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 401–450 of 1135 papers

TitleStatusHype
RMM: A Recursive Mental Model for Dialogue NavigationCode1
InstructionGPT-4: A 200-Instruction Paradigm for Fine-Tuning MiniGPT-4Code1
Instruction-Guided Visual MaskingCode1
Can Language Models Follow Multiple Turns of Entangled Instructions?Code1
ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic EnvironmentsCode1
CoPESD: A Multi-Level Surgical Motion Dataset for Training Large Vision-Language Models to Co-Pilot Endoscopic Submucosal DissectionCode1
RealWebAssist: A Benchmark for Long-Horizon Web Assistance with Real-World UsersCode1
EarthMarker: A Visual Prompting Multi-modal Large Language Model for Remote SensingCode1
Instruction-Following Agents with Multimodal TransformerCode1
Instruction Position Matters in Sequence Generation with Large Language ModelsCode1
RecGPT: Generative Pre-training for Text-based RecommendationCode1
Instruct and Extract: Instruction Tuning for On-Demand Information ExtractionCode1
Answer is All You Need: Instruction-following Text Embedding via Answering the QuestionCode1
Instruction-Tuning Data Synthesis from Scratch via Web ReconstructionCode1
Inferring Rewards from Language in ContextCode1
InfMLLM: A Unified Framework for Visual-Language TasksCode1
An In-depth Look at Gemini's Language AbilitiesCode1
Incentivizing Reasoning for Advanced Instruction-Following of Large Language ModelsCode1
Bridging and Modeling Correlations in Pairwise Data for Direct Preference OptimizationCode1
Creative Agents: Empowering Agents with Imagination for Creative TasksCode1
Don't Reinvent the Wheel: Efficient Instruction-Following Text Embedding based on Guided Space TransformationCode1
Aya Dataset: An Open-Access Collection for Multilingual Instruction TuningCode1
Improving Translation Faithfulness of Large Language Models via Augmenting InstructionsCode1
Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction FollowingCode1
BotChat: Evaluating LLMs' Capabilities of Having Multi-Turn DialoguesCode1
Zero-Shot Compositional Policy Learning via Language GroundingCode1
Do LLMs "know" internally when they follow instructions?Code1
A Dual-Space Framework for General Knowledge Distillation of Large Language ModelsCode1
PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient GenerationCode1
Monte Carlo Thought Search: Large Language Model Querying for Complex Scientific Reasoning in Catalyst DesignCode1
PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt TuningCode1
An Emulator for Fine-Tuning Large Language Models using Small Language ModelsCode1
Language-Conditioned Reinforcement Learning to Solve Misunderstandings with Action CorrectionsCode1
Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical StudyCode1
Making Large Language Models Better Data CreatorsCode1
ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language TuningCode1
NPHardEval4V: A Dynamic Reasoning Benchmark of Multimodal Large Language ModelsCode1
Diversify and Conquer: Diversity-Centric Data Selection with Iterative RefinementCode1
IDA-Bench: Evaluating LLMs on Interactive Guided Data AnalysisCode1
Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy InstructionsCode1
IHEval: Evaluating Language Models on Following the Instruction HierarchyCode1
Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language ModelsCode1
Infer Human's Intentions Before Following Natural Language InstructionsCode1
TOAST: Transfer Learning via Attention SteeringCode1
Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning ModelsCode1
STING-BEE: Towards Vision-Language Model for Real-World X-ray Baggage Security InspectionCode1
Playpen: An Environment for Exploring Learning Through Conversational InteractionCode0
Beyond Content Relevance: Evaluating Instruction Following in Retrieval ModelsCode0
Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax ReductionCode0
Analysis of Language Change in Collaborative Instruction FollowingCode0
Show:102550
← PrevPage 9 of 23Next →

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