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 1001–1025 of 1135 papers

TitleStatusHype
Incorporating Visual Experts to Resolve the Information Loss in Multimodal Large Language Models—0
Inference-Time Language Model Alignment via Integrated Value Guidance—0
Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization—0
Data Diversity Matters for Robust Instruction Tuning—0
InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-training—0
InsightEdit: Towards Better Instruction Following for Image Editing—0
DAFE: LLM-Based Evaluation Through Dynamic Arbitration for Free-Form Question-Answering—0
Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following—0
InstructBooth: Instruction-following Personalized Text-to-Image Generation—0
Attend and Enrich: Enhanced Visual Prompt for Zero-Shot Learning—0
Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy—0
InstructionCP: A fast approach to transfer Large Language Models into target language—0
Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game—0
Instruction Following by Boosting Attention of Large Language Models—0
D3: Diversity, Difficulty, and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning—0
Instruction-following Evaluation through Verbalizer Manipulation—0
Instruction-Following Pruning for Large Language Models—0
Instruction-Following Speech Recognition—0
Aligner: One Global Token is Worth Millions of Parameters When Aligning Large Language Models—0
Instruction Mining: Instruction Data Selection for Tuning Large Language Models—0
Tests as Prompt: A Test-Driven-Development Benchmark for LLM Code Generation—0
Instruction Tuning on Public Government and Cultural Data for Low-Resource Language: a Case Study in Kazakh—0
CycleAlign: Iterative Distillation from Black-box LLM to White-box Models for Better Human Alignment—0
Text as Image: Learning Transferable Adapter for Multi-Label Classification—0
Only-IF:Revealing the Decisive Effect of Instruction Diversity on Generalization—0
Show:102550
← PrevPage 41 of 46Next →

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