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 671–680 of 1135 papers

TitleStatusHype
Iterative Value Function Optimization for Guided Decoding—0
Iterative Vision-and-Language Navigation—0
JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent—0
Adaptive Detoxification: Safeguarding General Capabilities of LLMs through Toxicity-Aware Knowledge Editing—0
Joint Embeddings for Graph Instruction Tuning—0
Joint Flashback Adaptation for Forgetting-Resistant Instruction Tuning—0
The Hidden Space of Safety: Understanding Preference-Tuned LLMs in Multilingual context—0
KAUCUS: Knowledge Augmented User Simulators for Training Language Model Assistants—0
Keypoints-Integrated Instruction-Following Data Generation for Enhanced Human Pose Understanding in Multimodal Models—0
KITE: Keypoint-Conditioned Policies for Semantic Manipulation—0
Show:102550
← PrevPage 68 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