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 991–1000 of 1135 papers

TitleStatusHype
NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language ModelsCode2
PandaGPT: One Model To Instruction-Follow Them AllCode2
TOAST: Transfer Learning via Attention SteeringCode1
PathAsst: A Generative Foundation AI Assistant Towards Artificial General Intelligence of PathologyCode1
PIVOINE: Instruction Tuning for Open-world Information ExtractionCode1
ExpertPrompting: Instructing Large Language Models to be Distinguished ExpertsCode2
Bactrian-X: Multilingual Replicable Instruction-Following Models with Low-Rank AdaptationCode1
SAIL: Search-Augmented Instruction Learning—0
A Monte Carlo Language Model Pipeline for Zero-Shot Sociopolitical Event Extraction—0
QLoRA: Efficient Finetuning of Quantized LLMsCode6
Show:102550
← PrevPage 100 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