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 261–270 of 1135 papers

TitleStatusHype
Lexicon Learning for Few-Shot Neural Sequence ModelingCode1
CoPESD: A Multi-Level Surgical Motion Dataset for Training Large Vision-Language Models to Co-Pilot Endoscopic Submucosal DissectionCode1
CoachLM: Automatic Instruction Revisions Improve the Data Quality in LLM Instruction TuningCode1
Language-Conditioned Reinforcement Learning to Solve Misunderstandings with Action CorrectionsCode1
Contrastive Vision-Language Alignment Makes Efficient Instruction LearnerCode1
Lana: A Language-Capable Navigator for Instruction Following and GenerationCode1
Language Imbalance Driven Rewarding for Multilingual Self-improvingCode1
Large Language Models as Evaluators for Recommendation ExplanationsCode1
Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation ExtractorsCode1
AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language ModelsCode1
Show:102550
← PrevPage 27 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