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 151–200 of 1135 papers

TitleStatusHype
Rec-R1: Bridging Generative Large Language Models and User-Centric Recommendation Systems via Reinforcement LearningCode2
Effectively Controlling Reasoning Models through Thinking Intervention—0
Pay More Attention to the Robustness of Prompt for Instruction Data Mining—0
Learning to Instruct for Visual Instruction Tuning—0
InsViE-1M: Effective Instruction-based Video Editing with Elaborate Dataset ConstructionCode1
Qwen2.5-Omni Technical ReportCode7
Gemma 3 Technical Report—0
SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the WildCode7
OmniGeo: Towards a Multimodal Large Language Models for Geospatial Artificial Intelligence—0
LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction TuningCode2
Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual SettingsCode0
ThinkPatterns-21k: A Systematic Study on the Impact of Thinking Patterns in LLMs—0
Can Language Models Follow Multiple Turns of Entangled Instructions?Code1
ICCO: Learning an Instruction-conditioned Coordinator for Language-guided Task-aligned Multi-robot Control—0
D3: Diversity, Difficulty, and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning—0
ASMA-Tune: Unlocking LLMs' Assembly Code Comprehension via Structural-Semantic Instruction TuningCode0
Compositional Subspace Representation Fine-tuning for Adaptive Large Language Models—0
Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding—0
Got Compute, but No Data: Lessons From Post-training a Finnish LLM—0
DAFE: LLM-Based Evaluation Through Dynamic Arbitration for Free-Form Question-Answering—0
Open-World Skill Discovery from Unsegmented Demonstrations—0
Robust Multi-Objective Controlled Decoding of Large Language ModelsCode0
Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation ModelCode2
XIFBench: Evaluating Large Language Models on Multilingual Instruction Following—0
DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMsCode2
REF-VLM: Triplet-Based Referring Paradigm for Unified Visual DecodingCode1
Dr Genre: Reinforcement Learning from Decoupled LLM Feedback for Generic Text Rewriting—0
WildIFEval: Instruction Following in the WildCode0
RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMsCode2
S2S-Arena, Evaluating Speech2Speech Protocols on Instruction Following with Paralinguistic Information—0
Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference AlignmentCode0
FuseChat-3.0: Preference Optimization Meets Heterogeneous Model FusionCode1
IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information Retrieval—0
CodeIF-Bench: Evaluating Instruction-Following Capabilities of Large Language Models in Interactive Code Generation—0
LEWIS (LayEr WIse Sparsity) -- A Training Free Guided Model Merging Approach—0
Attentive Reasoning Queries: A Systematic Method for Optimizing Instruction-Following in Large Language ModelsCode11
Unified Mind Model: Reimagining Autonomous Agents in the LLM Era—0
Robust Learning of Diverse Code Edits—0
Iterative Value Function Optimization for Guided Decoding—0
InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-training—0
CrowdSelect: Synthetic Instruction Data Selection with Multi-LLM WisdomCode1
In-context Learning vs. Instruction Tuning: The Case of Small and Multilingual Language Models—0
Re-Imagining Multimodal Instruction Tuning: A Representation ViewCode0
Triple Phase Transitions: Understanding the Learning Dynamics of Large Language Models from a Neuroscience Perspective—0
Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge—0
DataMan: Data Manager for Pre-training Large Language Models—0
Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward SystemsCode2
Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models—0
Ground-level Viewpoint Vision-and-Language Navigation in Continuous Environments—0
CodeIF: Benchmarking the Instruction-Following Capabilities of Large Language Models for Code GenerationCode1
Show:102550
← PrevPage 4 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