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 251–300 of 1135 papers

TitleStatusHype
Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models—0
MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMsCode2
Critique Fine-Tuning: Learning to Critique is More Effective than Learning to ImitateCode2
Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model ScalingCode11
3D-MoE: A Mixture-of-Experts Multi-modal LLM for 3D Vision and Pose Diffusion via Rectified Flow—0
How well can LLMs Grade Essays in Arabic?—0
Advancing Mathematical Reasoning in Language Models: The Impact of Problem-Solving Data, Data Synthesis Methods, and Training Stages—0
The Breeze 2 Herd of Models: Traditional Chinese LLMs Based on Llama with Vision-Aware and Function-Calling CapabilitiesCode3
Online Preference Alignment for Language Models via Count-based ExplorationCode1
Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual FeedbackCode2
Compositional Instruction Following with Language Models and Reinforcement Learning—0
VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language ModelCode3
InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward ModelCode0
Curiosity-Driven Reinforcement Learning from Human FeedbackCode1
BAP v2: An Enhanced Task Framework for Instruction Following in Minecraft Dialogues—0
Zero-shot and Few-shot Learning with Instruction-following LLMs for Claim Matching in Automated Fact-checking—0
DNA 1.0 Technical Report—0
A Multi-Modal AI Copilot for Single-Cell Analysis with Instruction FollowingCode1
Iterative Label Refinement Matters More than Preference Optimization under Weak SupervisionCode0
Facial Dynamics in Video: Instruction Tuning for Improved Facial Expression Perception and Contextual AwarenessCode1
Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model—0
A Comprehensive Evaluation of Large Language Models on Mental Illnesses in Arabic Context—0
MinMo: A Multimodal Large Language Model for Seamless Voice Interaction—0
Scalable Vision Language Model Training via High Quality Data Curation—0
Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models—0
Demystifying Domain-adaptive Post-training for Financial LLMsCode1
LongViTU: Instruction Tuning for Long-Form Video Understanding—0
Language and Planning in Robotic Navigation: A Multilingual Evaluation of State-of-the-Art Models—0
DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization—0
Instruction-Following Pruning for Large Language Models—0
ProgCo: Program Helps Self-Correction of Large Language ModelsCode0
Towards Interactive Deepfake AnalysisCode0
SLADE: Shielding against Dual Exploits in Large Vision-Language Models—0
HSI-GPT: A General-Purpose Large Scene-Motion-Language Model for Human Scene Interaction—0
MIMO: A Medical Vision Language Model with Visual Referring Multimodal Input and Pixel Grounding Multimodal OutputCode0
TinyHelen's First Curriculum: Training and Evaluating Tiny Language Models in a Simpler Language EnvironmentCode1
Hindsight Planner: A Closed-Loop Few-Shot Planner for Embodied Instruction Following—0
Find the Intention of Instruction: Comprehensive Evaluation of Instruction Understanding for Large Language ModelsCode0
Internalized Self-Correction for Large Language Models—0
LearnLM: Improving Gemini for Learning—0
Align Anything: Training All-Modality Models to Follow Instructions with Language FeedbackCode7
HREF: Human Response-Guided Evaluation of Instruction Following in Language ModelsCode0
Length Controlled Generation for Black-box LLMs—0
Qwen2.5 Technical ReportCode13
Systematic Evaluation of Long-Context LLMs on Financial Concepts—0
A Systematic Examination of Preference Learning through the Lens of Instruction-Following—0
MetaMorph: Multimodal Understanding and Generation via Instruction Tuning—0
Pipeline Analysis for Developing Instruct LLMs in Low-Resource Languages: A Case Study on Basque—0
Question: How do Large Language Models perform on the Question Answering tasks? Answer:—0
LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-SteeringCode0
Show:102550
← PrevPage 6 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