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 501–550 of 1135 papers

TitleStatusHype
1.5-Pints Technical Report: Pretraining in Days, Not Months -- Your Language Model Thrives on Quality DataCode3
Extend Model Merging from Fine-Tuned to Pre-Trained Large Language Models via Weight DisentanglementCode1
A Framework for Fine-Tuning LLMs using Heterogeneous Feedback—0
Semantic Skill Grounding for Embodied Instruction-Following in Cross-Domain Environments—0
Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language ModelsCode0
Autonomous Improvement of Instruction Following Skills via Foundation ModelsCode2
SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian LanguagesCode2
SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain—0
ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic EnvironmentsCode1
Efficient Inference of Vision Instruction-Following Models with Elastic CacheCode1
HAPFI: History-Aware Planning based on Fused Information—0
PrimeGuard: Safe and Helpful LLMs through Tuning-Free RoutingCode0
Failures to Find Transferable Image Jailbreaks Between Vision-Language Models—0
DISCO: Embodied Navigation and Interaction via Differentiable Scene Semantics and Dual-level ControlCode1
ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities—0
EarthMarker: A Visual Prompting Multi-modal Large Language Model for Remote SensingCode1
NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language ModelsCode3
SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic FinetuningCode1
Situated Instruction Following—0
Qwen2-Audio Technical ReportCode7
Empowering Persian LLMs for Instruction Following: A Novel Dataset and Training ApproachCode0
Instruction Following with Goal-Conditioned Reinforcement Learning in Virtual EnvironmentsCode0
Beyond Instruction Following: Evaluating Inferential Rule Following of Large Language Models—0
LIONs: An Empirically Optimized Approach to Align Language ModelsCode1
LVLM-empowered Multi-modal Representation Learning for Visual Place Recognition—0
From Loops to Oops: Fallback Behaviors of Language Models Under UncertaintyCode0
Large Language Model as an Assignment Evaluator: Insights, Feedback, and Challenges in a 1000+ Student Course—0
MMSci: A Dataset for Graduate-Level Multi-Discipline Multimodal Scientific UnderstandingCode2
Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMsCode1
Semantic Graphs for Syntactic Simplification: A Revisit from the Age of LLMCode0
Benchmarking Complex Instruction-Following with Multiple Constraints CompositionCode2
FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMsCode11
Diverse and Fine-Grained Instruction-Following Ability Exploration with Synthetic Data—0
Pelican: Correcting Hallucination in Vision-LLMs via Claim Decomposition and Program of Thought Verification—0
D-Rax: Domain-specific Radiologic assistant leveraging multi-modal data and eXpert model predictions—0
MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMsCode1
Improving Multilingual Instruction Finetuning via Linguistically Natural and Diverse Datasets—0
Iterative Data Generation with Large Language Models for Aspect-based Sentiment Analysis—0
The SIFo Benchmark: Investigating the Sequential Instruction Following Ability of Large Language ModelsCode1
ScaleBiO: Scalable Bilevel Optimization for LLM Data Reweighting—0
MM-Instruct: Generated Visual Instructions for Large Multimodal Model AlignmentCode1
OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents—0
LiveBench: A Challenging, Contamination-Limited LLM BenchmarkCode5
DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment—0
Suri: Multi-constraint Instruction Following for Long-form Text GenerationCode1
Role-Play Zero-Shot Prompting with Large Language Models for Open-Domain Human-Machine Conversation—0
A Text is Worth Several Tokens: Text Embedding from LLMs Secretly Aligns Well with The Key Tokens—0
Following Length Constraints in Instructions—0
Dual-Space Knowledge Distillation for Large Language ModelsCode2
AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language ModelsCode1
Show:102550
← PrevPage 11 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