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 921–930 of 1135 papers

TitleStatusHype
Building Accurate Translation-Tailored LLMs with Language Aware Instruction TuningCode0
VisualCritic: Making LMMs Perceive Visual Quality Like Humans—0
WoLF: Wide-scope Large Language Model Framework for CXR Understanding—0
Third-Party Language Model Performance Prediction from InstructionCode0
Don't Half-listen: Capturing Key-part Information in Continual Instruction Tuning—0
Mitigating Dialogue Hallucination for Large Vision Language Models via Adversarial Instruction Tuning—0
DiffChat: Learning to Chat with Text-to-Image Synthesis Models for Interactive Image Creation—0
CoTBal: Comprehensive Task Balancing for Multi-Task Visual Instruction Tuning—0
Aligners: Decoupling LLMs and AlignmentCode0
KIWI: A Dataset of Knowledge-Intensive Writing Instructions for Answering Research Questions—0
Show:102550
← PrevPage 93 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