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 426–450 of 1135 papers

TitleStatusHype
Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction FollowingCode1
BotChat: Evaluating LLMs' Capabilities of Having Multi-Turn DialoguesCode1
Do LLMs "know" internally when they follow instructions?Code1
A Dual-Space Framework for General Knowledge Distillation of Large Language ModelsCode1
An Emulator for Fine-Tuning Large Language Models using Small Language ModelsCode1
Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical StudyCode1
Bactrian-X: Multilingual Replicable Instruction-Following Models with Low-Rank AdaptationCode1
PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt TuningCode1
ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language TuningCode1
Diversify and Conquer: Diversity-Centric Data Selection with Iterative RefinementCode1
IDA-Bench: Evaluating LLMs on Interactive Guided Data AnalysisCode1
Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy InstructionsCode1
IHEval: Evaluating Language Models on Following the Instruction HierarchyCode1
Infer Human's Intentions Before Following Natural Language InstructionsCode1
Curiosity-Driven Reinforcement Learning from Human FeedbackCode1
ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic EnvironmentsCode1
"No, to the Right" -- Online Language Corrections for Robotic Manipulation via Shared AutonomyCode1
RES-Q: Evaluating Code-Editing Large Language Model Systems at the Repository ScaleCode1
STRICT: Stress Test of Rendering Images Containing TextCode1
OmniGenBench: A Benchmark for Omnipotent Multimodal Generation across 50+ TasksCode1
Online Continual Learning For Interactive Instruction Following AgentsCode1
Preference-Guided Reflective Sampling for Aligning Language ModelsCode0
Beyond Content Relevance: Evaluating Instruction Following in Retrieval ModelsCode0
Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax ReductionCode0
Analysis of Language Change in Collaborative Instruction FollowingCode0
Show:102550
← PrevPage 18 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