Papers with Code 아카이브

GSM8K

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

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/8188zq/Inference-Time-Decontamination

공식 코드

Inference-Time Decontamination: Reusing Leaked Benchmarks for Large Language Model Evaluation

https://github.com/DAMO-NLP-SG/FineReason

공식 코드

FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving

https://github.com/Gunale0926/SORSA

공식 코드

SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language Models

https://github.com/HKUDS/SepLLM

공식 코드

SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator

https://github.com/Harry67Hu/CORY

공식 코드

Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning

https://github.com/Lolo1222/EquivPruner

공식 코드

EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning

https://github.com/NVIDIA/NeMo-Inspector

공식 코드

NeMo-Inspector: A Visualization Tool for LLM Generation Analysis

https://github.com/Rain9876/ShareLoRA

공식 코드

ShareLoRA: Parameter Efficient and Robust Large Language Model Fine-tuning via Shared Low-Rank Adaptation

https://github.com/TanZhendong/AR-Sampling

공식 코드

Adaptive Rectification Sampling for Test-Time Compute Scaling

https://github.com/TracyGuo2001/NLoRA

공식 코드

NLoRA: Nyström-Initiated Low-Rank Adaptation for Large Language Models

https://github.com/YuxiXie/MCTS-DPO

공식 코드

Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning

https://github.com/adkipnis/metabench

공식 코드

$\texttt{metabench}$ -- A Sparse Benchmark to Measure General Ability in Large Language Models

https://github.com/aiframeresearch/spo

공식 코드

Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models

https://github.com/akarim23131/lost_in_cultural_translation

공식 코드

Lost in Cultural Translation: Do LLMs Struggle with Math Across Cultural Contexts?

https://github.com/aladinD/SafeMERGE

공식 코드

SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging

https://github.com/alonso130r/knowledge-distillation

공식 코드

Enhancing Knowledge Distillation for LLMs with Response-Priming Prompting

https://github.com/apple/axlearn

공식 코드

Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM Training

https://github.com/awwang10/llmpromptboosting

공식 코드

Boosted Prompt Ensembles for Large Language Models

https://github.com/baichuan-inc/baichuan2

공식 코드

Baichuan 2: Open Large-scale Language Models

https://github.com/beyonderxx/trace

공식 코드

TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models

https://github.com/bigai-nlco/latentseek

공식 코드

Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space

https://github.com/bryanchrist/mathneuro

공식 코드

Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passes

https://github.com/caisa-lab/arithmattack

공식 코드

ArithmAttack: Evaluating Robustness of LLMs to Noisy Context in Math Problem Solving

https://github.com/ccai-lab/self-braking-tuning

공식 코드

Let LLMs Break Free from Overthinking via Self-Braking Tuning

https://github.com/changyuchen347/maskedthought

공식 코드

Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models

https://github.com/chengpengli1003/dotamath

공식 코드

DotaMath: Decomposition of Thought with Code Assistance and Self-correction for Mathematical Reasoning

https://github.com/chenzhiling9954/critical-tokens-matter

공식 코드

Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability

https://github.com/chuanyang-Zheng/Progressive-Hint

공식 코드

Progressive-Hint Prompting Improves Reasoning in Large Language Models

https://github.com/d223302/over-reasoning-of-llms

공식 코드

Over-Reasoning and Redundant Calculation of Large Language Models

https://github.com/da03/internalize_cot_step_by_step

공식 코드

From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step

https://github.com/dair-iitd/fill-in-the-blank-mwp

공식 코드

Fill in the Blank: Exploring and Enhancing LLM Capabilities for Backward Reasoning in Math Word Problems

https://github.com/damo-nlp-sg/caring

공식 코드

Neuro-Symbolic Integration Brings Causal and Reliable Reasoning Proofs

https://github.com/data-dream-gdsp/Multiplex-CoT

공식 코드

MyGO Multiplex CoT: A Method for Self-Reflection in Large Language Models via Double Chain of Thought Thinking

https://github.com/davidfanzz/scmoe

공식 코드

Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-Contrast

https://github.com/declare-lab/della

공식 코드

DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling

https://github.com/declare-lab/llm-reasoningtest

공식 코드

Evaluating LLMs' Mathematical and Coding Competency through Ontology-guided Interventions

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.