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 641–650 of 1135 papers

TitleStatusHype
Improving Instruction Following in Language Models through Proxy-Based Uncertainty EstimationCode0
CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-ExpertsCode2
Zero-shot LLM-guided Counterfactual Generation: A Case Study on NLP Model EvaluationCode0
Long Context Alignment with Short Instructions and Synthesized Positions—0
Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment—0
LLM as Dataset Analyst: Subpopulation Structure Discovery with Large Language ModelCode0
WildChat: 1M ChatGPT Interaction Logs in the Wild—0
LLM-AD: Large Language Model based Audio Description System—0
FLAME: Factuality-Aware Alignment for Large Language Models—0
Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation—0
Show:102550
← PrevPage 65 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