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 301–350 of 1135 papers

TitleStatusHype
RuleR: Improving LLM Controllability by Rule-based Data RecyclingCode1
Hybrid Alignment Training for Large Language ModelsCode1
LLaSA: A Multimodal LLM for Human Activity Analysis Through Wearable and Smartphone SensorsCode1
Finding Blind Spots in Evaluator LLMs with Interpretable ChecklistsCode1
RS-GPT4V: A Unified Multimodal Instruction-Following Dataset for Remote Sensing Image UnderstandingCode1
ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat TemplatesCode1
WPO: Enhancing RLHF with Weighted Preference OptimizationCode1
TasTe: Teaching Large Language Models to Translate through Self-ReflectionCode1
SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific LiteratureCode1
Large Language Models as Evaluators for Recommendation ExplanationsCode1
Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play ApproachCode1
Is In-Context Learning Sufficient for Instruction Following in LLMs?Code1
Instruction-Guided Visual MaskingCode1
MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn InteractionsCode1
AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source DataCode1
Mosaic-IT: Free Compositional Data Augmentation Improves Instruction TuningCode1
RecGPT: Generative Pre-training for Text-based RecommendationCode1
The Instruction Hierarchy: Training LLMs to Prioritize Privileged InstructionsCode1
Facial Affective Behavior Analysis with Instruction TuningCode1
Evaluating LLMs at Detecting Errors in LLM ResponsesCode1
MMIDR: Teaching Large Language Model to Interpret Multimodal Misinformation via Knowledge DistillationCode1
ChartInstruct: Instruction Tuning for Chart Comprehension and ReasoningCode1
Online Continual Learning For Interactive Instruction Following AgentsCode1
Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal ModelsCode1
IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code GeneratorsCode1
NPHardEval4V: A Dynamic Reasoning Benchmark of Multimodal Large Language ModelsCode1
MELoRA: Mini-Ensemble Low-Rank Adapters for Parameter-Efficient Fine-TuningCode1
Pragmatic Instruction Following and Goal Assistance via Cooperative Language-Guided Inverse PlanningCode1
Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation SystemsCode1
Defending Large Language Models against Jailbreak Attacks via Semantic SmoothingCode1
On the Multi-turn Instruction Following for Conversational Web AgentsCode1
INSTRUCTIR: A Benchmark for Instruction Following of Information Retrieval ModelsCode1
PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt TuningCode1
Your Vision-Language Model Itself Is a Strong Filter: Towards High-Quality Instruction Tuning with Data SelectionCode1
Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language ModelsCode1
Answer is All You Need: Instruction-following Text Embedding via Answering the QuestionCode1
Aya Dataset: An Open-Access Collection for Multilingual Instruction TuningCode1
Personalized Language Modeling from Personalized Human FeedbackCode1
A Survey on Data Selection for LLM Instruction TuningCode1
SelectLLM: Can LLMs Select Important Instructions to Annotate?Code1
F-Eval: Assessing Fundamental Abilities with Refined Evaluation MethodsCode1
Self-Rewarding Language ModelsCode1
Kun: Answer Polishment for Chinese Self-Alignment with Instruction Back-TranslationCode1
Benchmarking Large Language Models on Controllable Generation under Diversified InstructionsCode1
Jatmo: Prompt Injection Defense by Task-Specific FinetuningCode1
An In-depth Look at Gemini's Language AbilitiesCode1
M3DBench: Let's Instruct Large Models with Multi-modal 3D PromptsCode1
Creative Agents: Empowering Agents with Imagination for Creative TasksCode1
Generative Parameter-Efficient Fine-TuningCode1
SeaLLMs -- Large Language Models for Southeast AsiaCode1
Show:102550
← PrevPage 7 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