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 861–870 of 1135 papers

TitleStatusHype
Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free LunchCode2
PhoGPT: Generative Pre-training for VietnameseCode2
ChEF: A Comprehensive Evaluation Framework for Standardized Assessment of Multimodal Large Language Models—0
COSMIC: Data Efficient Instruction-tuning For Speech In-Context Learning—0
Active Reasoning in an Open-World Environment—0
FaithScore: Fine-grained Evaluations of Hallucinations in Large Vision-Language ModelsCode1
Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game—0
Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy InstructionsCode1
FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language ModelsCode1
Making Large Language Models Better Data CreatorsCode1
Show:102550
← PrevPage 87 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