SOTAVerified

Math

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 651–675 of 1596 papers

TitleStatusHype
Evaluating Robustness of Reward Models for Mathematical Reasoning—0
Not All LLM Reasoners Are Created Equal—0
Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models—0
Mind Scramble: Unveiling Large Language Model Psychology Via TypoglycemiaCode0
VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit AssignmentCode2
Automated Knowledge Concept Annotation and Question Representation Learning for Knowledge TracingCode0
OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction DataCode4
LASeR: Learning to Adaptively Select Reward Models with Multi-Armed BanditsCode1
Scheherazade: Evaluating Chain-of-Thought Math Reasoning in LLMs with Chain-of-ProblemsCode0
Instance-adaptive Zero-shot Chain-of-Thought Prompting—0
The Perfect Blend: Redefining RLHF with Mixture of Judges—0
INC-Math: Integrating Natural Language and Code for Enhanced Mathematical Reasoning in Large Language Models—0
Revisiting the Superficial Alignment Hypothesis—0
On the Inductive Bias of Stacking Towards Improving Reasoning—0
BEATS: Optimizing LLM Mathematical Capabilities with BackVerify and Adaptive Disambiguate based Efficient Tree SearchCode1
Learning to Love Edge Cases in Formative Math Assessment: Using the AMMORE Dataset and Chain-of-Thought Prompting to Improve Grading Accuracy—0
Democratizing Signal Processing and Machine Learning: Math Learning Equity for Elementary and Middle School Students—0
PMSS: Pretrained Matrices Skeleton Selection for LLM Fine-tuning—0
LLaMa-SciQ: An Educational Chatbot for Answering Science MCQ—0
Models Can and Should Embrace the Communicative Nature of Human-Generated Math—0
Archon: An Architecture Search Framework for Inference-Time TechniquesCode2
PTD-SQL: Partitioning and Targeted Drilling with LLMs in Text-to-SQLCode0
Beyond Accuracy Optimization: Computer Vision Losses for Large Language Model Fine-TuningCode0
ControlMath: Controllable Data Generation Promotes Math Generalist Models—0
Balancing LoRA Performance and Efficiency with Simple Shard SharingCode2
Show:102550
← PrevPage 27 of 64Next →

No leaderboard results yet.