Mathematical Reasoning

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 701–725 of 805 papers

Title	Date	Tasks	Status	Hype
CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets	Sep 29, 2023	Language ModellingMathematical Reasoning	CodeCode Available	2
ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving	Sep 29, 2023	Arithmetic ReasoningComputational Efficiency	CodeCode Available	3
LPML: LLM-Prompting Markup Language for Mathematical Reasoning	Sep 21, 2023	Mathematical Reasoning	—Unverified	0
Code Soliloquies for Accurate Calculations in Large Language Models	Sep 21, 2023	Language ModellingLarge Language Model	CodeCode Available	0
MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models	Sep 21, 2023	Arithmetic ReasoningGSM8K	CodeCode Available	2
Auto-Regressive Next-Token Predictors are Universal Learners	Sep 13, 2023	Mathematical ReasoningText Generation	CodeCode Available	1
MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning	Sep 11, 2023	MathMathematical Reasoning	CodeCode Available	2
On the meaning of uncertainty for ethical AI: philosophy and practice	Sep 11, 2023	Decision MakingMathematical Reasoning	—Unverified	0
No Train Still Gain. Unleash Mathematical Reasoning of Large Language Models with Monte Carlo Tree Search Guided by Energy Function	Sep 1, 2023	GSM8KMathematical Reasoning	—Unverified	0
When Do Program-of-Thoughts Work for Reasoning?	Aug 29, 2023	Code GenerationMathematical Reasoning	CodeCode Available	2
Semi-Supervised Learning via Weight-aware Distillation under Class Distribution Mismatch	Aug 23, 2023	Mathematical Reasoning	CodeCode Available	1
WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct	Aug 18, 2023	Arithmetic ReasoningGSM8K	CodeCode Available	5
Probabilistic Results on the Architecture of Mathematical Reasoning Aligned by Cognitive Alternation	Aug 17, 2023	Mathematical Reasoning	—Unverified	0
Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation	Aug 16, 2023	Language ModelingLanguage Modelling	CodeCode Available	1
Forward-Backward Reasoning in Large Language Models for Mathematical Verification	Aug 15, 2023	Mathematical Reasoning	—Unverified	0
Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification	Aug 15, 2023	Arithmetic ReasoningMath	CodeCode Available	2
Scaling Relationship on Learning Mathematical Reasoning with Large Language Models	Aug 3, 2023	Arithmetic ReasoningGSM8K	CodeCode Available	2
Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models	Aug 1, 2023	In-Context LearningMath	—Unverified	0
FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios	Jul 25, 2023	Code GenerationFact Checking	CodeCode Available	2
MinT: Boosting Generalization in Mathematical Reasoning via Multi-View Fine-Tuning	Jul 16, 2023	Knowledge DistillationMathematical Reasoning	—Unverified	0
MWPRanker: An Expression Similarity Based Math Word Problem Retriever	Jul 3, 2023	Logical SequenceMath	—Unverified	0
Math Word Problem Solving by Generating Linguistic Variants of Problem Statements	Jun 24, 2023	DecoderIngenuity	CodeCode Available	0
JiuZhang 2.0: A Unified Chinese Pre-trained Language Model for Multi-task Mathematical Problem Solving	Jun 19, 2023	In-Context LearningLanguage Modeling	—Unverified	0
Position: AI Evaluation Should Learn from How We Test Humans	Jun 18, 2023	Mathematical ReasoningPosition	CodeCode Available	0
Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond	Jun 16, 2023	BenchmarkingEvidence Selection	CodeCode Available	1

Show:10 25 50

← PrevPage 29 of 33Next →

All datasets AIME24 FrontierMath Lila (IID)Lila (OOD)PGPS9K AMC23 GeoQA Math500 UniGeo UniGeo (PRV)

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	Xolver	Acc	94.4	—	Unverified
2	DeepSeek-r1	Acc	79.8	—	Unverified
3	Openai-o1	Acc	74.4	—	Unverified
4	Openai-o1-mini	Acc	70	—	Unverified
5	Search-o1	Acc	56.7	—	Unverified
6	s1-32B	Acc	56.7	—	Unverified
7	Openai-o1-preview	Acc	44.6	—	Unverified
8	Qwen2.5-72B-Instruct	Acc	23.3	—	Unverified
9	Claude3.5-Sonnet	Acc	16	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	o3	Accuracy	0.25	—	Unverified
2	Gemini 1.5 Pro (002)	Accuracy	0.02	—	Unverified
3	GPT-4o	Accuracy	0.01	—	Unverified
4	o1-mini	Accuracy	0.01	—	Unverified
5	o1-preview	Accuracy	0.01	—	Unverified
6	Claude 3.5 Sonnet	Accuracy	0.01	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Codex (Few-Shot, 175B)	Accuracy	0.6	—	Unverified
2	Bhāskara-P (Fine-tuned, 2.7B)	Accuracy	0.48	—	Unverified
3	Neo-P (Fine-tuned, 2.7B)	Accuracy	0.39	—	Unverified
4	GPT-3 (Few-Shot, 175B)	Accuracy	0.38	—	Unverified
5	Bhāskara-A (Fine-tuned, 2.7B)	Accuracy	0.25	—	Unverified
6	Neo-A (Fine-tuned, 2.7B)	Accuracy	0.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Codex (Few-Shot, 175B)	Accuracy	0.59	—	Unverified
2	Bhāskara-P (Fine-tuned, 2.7B)	Accuracy	0.45	—	Unverified
3	GPT-3 (Few-Shot, 175B)	Accuracy	0.38	—	Unverified
4	Bhāskara-A (Fine-tuned, 2.7B)	Accuracy	0.27	—	Unverified
5	Neo-P (Fine-tuned, 2.7B)	Accuracy	0.24	—	Unverified
6	Neo-A (Fine-tuned, 2.7B)	Accuracy	0.18	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	GOLD	Completion accuracy	65.8	—	Unverified
2	PGPSNet	Completion accuracy	62.7	—	Unverified
3	GAPS	Completion accuracy	61.2	—	Unverified
4	Inter-GPS	Completion accuracy	59.8	—	Unverified
5	Geoformer	Completion accuracy	35.6	—	Unverified
6	NGS	Completion accuracy	34.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	QWQ-32B-preview	Acc	82.5	—	Unverified
2	Math-Master	Acc	82	—	Unverified
3	Qwen2.5-Math-7B-instruct	Acc	62.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	GOLD	Accuracy (%)	75.2	—	Unverified
2	GAPS	Accuracy (%)	67.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Search-o1	Acc	86.4	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	GOLD	Accuracy (%)	98.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	GAPS	Accuracy (%)	97.5	—	Unverified