Papers with Code 아카이브

MMLU

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

0

평가표

3

보존된 평가 기록

1

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/leeroo-ai/leeroo_orchestrator

공식 코드

Routoo: Learning to Route to Large Language Models Effectively

https://github.com/linkedin/controlllm

공식 코드

Control LLM: Controlled Evolution for Intelligence Retention in LLM

https://github.com/liyucheng09/contamination_detector

공식 코드

An Open Source Data Contamination Report for Large Language Models

https://github.com/lkaesberg/decision-protocols

공식 코드

Voting or Consensus? Decision-Making in Multi-Agent Debate

https://github.com/lm-sys/llm-decontaminator

공식 코드

Rethinking Benchmark and Contamination for Language Models with Rephrased Samples

https://github.com/longfeiyun17/diversitycollapse

공식 코드

The Price of Format: Diversity Collapse in LLMs

https://github.com/lotusrc/d2po

공식 코드

Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay Perspective

https://github.com/lranaldii/crossalpaca

공식 코드

Empowering Cross-lingual Abilities of Instruction-tuned Large Language Models by Translation-following demonstrations

https://github.com/lrudl/sad

공식 코드

Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs

https://github.com/lukasvierling/dynamicgptswarm

공식 코드

Input Conditioned Graph Generation for Language Agents

https://github.com/maitrix-org/de-arena

공식 코드

Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models

https://github.com/manishemirani/void_in_language_models

공식 코드

Void in Language Models

https://github.com/microsoft/FILM

공식 코드

Make Your LLM Fully Utilize the Context

https://github.com/microsoft/mmlu-cf

공식 코드

MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark

https://github.com/microsoft/moonlit

공식 코드

Compresso: Structured Pruning with Collaborative Prompting Learns Compact Large Language Models

https://github.com/microsoft/promptbench

공식 코드

Efficient multi-prompt evaluation of LLMs

https://github.com/modeeric/orbit-llama

공식 코드

ORBIT: Cost-Effective Dataset Curation for Large Language Model Domain Adaptation with an Astronomy Case Study

https://github.com/mosesananta/qless

공식 코드

QLESS: A Quantized Approach for Data Valuation and Selection in Large Language Model Fine-Tuning

https://github.com/nailashfrni/mcq-leakage-detection-code

공식 코드

Simulating Training Data Leakage in Multiple-Choice Benchmarks for LLM Evaluation

https://github.com/national-center-for-ai-saudi-arabia/lm-evaluation-harness

공식 코드

When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards

https://github.com/networks-learning/coupled-llm-evaluation

공식 코드

Evaluation of Large Language Models via Coupled Token Generation

https://github.com/nivgold/dfpe

공식 코드

DFPE: A Diverse Fingerprint Ensemble for Enhancing LLM Performance

https://github.com/nvlabs/minitron

공식 코드

Compact Language Models via Pruning and Knowledge Distillation

https://github.com/openmatch/augmentation-adapted-retriever

공식 코드

Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-In

https://github.com/opennlg/openba

공식 코드

OpenBA: An Open-sourced 15B Bilingual Asymmetric seq2seq Model Pre-trained from Scratch

https://github.com/optimalscale/lmflow

공식 코드

LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning

https://github.com/paperswithcode/galai

공식 코드

Galactica: A Large Language Model for Science

https://github.com/pixeli99/owlore

공식 코드

OwLore: Outlier-weighed Layerwise Sampled Low-Rank Projection for Memory-Efficient LLM Fine-tuning

https://github.com/prateeky2806/compeft

공식 코드

ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization

https://github.com/psunlpgroup/fover

공식 코드

Training Step-Level Reasoning Verifiers with Formal Verification Tools

https://github.com/pytorch-labs/applied-ai

공식 코드

HadaCore: Tensor Core Accelerated Hadamard Transform Kernel

https://github.com/qingyangzhang/empo

공식 코드

Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization

https://github.com/qwenlm/qwen2

공식 코드

Qwen2 Technical Report

https://github.com/raojay7/commonit

공식 코드

CommonIT: Commonality-Aware Instruction Tuning for Large Language Models via Data Partitions

https://github.com/rishabh-ranjan/post-hoc-reversal

공식 코드

Post-Hoc Reversal: Are We Selecting Models Prematurely?

https://github.com/rucaibox/gpo

공식 코드

Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers

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