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 281–290 of 1135 papers

TitleStatusHype
Ex3: Automatic Novel Writing by Extracting, Excelsior and ExpandingCode1
LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMsCode1
Bridging and Modeling Correlations in Pairwise Data for Direct Preference OptimizationCode1
Investigating Instruction Tuning Large Language Models on GraphsCode1
WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language ModelsCode1
Extend Model Merging from Fine-Tuned to Pre-Trained Large Language Models via Weight DisentanglementCode1
ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic EnvironmentsCode1
Efficient Inference of Vision Instruction-Following Models with Elastic CacheCode1
DISCO: Embodied Navigation and Interaction via Differentiable Scene Semantics and Dual-level ControlCode1
EarthMarker: A Visual Prompting Multi-modal Large Language Model for Remote SensingCode1
Show:102550
← PrevPage 29 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