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 361–370 of 1135 papers

TitleStatusHype
Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form PlanningCode1
Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation SystemsCode1
Fool Your (Vision and) Language Model With Embarrassingly Simple PermutationsCode1
A Recipe For Building a Compliant Real Estate ChatbotCode1
Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small ScorerCode1
Jatmo: Prompt Injection Defense by Task-Specific FinetuningCode1
Kun: Answer Polishment for Chinese Self-Alignment with Instruction Back-TranslationCode1
Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated TextCode1
Efficient Inference of Vision Instruction-Following Models with Elastic CacheCode1
FuseChat-3.0: Preference Optimization Meets Heterogeneous Model FusionCode1
Show:102550
← PrevPage 37 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