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 901–950 of 1135 papers

TitleStatusHype
Fool Your (Vision and) Language Model With Embarrassingly Simple PermutationsCode1
PACIT: Unlocking the Power of Examples for Better In-Context Instruction TuningCode0
Back to the Future: Towards Explainable Temporal Reasoning with Large Language ModelsCode1
Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context LearningCode1
Reformulating Vision-Language Foundation Models and Datasets Towards Universal Multimodal AssistantsCode2
SLM: Bridge the thin gap between speech and text foundation models—0
From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction TuningCode1
Self-Specialization: Uncovering Latent Expertise within Large Language Models—0
ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular QuantizersCode2
MentaLLaMA: Interpretable Mental Health Analysis on Social Media with Large Language ModelsCode2
Towards LLM-guided Causal Explainability for Black-box Text Classifiers—0
Frustrated with Code Quality Issues? LLMs can Help!—0
AceGPT, Localizing Large Language Models in ArabicCode1
LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation DatasetCode7
LongLoRA: Efficient Fine-tuning of Long-Context Large Language ModelsCode6
Natural Language Embedded Programs for Hybrid Language Symbolic ReasoningCode1
Instruction-Following Speech Recognition—0
Monolingual or Multilingual Instruction Tuning: Which Makes a Better AlpacaCode0
Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference—0
TextBind: Multi-turn Interleaved Multimodal Instruction-following in the WildCode1
DoG-Instruct: Towards Premium Instruction-Tuning Data via Text-Grounded Instruction WrappingCode0
Quantifying and Attributing the Hallucination of Large Language Models via Association Analysis—0
Efficient Finetuning Large Language Models For Vietnamese Chatbot—0
ImageBind-LLM: Multi-modality Instruction TuningCode5
Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty—0
Are Emergent Abilities in Large Language Models just In-Context Learning?Code1
Self-driven Grounding: Large Language Model Agents with Automatical Language-aligned Skill Learning—0
Language-Conditioned Change-point Detection to Identify Sub-Tasks in Robotics DomainsCode0
FactLLaMA: Optimizing Instruction-Following Language Models with External Knowledge for Automated Fact-Checking—0
Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction FollowingCode2
Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following ModelsCode1
LLaSM: Large Language and Speech ModelCode2
Evaluating the Robustness to Instructions of Large Language Models—0
Empowering Cross-lingual Abilities of Instruction-tuned Large Language Models by Translation-following demonstrationsCode0
MedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records—0
Code Llama: Open Foundation Models for CodeCode6
Improving Translation Faithfulness of Large Language Models via Augmenting InstructionsCode1
Instruction Position Matters in Sequence Generation with Large Language ModelsCode1
From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction TuningCode2
InstructionGPT-4: A 200-Instruction Paradigm for Fine-Tuning MiniGPT-4Code1
UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding—0
PUMGPT: A Large Vision-Language Model for Product Understanding—0
Multi-Level Compositional Reasoning for Interactive Instruction FollowingCode0
Evaluating the Instruction-Following Robustness of Large Language Models to Prompt InjectionCode0
EcomGPT: Instruction-tuning Large Language Models with Chain-of-Task Tasks for E-commerceCode2
#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language ModelsCode2
Context-Aware Planning and Environment-Aware Memory for Instruction Following Embodied AgentsCode1
VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World UseCode1
Self-Alignment with Instruction BacktranslationCode1
LLaMA-E: Empowering E-commerce Authoring with Object-Interleaved Instruction Following—0
Show:102550
← PrevPage 19 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