https://github.com/23japhone/halo
공식 코드HALO: Hierarchical Autonomous Logic-Oriented Orchestration for Multi-Agent LLM Systems
Papers with Code 아카이브
Arithmetic Reasoning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 5
- 보존된 평가 기록
- 169
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/CERT-Lab/fed-sb
공식 코드https://github.com/EleutherAI/math-lm
공식 코드https://github.com/RaghavSinghal10/fedex-lora
공식 코드FedEx-LoRA: Exact Aggregation for Federated and Efficient Fine-Tuning of Foundation Models
https://github.com/UKPLab/SciGen
공식 코드Learning to Reason for Text Generation from Scientific Tables
https://github.com/WENGSYX/Self-Verification
공식 코드Large Language Models are Better Reasoners with Self-Verification
https://github.com/Yiwei98/TDG
공식 코드https://github.com/agi-edgerunners/llm-adapters
공식 코드LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models
https://github.com/aiha-lab/tsld
공식 코드Token-Scaled Logit Distillation for Ternary Weight Generative Language Models
https://github.com/alestolfo/lm-arithmetic
공식 코드https://github.com/baohaoliao/road
공식 코드3-in-1: 2D Rotary Adaptation for Efficient Finetuning, Efficient Batching and Composability
https://github.com/chengxuphd/dcr
공식 코드https://github.com/chuanyang-Zheng/Progressive-Hint
공식 코드Progressive-Hint Prompting Improves Reasoning in Large Language Models
https://github.com/cityuhkai/sbora
공식 코드https://github.com/cyzhh/MMOS
공식 코드An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning
https://github.com/dakingrai/neuron-analysis-cot-arithmetic-reasoning
공식 코드https://github.com/damo-nlp-sg/caring
공식 코드Neuro-Symbolic Integration Brings Causal and Reliable Reasoning Proofs
https://github.com/declare-lab/llm-reasoningtest
공식 코드Evaluating LLMs' Mathematical and Coding Competency through Ontology-guided Interventions
https://github.com/deepseek-ai/deepseek-math
공식 코드DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
https://github.com/devichand579/HPT
공식 코드https://github.com/dsgt-arc/checkthat-2025-numerical
공식 코드https://github.com/dvlab-research/step-dpo
공식 코드Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
https://github.com/dxlong2000/chatgpt-as-a-math-questioner
공식 코드ChatGPT as a Math Questioner? Evaluating ChatGPT on Generating Pre-university Math Questions
https://github.com/eleutherai/gpt-neox
공식 코드https://github.com/emma1066/zero-shot-ner-with-chatgpt
공식 코드https://github.com/facebookresearch/dual-system-for-visual-language-reasoning
공식 코드DOMINO: A Dual-System for Multi-step Visual Language Reasoning
https://github.com/facebookresearch/llama
공식 코드https://github.com/finitearth/capo
공식 코드https://github.com/finitearth/promptolution
공식 코드https://github.com/freedomintelligence/ovm
공식 코드OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning
https://github.com/google-research-datasets/gsm-ic
공식 코드Large Language Models Can Be Easily Distracted by Irrelevant Context
https://github.com/google-research/google-research
공식 코드https://github.com/gpgg/art
공식 코드https://github.com/hccngu/dialcot
공식 코드DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models
https://github.com/hkunlp/batch-prompting
공식 코드Batch Prompting: Efficient Inference with Large Language Model APIs
https://github.com/hkust-nlp/dart-math
공식 코드DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.