Papers with Code 아카이브
Instruction Following
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 1
- 보존된 평가 기록
- 4
Instruction following is the basic task of the model. This task is dedicated to evaluating the ability of the large model to follow human instructions. It is hoped that the model can generate controllable and safe answers.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/thu-keg/agentif
공식 코드AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios
https://github.com/thu-keg/crab
공식 코드Constraint Back-translation Improves Complex Instruction Following of Large Language Models
https://github.com/thu-keg/verif
공식 코드VerIF: Verification Engineering for Reinforcement Learning in Instruction Following
https://github.com/thudm/agentbench
공식 코드https://github.com/thudm/chatglm-6b
공식 코드ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools
https://github.com/thudm/longalign
공식 코드LongAlign: A Recipe for Long Context Alignment of Large Language Models
https://github.com/thunlp/muffin
공식 코드Reformulating Vision-Language Foundation Models and Datasets Towards Universal Multimodal Assistants
https://github.com/tianyi-lab/cherry_llm
공식 코드https://github.com/tianyi-lab/mosaic-it
공식 코드Mosaic-IT: Free Compositional Data Augmentation Improves Instruction Tuning
https://github.com/tianyi-lab/reflection_tuning
공식 코드Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning
https://github.com/tianyi-lab/ruler
공식 코드RuleR: Improving LLM Controllability by Rule-based Data Recycling
https://github.com/tianyu-z/strict-bench
공식 코드https://github.com/timdettmers/bitsandbytes
공식 코드https://github.com/tingchenfu/mathif
공식 코드Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models
https://github.com/tjunlp-lab/m3ke
공식 코드https://github.com/tml-epfl/icl-alignment
공식 코드Is In-Context Learning Sufficient for Instruction Following in LLMs?
https://github.com/ttengwang/caption-anything
공식 코드Caption Anything: Interactive Image Description with Diverse Multimodal Controls
https://github.com/tzjtatata/myriad
공식 코드Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detection
https://github.com/ucsb-nlp-chang/semanticsmooth
공식 코드Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing
https://github.com/uds-lsv/multilingual-icl-analysis
공식 코드The Impact of Demonstrations on Multilingual In-Context Learning: A Multidimensional Analysis
https://github.com/uiuctml/mergebench
공식 코드https://github.com/ukplab/on-emergence
공식 코드Are Emergent Abilities in Large Language Models just In-Context Learning?
https://github.com/ustc-starteam/chemeval
공식 코드ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models
https://github.com/uw-nsl/ChatBug
공식 코드ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates
https://github.com/vargpt-family/vargpt-v1.1
공식 코드https://github.com/veronicium/doclens
공식 코드DocLens: Multi-aspect Fine-grained Evaluation for Medical Text Generation
https://github.com/vim-bench/vim_tool
공식 코드Text as Images: Can Multimodal Large Language Models Follow Printed Instructions in Pixels?
https://github.com/vinairesearch/phogpt
공식 코드https://github.com/vinairesearch/recgpt
공식 코드RecGPT: Generative Pre-training for Text-based Recommendation
https://github.com/vis-nlp/chartinstruct
공식 코드ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoning
https://github.com/vistec-ai/wangchanlion
공식 코드https://github.com/vzhong/language_feedback_models
공식 코드https://github.com/wagner-group/prompt-injection-defense
공식 코드https://github.com/walledai/walledeval
공식 코드WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models
https://github.com/waltonfuture/InstructionGPT-4
공식 코드InstructionGPT-4: A 200-Instruction Paradigm for Fine-Tuning MiniGPT-4
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.