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 1–50 of 1135 papers

TitleStatusHype
AnyCap Project: A Unified Framework, Dataset, and Benchmark for Controllable Omni-modal Captioning—0
How Many Instructions Can LLMs Follow at Once?—0
DrafterBench: Benchmarking Large Language Models for Tasks Automation in Civil EngineeringCode2
Multilingual Multimodal Software Developer for Code Generation—0
TuneShield: Mitigating Toxicity in Conversational AI while Fine-tuning on Untrusted Data—0
Meta SecAlign: A Secure Foundation LLM Against Prompt Injection AttacksCode2
DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal AlignmentCode2
Kwai Keye-VL Technical ReportCode4
Bridging Offline and Online Reinforcement Learning for LLMs—0
LLaVA-Pose: Enhancing Human Pose and Action Understanding via Keypoint-Integrated Instruction TuningCode0
Multi-lingual Functional Evaluation for Large Language Models—0
Learning Instruction-Following Policies through Open-Ended Instruction Relabeling with Large Language Models—0
JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent—0
InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech SystemsCode1
Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers—0
Instruction Following by Boosting Attention of Large Language Models—0
Mixture of Weight-shared Heterogeneous Group Attention Experts for Dynamic Token-wise KV Optimization—0
LeVERB: Humanoid Whole-Body Control with Latent Vision-Language Instruction—0
MM-R5: MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document RetrievalCode0
CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following—0
HalLoc: Token-level Localization of Hallucinations for Vision Language ModelsCode0
AC/DC: LLM-based Audio Comprehension via Dialogue Continuation—0
Conversational Search: From Fundamentals to Frontiers in the LLM Era—0
Magistral—0
Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation LearningCode0
Alzheimer's Dementia Detection Using Perplexity from Paired Large Language Models—0
VerIF: Verification Engineering for Reinforcement Learning in Instruction FollowingCode2
LLaVA-c: Continual Improved Visual Instruction Tuning—0
RHealthTwin: Towards Responsible and Multimodal Digital Twins for Personalized Well-being—0
EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language ModelsCode0
LeVo: High-Quality Song Generation with Multi-Preference AlignmentCode5
Video Unlearning via Low-Rank Refusal Vector—0
Aligning Text, Images, and 3D Structure Token-by-Token—0
Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated TextCode1
Audio-Aware Large Language Models as Judges for Speaking Styles—0
Being Strong Progressively! Enhancing Knowledge Distillation of Large Language Models through a Curriculum Learning FrameworkCode0
RELIC: Evaluating Compositional Instruction Following via Language Recognition—0
Unleashing Hour-Scale Video Training for Long Video-Language Understanding—0
SeedEdit 3.0: Fast and High-Quality Generative Image Editing—0
Identifying Reliable Evaluation Metrics for Scientific Text RevisionCode0
On the Mechanism of Reasoning Pattern Selection in Reinforcement Learning for Language Models—0
Robust Anti-Backdoor Instruction Tuning in LVLMs—0
RewardAnything: Generalizable Principle-Following Reward ModelsCode1
MASTER: Enhancing Large Language Model via Multi-Agent Simulated Teaching—0
TIIF-Bench: How Does Your T2I Model Follow Your Instructions?—0
Incentivizing Reasoning for Advanced Instruction-Following of Large Language ModelsCode1
RewardBench 2: Advancing Reward Model EvaluationCode4
MoDA: Modulation Adapter for Fine-Grained Visual Grounding in Instructional MLLMs—0
FusionAudio-1.2M: Towards Fine-grained Audio Captioning with Multimodal Contextual FusionCode2
PersianMedQA: Language-Centric Evaluation of LLMs in the Persian Medical Domain—0
Show:102550
← PrevPage 1 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