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 401–425 of 1135 papers

TitleStatusHype
Large Language Models as Evaluators for Recommendation ExplanationsCode1
Contrastive Vision-Language Alignment Makes Efficient Instruction LearnerCode1
Language-Conditioned Reinforcement Learning to Solve Misunderstandings with Action CorrectionsCode1
RuleRAG: Rule-guided retrieval-augmented generation with language models for question answeringCode1
Language Imbalance Driven Rewarding for Multilingual Self-improvingCode1
CoPESD: A Multi-Level Surgical Motion Dataset for Training Large Vision-Language Models to Co-Pilot Endoscopic Submucosal DissectionCode1
Answer is All You Need: Instruction-following Text Embedding via Answering the QuestionCode1
Lana: A Language-Capable Navigator for Instruction Following and GenerationCode1
Kun: Answer Polishment for Chinese Self-Alignment with Instruction Back-TranslationCode1
An In-depth Look at Gemini's Language AbilitiesCode1
Bridging and Modeling Correlations in Pairwise Data for Direct Preference OptimizationCode1
Don't Reinvent the Wheel: Efficient Instruction-Following Text Embedding based on Guided Space TransformationCode1
IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code GeneratorsCode1
Is In-Context Learning Sufficient for Instruction Following in LLMs?Code1
InsViE-1M: Effective Instruction-based Video Editing with Elaborate Dataset ConstructionCode1
Inferring Rewards from Language in ContextCode1
BotChat: Evaluating LLMs' Capabilities of Having Multi-Turn DialoguesCode1
Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play ApproachCode1
Do LLMs "know" internally when they follow instructions?Code1
Creative Agents: Empowering Agents with Imagination for Creative TasksCode1
A Dual-Space Framework for General Knowledge Distillation of Large Language ModelsCode1
InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech SystemsCode1
Investigating Instruction Tuning Large Language Models on GraphsCode1
Jatmo: Prompt Injection Defense by Task-Specific FinetuningCode1
Instruction Position Matters in Sequence Generation with Large Language ModelsCode1
Show:102550
← PrevPage 17 of 46Next →

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