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 801–825 of 1135 papers

TitleStatusHype
SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-ScalingCode3
Aurora:Activating Chinese chat capability for Mixtral-8x7B sparse Mixture-of-Experts through Instruction-TuningCode2
T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by StepCode2
LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding—0
Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuning—0
An In-depth Look at Gemini's Language AbilitiesCode1
M3DBench: Let's Instruct Large Models with Multi-modal 3D PromptsCode1
Rethinking the Instruction Quality: LIFT is What You Need—0
LMDrive: Closed-Loop End-to-End Driving with Large Language ModelsCode2
ThinkBot: Embodied Instruction Following with Thought Chain Reasoning—0
InstructAny2Pix: Flexible Visual Editing via Multimodal Instruction FollowingCode0
Aligner: One Global Token is Worth Millions of Parameters When Aligning Large Language Models—0
Localized Symbolic Knowledge Distillation for Visual Commonsense ModelsCode0
Text as Image: Learning Transferable Adapter for Multi-Label Classification—0
MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Following—0
Creative Agents: Empowering Agents with Imagination for Creative TasksCode1
InstructBooth: Instruction-following Personalized Text-to-Image Generation—0
MedXChat: A Unified Multimodal Large Language Model Framework towards CXRs Understanding and Generation—0
TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video UnderstandingCode2
SeaLLMs -- Large Language Models for Southeast AsiaCode1
Generative Parameter-Efficient Fine-TuningCode1
FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, ToxicityCode0
Contrastive Vision-Language Alignment Makes Efficient Instruction LearnerCode1
Text as Images: Can Multimodal Large Language Models Follow Printed Instructions in Pixels?Code1
Ranni: Taming Text-to-Image Diffusion for Accurate Instruction FollowingCode5
Show:102550
← PrevPage 33 of 46Next →

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