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 211–220 of 1135 papers

TitleStatusHype
Adaptive Markup Language Generation for Contextually-Grounded Visual Document UnderstandingCode1
A Multi-Modal AI Copilot for Single-Cell Analysis with Instruction FollowingCode1
Lana: A Language-Capable Navigator for Instruction Following and GenerationCode1
Language-Conditioned Reinforcement Learning to Solve Misunderstandings with Action CorrectionsCode1
A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language ModelsCode1
Kun: Answer Polishment for Chinese Self-Alignment with Instruction Back-TranslationCode1
BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language ModelsCode1
Benchmarking Large Language Models on Controllable Generation under Diversified InstructionsCode1
Instruction Following without Instruction TuningCode1
Language Imbalance Driven Rewarding for Multilingual Self-improvingCode1
Show:102550
← PrevPage 22 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