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 511–520 of 1135 papers

TitleStatusHype
Data Diversity Matters for Robust Instruction Tuning—0
Hypencoder: Hypernetworks for Information Retrieval—0
Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought—0
Human-Instruction-Free LLM Self-Alignment with Limited Samples—0
DAFE: LLM-Based Evaluation Through Dynamic Arbitration for Free-Form Question-Answering—0
Less is More: Generating Grounded Navigation Instructions from Landmarks—0
LIMIT: Less Is More for Instruction Tuning Across Evaluation Paradigms—0
Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Text—0
HSI-GPT: A General-Purpose Large Scene-Motion-Language Model for Human Scene Interaction—0
D3: Diversity, Difficulty, and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning—0
Show:102550
← PrevPage 52 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