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 501–510 of 1135 papers

TitleStatusHype
Sparse Activation Editing for Reliable Instruction Following in Narratives—0
ToDi: Token-wise Distillation via Fine-Grained Divergence Control—0
CASTILLO: Characterizing Response Length Distributions of Large Language ModelsCode0
LIFEBench: Evaluating Length Instruction Following in Large Language ModelsCode0
Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective—0
Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought—0
FlowKV: Enhancing Multi-Turn Conversational Coherence in LLMs via Isolated Key-Value Cache Management—0
Joint Flashback Adaptation for Forgetting-Resistant Instruction Tuning—0
ThinkLess: A Training-Free Inference-Efficient Method for Reducing Reasoning Redundancy—0
DecIF: Improving Instruction-Following through Meta-Decomposition—0
Show:102550
← PrevPage 51 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