https://github.com/flowritecom/flow-merge
Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
Papers with Code 아카이브
GSM8K
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 2
- 보존된 평가 기록
- 3
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/gen-verse/reasonflux
SuperCorrect: Supervising and Correcting Language Models with Error-Driven Insights
https://github.com/guanziju/Open_CODI
CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation
https://github.com/guidance-ai/guidance
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
https://github.com/hkust-nlp/b-star
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
https://github.com/huang-research-group/Matrix-SSL
https://github.com/hughbzhang/o1_inference_scaling_laws
Self-Consistency Improves Chain of Thought Reasoning in Language Models
https://github.com/imnearth/coat
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
https://github.com/infini-ai-lab/sirius
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
https://github.com/jerrywu-code/susgen
Common 7B Language Models Already Possess Strong Math Capabilities
https://github.com/jl-er/rwkv-peft
Balancing LoRA Performance and Efficiency with Simple Shard Sharing
https://github.com/just-curieous/curie
Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
https://github.com/kagnlp/Xolver
Xolver: Multi-Agent Reasoning with Holistic Experience Learning Just Like an Olympiad Team
https://github.com/kvadityasrivatsa/analyzing-llms-for-mwps
https://github.com/laihuiyuan/mcot
https://github.com/lastmile-ai/aiconfig
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
https://github.com/lastmile-ai/aiconfig/tree/main/cookbooks/Multi-LLM-Consistency
Self-Consistency Improves Chain of Thought Reasoning in Language Models
https://github.com/lm-sys/routellm
https://github.com/lupantech/chameleon-llm
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
https://github.com/mbzuai-clear/ioe-prompting
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
https://github.com/michelemancusi/LQVAE-separation
https://github.com/microsoft/Multilingual-Evaluation-of-Generative-AI-MEGA
https://github.com/microsoft/guidance
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
https://github.com/mrlab-ai/NL2Plan
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
https://github.com/nicolay-r/reasoning-for-sentiment-analysis-framework
https://github.com/nicolay-r/thor-ecac
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
https://github.com/nlpxucan/wizardlm
WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct
https://github.com/opendatalab/charm
https://github.com/opendrivelab/drivelm
Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Language Models
https://github.com/project-numina/aimo-progress-prize
https://github.com/qingyangzhang/empo
https://github.com/qwenlm/qwen1.5
https://github.com/rlqja1107/torch-LLM4SGG
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
https://github.com/scofield7419/thor-isa
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
https://github.com/shahriargolchin/time-travel-in-llms
Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language Models
https://github.com/skytliang/multi-agents-debate
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.