Papers with Code 아카이브
Multi-task Language Understanding
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 5
- 보존된 평가 기록
- 79
The test covers 57 tasks including elementary mathematics, US history, computer science, law, and more. https://arxiv.org/pdf/2009.03300.pdf
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Effectiveness of Zero-shot-CoT in Japanese Prompts
TUMLU: A Unified and Native Language Understanding Benchmark for Turkic Languages
IndicMMLU-Pro: Benchmarking Indic Large Language Models on Multi-Task Language Understanding
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark
Llama 3 Meets MoE: Efficient Upcycling
GPT-4o as the Gold Standard: A Scalable and General Purpose Approach to Filter Language Model Pretraining Data
Reasoning Beyond Bias: A Study on Counterfactual Prompting and Chain of Thought Reasoning
The Llama 3 Herd of Models
Breaking the Ceiling of the LLM Community by Treating Token Generation as a Classification for Ensembling
Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive Principles
MMLU-SR: A Benchmark for Stress-Testing Reasoning Capability of Large Language Models
MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM
ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic
Routoo: Learning to Route to Large Language Models Effectively
Mixtral of Experts
Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks
Gemini: A Family of Highly Capable Multimodal Models
The Falcon Series of Open Language Models
Orca 2: Teaching Small Language Models How to Reason
MiLe Loss: a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models
Mistral 7B
Large Language Models Only Pass Primary School Exams in Indonesia: A Comprehensive Test on IndoMMLU
Are Human-generated Demonstrations Necessary for In-context Learning?
Textbooks Are All You Need II: phi-1.5 technical report
Llama 2: Open Foundation and Fine-Tuned Chat Models
Let's Do a Thought Experiment: Using Counterfactuals to Improve Moral Reasoning
MERGE: Fast Private Text Generation
PaLM 2 Technical Report
BloombergGPT: A Large Language Model for Finance
GPT-4 Technical Report
LLaMA: Open and Efficient Foundation Language Models
REPLUG: Retrieval-Augmented Black-Box Language Models
Galactica: A Large Language Model for Science
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.