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 571–580 of 1135 papers

TitleStatusHype
Diversity Measurement and Subset Selection for Instruction Tuning Datasets—0
Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis—0
Diverse and Fine-Grained Instruction-Following Ability Exploration with Synthetic Data—0
Gaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion Priors—0
Gemma 3 Technical Report—0
DistilQwen2.5: Industrial Practices of Training Distilled Open Lightweight Language Models—0
Distilling Internet-Scale Vision-Language Models into Embodied Agents—0
Generalization in Instruction Following Systems—0
Can Query Expansion Improve Generalization of Strong Cross-Encoder Rankers?—0
Generate Subgoal Images before Act: Unlocking the Chain-of-Thought Reasoning in Diffusion Model for Robot Manipulation with Multimodal Prompts—0
Show:102550
← PrevPage 58 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