ErrorRadar is a new benchmark of 2,500 multimodal K-12 math problems for MLLM error step identification and categorization, where GPT-4o trails human experts by ~10%.
Mathbench: Evaluating the theory and application proficiency of llms with a hierarchical mathematics benchmark
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
DPrivBench is a new benchmark for evaluating LLMs on differential privacy reasoning, with results showing good performance on textbook mechanisms but substantial failures on advanced algorithms.
MathFlow decouples perception and inference stages in MLLMs for visual math, with a dedicated perception model delivering gains on the FlowVerse benchmark when paired with existing reasoners.
SemanticQA unifies prior multiword expression datasets into a benchmark that reveals substantial performance variation among language models on semantic reasoning tasks.
A benchmark shows an LLM solves number theory tasks given good hints, and a LightGBM classifier predicts the conductor of a Dirichlet L-function from its first 25 zeros with 93.9% test accuracy.
citing papers explorer
-
ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection
ErrorRadar is a new benchmark of 2,500 multimodal K-12 math problems for MLLM error step identification and categorization, where GPT-4o trails human experts by ~10%.
-
DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy
DPrivBench is a new benchmark for evaluating LLMs on differential privacy reasoning, with results showing good performance on textbook mechanisms but substantial failures on advanced algorithms.
-
MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems
MathFlow decouples perception and inference stages in MLLMs for visual math, with a dedicated perception model delivering gains on the FlowVerse benchmark when paired with existing reasoners.
-
Revisiting a Pain in the Neck: A Semantic Reasoning Benchmark for Language Models
SemanticQA unifies prior multiword expression datasets into a benchmark that reveals substantial performance variation among language models on semantic reasoning tasks.
-
Computational Experiments in Number Theory
A benchmark shows an LLM solves number theory tasks given good hints, and a LightGBM classifier predicts the conductor of a Dirichlet L-function from its first 25 zeros with 93.9% test accuracy.