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 411–420 of 1135 papers

TitleStatusHype
IDA-Bench: Evaluating LLMs on Interactive Guided Data AnalysisCode1
An In-depth Look at Gemini's Language AbilitiesCode1
PIVOINE: Instruction Tuning for Open-world Information ExtractionCode1
PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient GenerationCode1
Bridging and Modeling Correlations in Pairwise Data for Direct Preference OptimizationCode1
Don't Reinvent the Wheel: Efficient Instruction-Following Text Embedding based on Guided Space TransformationCode1
MELoRA: Mini-Ensemble Low-Rank Adapters for Parameter-Efficient Fine-TuningCode1
OphGLM: Training an Ophthalmology Large Language-and-Vision Assistant based on Instructions and DialogueCode1
BotChat: Evaluating LLMs' Capabilities of Having Multi-Turn DialoguesCode1
Do LLMs "know" internally when they follow instructions?Code1
Show:102550
← PrevPage 42 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