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 31–40 of 1135 papers

TitleStatusHype
LeVo: High-Quality Song Generation with Multi-Preference AlignmentCode5
Aligning Text, Images, and 3D Structure Token-by-Token—0
Video Unlearning via Low-Rank Refusal Vector—0
Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated TextCode1
Audio-Aware Large Language Models as Judges for Speaking Styles—0
Being Strong Progressively! Enhancing Knowledge Distillation of Large Language Models through a Curriculum Learning FrameworkCode0
Identifying Reliable Evaluation Metrics for Scientific Text RevisionCode0
RELIC: Evaluating Compositional Instruction Following via Language Recognition—0
SeedEdit 3.0: Fast and High-Quality Generative Image Editing—0
Unleashing Hour-Scale Video Training for Long Video-Language Understanding—0
Show:102550
← PrevPage 4 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