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 976–1000 of 1135 papers

TitleStatusHype
ThinkBot: Embodied Instruction Following with Thought Chain Reasoning—0
InstructAny2Pix: Flexible Visual Editing via Multimodal Instruction FollowingCode0
Aligner: One Global Token is Worth Millions of Parameters When Aligning Large Language Models—0
Localized Symbolic Knowledge Distillation for Visual Commonsense ModelsCode0
Text as Image: Learning Transferable Adapter for Multi-Label Classification—0
MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Following—0
InstructBooth: Instruction-following Personalized Text-to-Image Generation—0
MedXChat: A Unified Multimodal Large Language Model Framework towards CXRs Understanding and Generation—0
FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, ToxicityCode0
Towards Vision Enhancing LLMs: Empowering Multimodal Knowledge Storage and Sharing in LLMs—0
Releasing the CRaQAn (Coreference Resolution in Question-Answering): An open-source dataset and dataset creation methodology using instruction-following models—0
GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation—0
LIMIT: Less Is More for Instruction Tuning Across Evaluation Paradigms—0
Data Diversity Matters for Robust Instruction Tuning—0
RecExplainer: Aligning Large Language Models for Explaining Recommendation Models—0
Traffic Sign Interpretation in Real Road Scene—0
FollowEval: A Multi-Dimensional Benchmark for Assessing the Instruction-Following Capability of Large Language Models—0
Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination—0
WatME: Towards Lossless Watermarking Through Lexical Redundancy—0
MAP's not dead yet: Uncovering true language model modes by conditioning away degeneracy—0
Can Query Expansion Improve Generalization of Strong Cross-Encoder Rankers?—0
How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their VulnerabilitiesCode0
How You Prompt Matters! Even Task-Oriented Constraints in Instructions Affect LLM-Generated Text DetectionCode0
Generalization Analogies: A Testbed for Generalizing AI Oversight to Hard-To-Measure DomainsCode0
MART: Improving LLM Safety with Multi-round Automatic Red-Teaming—0
Show:102550
← PrevPage 40 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