Papers with Code 아카이브
Mathematical Reasoning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 7
- 평가표
- 11
- 보존된 평가 기록
- 41
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/rioyokotalab/swallow-code-math
공식 코드Rewriting Pre-Training Data Boosts LLM Performance in Math and Code
https://github.com/rlhflow/gvm
공식 코드https://github.com/rlhflow/self-rewarding-reasoning-llm
공식 코드https://github.com/rookie-joe/pda
공식 코드https://github.com/rosieyzh/openrlhf-pretrain
공식 코드Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining
https://github.com/rsinghlab/shape-blind
공식 코드Forgotten Polygons: Multimodal Large Language Models are Shape-Blind
https://github.com/ruc-dwbi-ml/research
공식 코드Semi-Supervised Learning via Weight-aware Distillation under Class Distribution Mismatch
https://github.com/rucaibox/cir
공식 코드https://github.com/rucaibox/jiuzhang3.0
공식 코드JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
https://github.com/rucaibox/mmath
공식 코드https://github.com/rucaibox/olymmath
공식 코드Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models
https://github.com/ruixin31/spurious_rewards
공식 코드https://github.com/safeailab/eagle
공식 코드EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
https://github.com/sail-sg/anytimereasoner
공식 코드Optimizing Anytime Reasoning via Budget Relative Policy Optimization
https://github.com/sail-sg/verifree
공식 코드https://github.com/salesforceairesearch/taco
공식 코드TACO: Learning Multi-modal Action Models with Synthetic Chains-of-Thought-and-Action
https://github.com/sallytan13/teaching-inspired-prompting
공식 코드https://github.com/sarahmart/hardmath
공식 코드HARDMath: A Benchmark Dataset for Challenging Problems in Applied Mathematics
https://github.com/scuuy/mathq-verify
공식 코드https://github.com/seamoke/Human-Think-Language
공식 코드How Do Humans Write Code? Large Models Do It the Same Way Too
https://github.com/sensellm/reflectioncoder
공식 코드ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation
https://github.com/sfeng-m/real4mwp
공식 코드Recall and Learn: A Memory-augmented Solver for Math Word Problems
https://github.com/sharif-ml-lab/CER
공식 코드https://github.com/shimao-zhang/process-self-rewarding
공식 코드https://github.com/shinandrew/youronmath
공식 코드https://github.com/sihengli99/repo
공식 코드https://github.com/simplescaling/s1
공식 코드https://github.com/sixuli/fedcbo
공식 코드https://github.com/smarter-vlm/smarter
공식 코드https://github.com/snfrieder/ghosts
공식 코드https://github.com/songmzhang/dskdv2
공식 코드A Dual-Space Framework for General Knowledge Distillation of Large Language Models
https://github.com/sophistz/question-aware-deductive-mwp
공식 코드https://github.com/sphere-ai-lab/formalmath-bench
공식 코드FormalMATH: Benchmarking Formal Mathematical Reasoning of Large Language Models
https://github.com/stardewxxx/o1-pruner
공식 코드O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning
https://github.com/starscream-11813/variational-mathematical-reasoning
공식 코드Math Word Problem Solving by Generating Linguistic Variants of Problem Statements
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.