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 651–660 of 1135 papers

TitleStatusHype
Modular Networks for Compositional Instruction Following—0
Can Large Language Models Understand Symbolic Graphics Programs?—0
Traffic Sign Interpretation in Real Road Scene—0
CamelEval: Advancing Culturally Aligned Arabic Language Models and Benchmarks—0
Training an LLM-as-a-Judge Model: Pipeline, Insights, and Practical Lessons—0
CorNav: Autonomous Agent with Self-Corrected Planning for Zero-Shot Vision-and-Language Navigation—0
MrSteve: Instruction-Following Agents in Minecraft with What-Where-When Memory—0
MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Following—0
CachePrune: Neural-Based Attribution Defense Against Indirect Prompt Injection Attacks—0
Multi-Level Aware Preference Learning: Enhancing RLHF for Complex Multi-Instruction Tasks—0
Show:102550
← PrevPage 66 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