LinAlg-Bench: A Forensic Benchmark Revealing Structural Failure Modes in LLM Mathematical Reasoning
cs.AI
Submitted: 2026-05-15
Updated: 2026-11-04
Code: https://github.com/shradhautk/LinAlgBench
Terminology
Sources
- Training Verifiers to Solve Math Word Problems
- DeepSeek-V3 Technical Report
- Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
- Large Language Models Cannot Self-Correct Reasoning Yet
- Language Models (Mostly) Know What They Know
- Teaching Arithmetic to Small Transformers
- Let's Verify Step by Step
- The Llama 3 Herd of Models
- Investigating the Limitations of Transformers with Simple Arithmetic Tasks
- Measuring and Narrowing the Compositionality Gap in Language Models
- Qwen2.5 Technical Report
- Qwen3 Technical Report
- How Language Model Hallucinations Can Snowball
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents