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
Extend Model Merging from Fine-Tuned to Pre-Trained Large Language Models via Weight DisentanglementCode1
Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New LanguagesCode1
Lana: A Language-Capable Navigator for Instruction Following and GenerationCode1
IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code GeneratorsCode1
InfMLLM: A Unified Framework for Visual-Language TasksCode1
Agri-LLaVA: Knowledge-Infused Large Multimodal Assistant on Agricultural Pests and DiseasesCode1
Ex3: Automatic Novel Writing by Extracting, Excelsior and ExpandingCode1
Incentivizing Reasoning for Advanced Instruction-Following of Large Language ModelsCode1
EventHallusion: Diagnosing Event Hallucinations in Video LLMsCode1
Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction FollowingCode1
InstructionGPT-4: A 200-Instruction Paradigm for Fine-Tuning MiniGPT-4Code1
Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language ModelsCode1
On the Exploitability of Instruction TuningCode1
PathAsst: A Generative Foundation AI Assistant Towards Artificial General Intelligence of PathologyCode1
Factorizing Perception and Policy for Interactive Instruction FollowingCode1
IHEval: Evaluating Language Models on Following the Instruction HierarchyCode1
ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat TemplatesCode1
MM-Skin: Enhancing Dermatology Vision-Language Model with an Image-Text Dataset Derived from TextbooksCode1
MoDS: Model-oriented Data Selection for Instruction TuningCode1
Evaluating LLMs at Detecting Errors in LLM ResponsesCode1
ChatGPT may Pass the Bar Exam soon, but has a Long Way to Go for the LexGLUE benchmarkCode1
AceGPT, Localizing Large Language Models in ArabicCode1
Evaluating Large Language Models at Evaluating Instruction FollowingCode1
AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic ScenariosCode1
Infer Human's Intentions Before Following Natural Language InstructionsCode1
Inferring Rewards from Language in ContextCode1
Evaluating Correctness and Faithfulness of Instruction-Following Models for Question AnsweringCode1
IDA-Bench: Evaluating LLMs on Interactive Guided Data AnalysisCode1
MM-CamObj: A Comprehensive Multimodal Dataset for Camouflaged Object ScenariosCode1
Instruct and Extract: Instruction Tuning for On-Demand Information ExtractionCode1
ChartInstruct: Instruction Tuning for Chart Comprehension and ReasoningCode1
MMIDR: Teaching Large Language Model to Interpret Multimodal Misinformation via Knowledge DistillationCode1
DocLens: Multi-aspect Fine-grained Evaluation for Medical Text GenerationCode1
Facial Affective Behavior Analysis with Instruction TuningCode1
Enhancing Cross-Tokenizer Knowledge Distillation with Contextual Dynamical MappingCode1
AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source DataCode1
FaithScore: Fine-grained Evaluations of Hallucinations in Large Vision-Language ModelsCode1
Investigating Instruction Tuning Large Language Models on GraphsCode1
CB2: Collaborative Natural Language Interaction Research PlatformCode1
Instruction Position Matters in Sequence Generation with Large Language ModelsCode1
Hybrid Alignment Training for Large Language ModelsCode1
Instruction-Tuning Data Synthesis from Scratch via Web ReconstructionCode1
Few-shot Object Grounding and Mapping for Natural Language Robot Instruction FollowingCode1
Alexa Arena: A User-Centric Interactive Platform for Embodied AICode1
FILM: Following Instructions in Language with Modular MethodsCode1
Finding Blind Spots in Evaluator LLMs with Interpretable ChecklistsCode1
MM-Instruct: Generated Visual Instructions for Large Multimodal Model AlignmentCode1
Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play ApproachCode1
InsViE-1M: Effective Instruction-based Video Editing with Elaborate Dataset ConstructionCode1
Monte Carlo Thought Search: Large Language Model Querying for Complex Scientific Reasoning in Catalyst DesignCode1
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