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 621–630 of 1135 papers

TitleStatusHype
Weak-to-Strong Search: Align Large Language Models via Searching over Small Language ModelsCode2
Self-Exploring Language Models: Active Preference Elicitation for Online AlignmentCode2
Empowering Source-Free Domain Adaptation with MLLM-driven Curriculum LearningCode0
Self-Corrected Multimodal Large Language Model for End-to-End Robot Manipulation—0
PromptFix: You Prompt and We Fix the PhotoCode4
RE-Adapt: Reverse Engineered Adaptation of Large Language Models—0
From Role-Play to Drama-Interaction: An LLM Solution—0
EditWorld: Simulating World Dynamics for Instruction-Following Image EditingCode2
SimPO: Simple Preference Optimization with a Reference-Free RewardCode4
A Survey on Vision-Language-Action Models for Embodied AICode4
Show:102550
← PrevPage 63 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