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 681–690 of 1135 papers

TitleStatusHype
Neural Semantic Parsing—0
Nevermind: Instruction Override and Moderation in Large Language Models—0
Zero-shot Object-Centric Instruction Following: Integrating Foundation Models with Traditional Navigation—0
Triple Phase Transitions: Understanding the Learning Dynamics of Large Language Models from a Neuroscience Perspective—0
TS-Align: A Teacher-Student Collaborative Framework for Scalable Iterative Finetuning of Large Language Models—0
Nudging: Inference-time Alignment of LLMs via Guided Decoding—0
BLSP-KD: Bootstrapping Language-Speech Pre-training via Knowledge Distillation—0
TuneShield: Mitigating Toxicity in Conversational AI while Fine-tuning on Untrusted Data—0
OmniGeo: Towards a Multimodal Large Language Models for Geospatial Artificial Intelligence—0
OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents—0
Show:102550
← PrevPage 69 of 114Next →

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