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 201–250 of 1135 papers

TitleStatusHype
LLM-RG4: Flexible and Factual Radiology Report Generation across Diverse Input ContextsCode2
VerIF: Verification Engineering for Reinforcement Learning in Instruction FollowingCode2
MAPLM: A Real-World Large-Scale Vision-Language Benchmark for Map and Traffic Scene UnderstandingCode2
Aligning Modalities in Vision Large Language Models via Preference Fine-tuningCode2
Autonomous Improvement of Instruction Following Skills via Foundation ModelsCode2
Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task ArithmeticCode2
MM-IFEngine: Towards Multimodal Instruction FollowingCode2
Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction FollowingCode2
The Replica Dataset: A Digital Replica of Indoor SpacesCode2
Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context LearningCode1
Adaptive Markup Language Generation for Contextually-Grounded Visual Document UnderstandingCode1
LLaSA: A Multimodal LLM for Human Activity Analysis Through Wearable and Smartphone SensorsCode1
LLaMo: Large Language Model-based Molecular Graph AssistantCode1
A Multi-Modal AI Copilot for Single-Cell Analysis with Instruction FollowingCode1
DISCO: Embodied Navigation and Interaction via Differentiable Scene Semantics and Dual-level ControlCode1
A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language ModelsCode1
BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language ModelsCode1
Instruction Following without Instruction TuningCode1
Benchmarking Large Language Models on Controllable Generation under Diversified InstructionsCode1
Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable SummarizationCode1
A modular vision language navigation and manipulation framework for long horizon compositional tasks in indoor environmentCode1
Democratizing Reasoning Ability: Tailored Learning from Large Language ModelCode1
Defending Large Language Models against Jailbreak Attacks via Semantic SmoothingCode1
Guiding Multi-Step Rearrangement Tasks with Natural Language InstructionsCode1
Defending Large Language Models Against Jailbreaking Attacks Through Goal PrioritizationCode1
DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate HallucinationsCode1
AlpaGasus: Training A Better Alpaca with Fewer DataCode1
HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction DataCode1
DANLI: Deliberative Agent for Following Natural Language InstructionsCode1
AlpaCare:Instruction-tuned Large Language Models for Medical ApplicationCode1
GIE-Bench: Towards Grounded Evaluation for Text-Guided Image EditingCode1
Hybrid Alignment Training for Large Language ModelsCode1
LIONs: An Empirically Optimized Approach to Align Language ModelsCode1
Demystifying Domain-adaptive Post-training for Financial LLMsCode1
Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLMCode1
Curiosity-Driven Reinforcement Learning from Human FeedbackCode1
AllenAct: A Framework for Embodied AI ResearchCode1
DialFRED: Dialogue-Enabled Agents for Embodied Instruction FollowingCode1
CrowdSelect: Synthetic Instruction Data Selection with Multi-LLM WisdomCode1
Bactrian-X: Multilingual Replicable Instruction-Following Models with Low-Rank AdaptationCode1
Learning to Map Natural Language Instructions to Physical Quadcopter Control using Simulated FlightCode1
Cross-model Control: Improving Multiple Large Language Models in One-time TrainingCode1
Back to the Future: Towards Explainable Temporal Reasoning with Large Language ModelsCode1
Zero-Shot Compositional Policy Learning via Language GroundingCode1
LASeR: Learning to Adaptively Select Reward Models with Multi-Armed BanditsCode1
Aya Dataset: An Open-Access Collection for Multilingual Instruction TuningCode1
Creative Agents: Empowering Agents with Imagination for Creative TasksCode1
FuseChat-3.0: Preference Optimization Meets Heterogeneous Model FusionCode1
Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language NavigationCode1
Lexicon Learning for Few-Shot Neural Sequence ModelingCode1
Show:102550
← PrevPage 5 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