SOTAVerified

Instruction Following

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.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 71–80 of 1135 papers

TitleStatusHype
SongComposer: A Large Language Model for Lyric and Melody Generation in Song CompositionCode3
ShapeLLM: Universal 3D Object Understanding for Embodied InteractionCode3
EventRL: Enhancing Event Extraction with Outcome Supervision for Large Language ModelsCode3
Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-TuningCode3
OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated LearningCode3
DistiLLM: Towards Streamlined Distillation for Large Language ModelsCode3
LongAlign: A Recipe for Long Context Alignment of Large Language ModelsCode3
Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-AlignmentCode3
SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-ScalingCode3
Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language ModelsCode3
Show:102550
← PrevPage 8 of 114Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1AutoIF (Llama3 70B)Inst-level loose-accuracy90.4—Unverified
2AutoIF (Qwen2 72B)Inst-level loose-accuracy88—Unverified
3GPT-4Inst-level loose-accuracy85.37—Unverified
4PaLM 2 SInst-level loose-accuracy59.11—Unverified