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 221–230 of 1135 papers

TitleStatusHype
Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLMCode1
Large Language Models as Evaluators for Recommendation ExplanationsCode1
DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate HallucinationsCode1
AlpaGasus: Training A Better Alpaca with Fewer DataCode1
DANLI: Deliberative Agent for Following Natural Language InstructionsCode1
AlpaCare:Instruction-tuned Large Language Models for Medical ApplicationCode1
GIE-Bench: Towards Grounded Evaluation for Text-Guided Image EditingCode1
LASeR: Learning to Adaptively Select Reward Models with Multi-Armed BanditsCode1
From Pixels to UI Actions: Learning to Follow Instructions via Graphical User InterfacesCode1
From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction TuningCode1
Show:102550
← PrevPage 23 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