Papers with Code 아카이브
Large Language Model
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 0
- 보존된 평가 기록
- 0
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/niuchuangnn/vllm_structure
공식 코드https://github.com/nju-pcalab/rag-diffusion
공식 코드Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement
https://github.com/nju-websoft/KG2RAG
공식 코드https://github.com/nju-websoft/mmrag
공식 코드https://github.com/nkai-decision-team/llm-pysc2
공식 코드LLM-PySC2: Starcraft II learning environment for Large Language Models
https://github.com/nkanak/brag-fake-news-campaigns
공식 코드https://github.com/nl2code/attentioncoder
공식 코드Improving Natural Language Capability of Code Large Language Model
https://github.com/nl4opt/nl4opt-competition
공식 코드NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions
https://github.com/nlp-bin/silc-efsa
공식 코드SILC-EFSA: Self-aware In-context Learning Correction for Entity-level Financial Sentiment Analysis
https://github.com/nlp-uoregon/ullme
공식 코드ULLME: A Unified Framework for Large Language Model Embeddings with Generation-Augmented Learning
https://github.com/nlp-waseda/comet-atomic-ja
공식 코드PHALM: Building a Knowledge Graph from Scratch by Prompting Humans and a Language Model
https://github.com/nlp2ct/hil-mt
공식 코드Human-in-the-loop Machine Translation with Large Language Model
https://github.com/nlpnorth/snakmodel
공식 코드SnakModel: Lessons Learned from Training an Open Danish Large Language Model
https://github.com/nolanoorg/spectrasuite
공식 코드Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale
https://github.com/nomic-ai/contrastors
공식 코드https://github.com/nomizy/think_net_prompt
공식 코드https://github.com/nomothings/charge
공식 코드Benchmarking Multimodal RAG through a Chart-based Document Question-Answering Generation Framework
https://github.com/norskregnesentral/conv_feedback
공식 코드Conversational Feedback in Scripted versus Spontaneous Dialogues: A Comparative Analysis
https://github.com/northsky0307/dppa-pruning-method-for-large-language-model-to-model-merging
공식 코드DPPA: Pruning Method for Large Language Model to Model Merging
https://github.com/novasearch-team/rag-retrieval
공식 코드Benchmarking the Myopic Trap: Positional Bias in Information Retrieval
https://github.com/novasky-ai/skythought
공식 코드LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!
https://github.com/ntunlp/opensource-llms-better-than-openai
공식 코드ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up?
https://github.com/nu-c3lab/satyrn
공식 코드https://github.com/nu-dialogue/jmultiwoz
공식 코드JMultiWOZ: A Large-Scale Japanese Multi-Domain Task-Oriented Dialogue Dataset
https://github.com/nusioraprivacy/eaas-privacy
공식 코드Split-and-Denoise: Protect large language model inference with local differential privacy
https://github.com/nusnlp/reacts
공식 코드Just What You Desire: Constrained Timeline Summarization with Self-Reflection for Enhanced Relevance
https://github.com/nuster1128/llm_agent_memory_survey
공식 코드A Survey on the Memory Mechanism of Large Language Model based Agents
https://github.com/nuster1128/memengine
공식 코드MemEngine: A Unified and Modular Library for Developing Advanced Memory of LLM-based Agents
https://github.com/nvlabs/coat
공식 코드COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training
https://github.com/nvlabs/maskllm
공식 코드MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models
https://github.com/nyu-llm-ctf/nyuctf_agents_craken
공식 코드CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution
https://github.com/nyuolab/MedDistractQA
공식 코드https://github.com/nyushcs/moleculargpt
공식 코드MolecularGPT: Open Large Language Model (LLM) for Few-Shot Molecular Property Prediction
https://github.com/oaklight/mango
공식 코드MANGO: A Benchmark for Evaluating Mapping and Navigation Abilities of Large Language Models
https://github.com/oashua/mathagent
공식 코드Modeling Complex Mathematical Reasoning via Large Language Model based MathAgent
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.