Papers with Code 아카이브
Mathematical Question Answering
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 2
- 보존된 평가 기록
- 10
Building systems that automatically answer mathematical questions.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/stanfordbdhg/llama.cpp
https://github.com/synthlabsai/big-math
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
https://github.com/tatsu-lab/stanford_alpaca
https://github.com/teelinsan/camoscio
https://github.com/usyd-fsalab/fp6_llm
https://github.com/uwnlp/geosolver
https://github.com/valdecy/pybibx
https://github.com/vcskaushik/LLMzip
https://github.com/vedantgaur/symbolic-mwp-reasoning
Are NLP Models really able to Solve Simple Math Word Problems?
https://github.com/vicentvankor/sun-shine
https://github.com/xiaoman-zhang/PMC-VQA
https://github.com/xuetianci/pacit
https://github.com/xusenlinzy/api-for-open-llm
https://github.com/xverse-ai/xverse-13b
https://github.com/xvyaward/owq
https://github.com/xzhang97666/alpacare
https://github.com/yangyucheng000/University/tree/main/model-1/qwen2
https://github.com/yangyucheng000/University/tree/main/model-3/qwen2_moe
https://github.com/ymcui/chinese-mixtral
https://github.com/young-geng/easylm
https://github.com/yuanmu97/secure-transformer-inference
https://github.com/yynil/rwkvinside
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
https://github.com/zihanzhaosjtu/librisqa
https://github.com/ziye2chen/LLMs-for-Mathematical-Analysis
https://github.com/zongqianwu/st-cot
https://github.com/zurichnlp/contradecode
https://huggingface.co/datasets/peiyi9979/Math-Shepherd
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.