https://github.com/yule-BUAA/MergeLLM
공식 코드Extend Model Merging from Fine-Tuned to Pre-Trained Large Language Models via Weight Disentanglement
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/yunqiaoyang/pcpo
공식 코드Probability-Consistent Preference Optimization for Enhanced LLM Reasoning
https://github.com/yutingli0606/vision-matters
공식 코드Vision Matters: Simple Visual Perturbations Can Boost Multimodal Math Reasoning
https://github.com/yuyijiong/parallel-decoding-in-one-sequence
공식 코드Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence
https://github.com/yyding1/scalequest
공식 코드Unleashing Reasoning Capability of LLMs via Scalable Question Synthesis from Scratch
https://github.com/yyht/openrlhf_async_pipline
공식 코드Agent RL Scaling Law: Agent RL with Spontaneous Code Execution for Mathematical Problem Solving
https://github.com/zbox1005/cot-uq
공식 코드CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-Thought
https://github.com/zefan-cai/r-kv
공식 코드R-KV: Redundancy-aware KV Cache Compression for Training-Free Reasoning Models Acceleration
https://github.com/zezeze97/DFE-GPS
공식 코드Diagram Formalization Enhanced Multi-Modal Geometry Problem Solver
https://github.com/zhangir-azerbayev/proofnet
공식 코드ProofNet: Autoformalizing and Formally Proving Undergraduate-Level Mathematics
https://github.com/zhao-zilong/ssc-cot
공식 코드Stepwise Self-Consistent Mathematical Reasoning with Large Language Models
https://github.com/zhaochen0110/cotempqa
공식 코드Living in the Moment: Can Large Language Models Grasp Co-Temporal Reasoning?
https://github.com/zhaoxlpku/promptcot
공식 코드PromptCoT: Synthesizing Olympiad-level Problems for Mathematical Reasoning in Large Language Models
https://github.com/zhenwen-nlp/mathchat
공식 코드MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn Interactions
https://github.com/zhourobotics/llm-mrs-survey
공식 코드https://github.com/ziye2chen/LLMs-for-Mathematical-Analysis
공식 코드https://github.com/zjunlp/Prompt4ReasoningPapers
공식 코드https://github.com/zjunlp/easyinstruct
공식 코드https://github.com/zrrskywalker/mavis
공식 코드MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine
https://github.com/zwhe99/deepmath
공식 코드https://github.com/zwq2018/embodied_reasoner
공식 코드Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks
https://github.com/zwq2018/multi-view-consistency-for-mwp
공식 코드Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem
https://gitlab.uni-koblenz.de/obermaie/negationcognitivereasoning
공식 코드https://github.com/12kimih/hicupid
https://github.com/2003pro/Graph2Tree
https://github.com/2023-MindSpore-1/ms-code-146
LogicSolver: Towards Interpretable Math Word Problem Solving with Logical Prompt-enhanced Learning
https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/llama
https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/deberta
https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/deberta_v2
https://github.com/Chenny0808/ape210k
Ape210K: A Large-Scale and Template-Rich Dataset of Math Word Problems
https://github.com/Davidzhangyuanhan/NOAH
https://github.com/ForoughA/neuralMath
https://github.com/IBM/Dromedary
https://github.com/Infini-AI-Lab/gsm_infinite
Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process
https://github.com/InternLM/opencompass
NeedleBench: Can LLMs Do Retrieval and Reasoning in Information-Dense Context?
https://github.com/JONGWE1/Paddle-DeBERTa
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.