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 141–150 of 1135 papers

TitleStatusHype
Holistic Capability Preservation: Towards Compact Yet Comprehensive Reasoning Models—0
Sculpting Subspaces: Constrained Full Fine-Tuning in LLMs for Continual LearningCode1
From 128K to 4M: Efficient Training of Ultra-Long Context Large Language Models—0
Finding Fantastic Experts in MoEs: A Unified Study for Expert Dropping Strategies and Observations—0
Separator Injection Attack: Uncovering Dialogue Biases in Large Language Models Caused by Role Separators—0
Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language ModelsCode2
VARGPT-v1.1: Improve Visual Autoregressive Large Unified Model via Iterative Instruction Tuning and Reinforcement LearningCode3
CrystalFormer-RL: Reinforcement Fine-Tuning for Materials DesignCode2
STING-BEE: Towards Vision-Language Model for Real-World X-ray Baggage Security InspectionCode1
The Hidden Space of Safety: Understanding Preference-Tuned LLMs in Multilingual context—0
Show:102550
← PrevPage 15 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