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 451–500 of 1135 papers

TitleStatusHype
Instruction Following without Instruction TuningCode1
Repairs in a Block World: A New Benchmark for Handling User Corrections with Multi-Modal Language ModelsCode0
ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language ModelsCode1
Eliciting Instruction-tuned Code Language Models' Capabilities to Utilize Auxiliary Function for Code Generation—0
Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form PlanningCode1
CamelEval: Advancing Culturally Aligned Arabic Language Models and Benchmarks—0
SIFToM: Robust Spoken Instruction Following through Theory of Mind—0
Exploring the Trade-Offs: Quantization Methods, Task Difficulty, and Model Size in Large Language Models From Edge to GiantCode0
Enhancing Low-Resource Language and Instruction Following Capabilities of Audio Language Models—0
Diversify and Conquer: Diversity-Centric Data Selection with Iterative RefinementCode1
Emo-DPO: Controllable Emotional Speech Synthesis through Direct Preference Optimization—0
SFR-RAG: Towards Contextually Faithful LLMs—0
StressPrompt: Does Stress Impact Large Language Models and Human Performance Similarly?—0
ASFT: Aligned Supervised Fine-Tuning through Absolute LikelihoodCode3
Keypoints-Integrated Instruction-Following Data Generation for Enhanced Human Pose Understanding in Multimodal Models—0
AdaPPA: Adaptive Position Pre-Fill Jailbreak Attack Approach Targeting LLMsCode0
RNR: Teaching Large Language Models to Follow Roles and Rules—0
Leveraging LLMs for Influence Path Planning in Proactive Recommendation—0
Continual Skill and Task Learning via Dialogue—0
Prompt Baking—0
LongGenBench: Benchmarking Long-Form Generation in Long Context LLMsCode1
Self-Judge: Selective Instruction Following with Alignment Self-EvaluationCode0
ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI SystemsCode3
Language Models Benefit from Preparation with Elicited Knowledge—0
Does Alignment Tuning Really Break LLMs' Internal Confidence?Code0
M4CXR: Exploring Multi-task Potentials of Multi-modal Large Language Models for Chest X-ray Interpretation—0
Entropic Distribution Matching in Supervised Fine-tuning of LLMs: Less Overfitting and Better Diversity—0
SciLitLLM: How to Adapt LLMs for Scientific Literature UnderstandingCode2
Multi-Modal Instruction-Tuning Small-Scale Language-and-Vision Assistant for Semiconductor Electron Micrograph Analysis—0
Parameter-Efficient Quantized Mixture-of-Experts Meets Vision-Language Instruction Tuning for Semiconductor Electron Micrograph Analysis—0
Instruct-SkillMix: A Powerful Pipeline for LLM Instruction TuningCode0
Foundational Model for Electron Micrograph Analysis: Instruction-Tuning Small-Scale Language-and-Vision Assistant for Enterprise Adoption—0
Preference Consistency Matters: Enhancing Preference Learning in Language Models with Automated Self-Curation of Training Corpora—0
Jamba-1.5: Hybrid Transformer-Mamba Models at ScaleCode5
Preference-Guided Reflective Sampling for Aligning Language ModelsCode0
Kubrick: Multimodal Agent Collaborations for Synthetic Video Generation—0
LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMsCode1
Ex3: Automatic Novel Writing by Extracting, Excelsior and ExpandingCode1
FuseChat: Knowledge Fusion of Chat ModelsCode4
Can Large Language Models Understand Symbolic Graphics Programs?—0
Bridging and Modeling Correlations in Pairwise Data for Direct Preference OptimizationCode1
IFShip: Interpretable Fine-grained Ship Classification with Domain Knowledge-Enhanced Vision-Language ModelsCode0
CROME: Cross-Modal Adapters for Efficient Multimodal LLM—0
Creating Arabic LLM Prompts at Scale—0
Space-LLaVA: a Vision-Language Model Adapted to Extraterrestrial Applications—0
Investigating Instruction Tuning Large Language Models on GraphsCode1
LLaVA-VSD: Large Language-and-Vision Assistant for Visual Spatial DescriptionCode0
EXAONE 3.0 7.8B Instruction Tuned Language Model—0
Empirical Analysis of Large Vision-Language Models against Goal Hijacking via Visual Prompt Injection—0
1.5-Pints Technical Report: Pretraining in Days, Not Months -- Your Language Model Thrives on Quality DataCode3
Show:102550
← PrevPage 10 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