR 2025 DARR: A Dual-Branch Arithmetic Regression Reasoning Framework for Solving Machine Number Reasoning AAAI 2025 Fine-Grained Manipulation of Arithmetic Neurons EMNLP 2025 How do autoregressive transformers solve full addition? EMNLP 2025 How Numerical Precision Affects Arithmetical Reasoning Capabilities of LLMs ACL 2025 Language Imbalance Driven Rewarding for Multilingual Self-improving ICLR 2025 Modular Arithmetic: Language Models Solve Math Digit by Digit IJCNLP 2025 PricingLogic: Evaluating LLMs Reasoning on Complex Tourism Pricing Tasks EMNLP 2025 Principled Understanding of Generalization for Generative Transformer Models in Arithmetic Reasoning Tasks ACL 2025 Probing for Arithmetic Errors in Language Models EMNLP 2025 Recitation over Reasoning: How Cutting-Edge Language Models Can Fail on Elementary School-Level Reasoning Problems? IJCNLP 2025 Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning ICLR 2025 SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training ICML 2025 Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models COLING 2025 The Lookahead Limitation: Why Multi-Operand Addition is Hard for LLMs EMNLP 2025 The Validation Gap: A Mechanistic Analysis of How Language Models Compute Arithmetic but Fail to Validate It EMNLP 2025 When natural language is not enough: The limits of in-context learning demonstrations in multilingual reasoning NAACL 2025 An Investigation of Neuron Activation as a Unified Lens to Explain Chain-of-Thought Eliciting Arithmetic Reasoning of LLMs ACL 2024 Are Human-generated Demonstrations Necessary for In-context Learning? ICLR 2024 Arithmetic Reasoning with LLM: Prolog Generation & Permutation NAACL 2024 Frugal LMs Trained to Invoke Symbolic Solvers Achieve Parameter-Efficient Arithmetic Reasoning AAAI 2024 Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis EMNLP 2024