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 701–710 of 1135 papers

TitleStatusHype
Fox-1 Technical Report—0
Bayesian Calibration of Win Rate Estimation with LLM EvaluatorsCode0
Multi-Reward as Condition for Instruction-based Image Editing—0
On the Loss of Context-awareness in General Instruction Fine-tuningCode0
Rate, Explain and Cite (REC): Enhanced Explanation and Attribution in Automatic Evaluation by Large Language ModelsCode0
Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors—0
TypeScore: A Text Fidelity Metric for Text-to-Image Generative Models—0
Beyond Content Relevance: Evaluating Instruction Following in Retrieval ModelsCode0
MDCure: A Scalable Pipeline for Multi-Document Instruction-FollowingCode0
UFT: Unifying Fine-Tuning of SFT and RLHF/DPO/UNA through a Generalized Implicit Reward Function—0
Show:102550
← PrevPage 71 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