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 691–700 of 1135 papers

TitleStatusHype
RewardBench: Evaluating Reward Models for Language ModelingCode4
WoLF: Wide-scope Large Language Model Framework for CXR Understanding—0
VisualCritic: Making LMMs Perceive Visual Quality Like Humans—0
Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language ModelsCode2
Third-Party Language Model Performance Prediction from InstructionCode0
MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World ControlCode2
Mitigating Dialogue Hallucination for Large Vision Language Models via Adversarial Instruction Tuning—0
Don't Half-listen: Capturing Key-part Information in Continual Instruction Tuning—0
ChartInstruct: Instruction Tuning for Chart Comprehension and ReasoningCode1
CoIN: A Benchmark of Continual Instruction tuNing for Multimodel Large Language ModelCode2
Show:102550
← PrevPage 70 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