REVIEW 8 cited by
A Survey of Deep Learning for Mathematical Reasoning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Mathematical reasoning is a fundamental aspect of human intelligence and is applicable in various fields, including science, engineering, finance, and everyday life. The development of artificial intelligence (AI) systems capable of solving math problems and proving theorems has garnered significant interest in the fields of machine learning and natural language processing. For example, mathematics serves as a testbed for aspects of reasoning that are challenging for powerful deep learning models, driving new algorithmic and modeling advances. On the other hand, recent advances in large-scale neural language models have opened up new benchmarks and opportunities to use deep learning for mathematical reasoning. In this survey paper, we review the key tasks, datasets, and methods at the intersection of mathematical reasoning and deep learning over the past decade. We also evaluate existing benchmarks and methods, and discuss future research directions in this domain.
Forward citations
Cited by 8 Pith papers
-
Augmenting speech transcripts of VR recordings with gaze, pointing, and visual context for multimodal coreference resolution
Augmenting VR speech transcripts with gaze and pointing cues improved GPT-4 coreference resolution from 40.6% to 67.1% accuracy.
-
Arrows of Math Reasoning Data Synthesis for Large Language Models: Diversity, Complexity and Correctness
A program-assisted pipeline generates 12.3 million math problem-solution pairs with execution-based verification, and fine-tuning on a 50k sample improves model scores on GSM8K, MATH, Minerva, and SVAMP.
-
STORM-BORN: A Challenging Mathematical Derivations Dataset Curated via a Human-in-the-Loop Multi-Agent Framework
A 100-problem benchmark of difficult math derivations from academic papers, where the best LLMs score below 5% and small-scale fine-tuning yields modest gains on standard math benchmarks.
-
Understanding Financial Reasoning in AI: A Multimodal Benchmark and Error Learning Approach
A new multimodal financial reasoning benchmark and a retrieval-based error feedback prompting method that improves model accuracy, with the improvement partly confounded by information leakage.
-
IMAGINE-E: Image Generation Intelligence Evaluation of State-of-the-art Text-to-Image Models
A new evaluation suite finds that CLIPScore, HPSv2, and Aesthetic Score misjudge challenging text-to-image outputs, while GPT-4o and human ratings favor FLUX.1 and Ideogram2.0.
-
System-2 Mathematical Reasoning via Enriched Instruction Tuning
Enriched Instruction Tuning (EIT) uses GPT-4 to add planning and missing reasoning steps to human-annotated math solutions, and fine-tuning LLaMA-2 on this data yields 84.1% on GSM8K and 32.5% on MATH.
-
Neuro-Photonix: Enabling Near-Sensor Neuro-Symbolic AI Computing on Silicon Photonics Substrate
A near-sensor silicon-photonics accelerator runs quantized neural networks and hyperdimensional symbolic encoding in the optical domain, claiming 30 GOPS/W and up to 20.8x power reduction over ASIC accelerators while ...
-
Enhancing the Reasoning Capabilities of Small Language Models via Solution Guidance Fine-Tuning
SGFT fine-tunes a small model to produce calculation-free solution plans and uses a second model to answer from them, outperforming CoT fine-tuning with roughly 3% of the training data.
Discussion (0). Continue with ORCID to comment.