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 351–375 of 1135 papers

TitleStatusHype
On the Loss of Context-awareness in General Instruction Fine-tuningCode0
Rate, Explain and Cite (REC): Enhanced Explanation and Attribution in Automatic Evaluation by Large Language ModelsCode0
Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors—0
TypeScore: A Text Fidelity Metric for Text-to-Image Generative Models—0
LLaMo: Large Language Model-based Molecular Graph AssistantCode1
Beyond Content Relevance: Evaluating Instruction Following in Retrieval ModelsCode0
Constraint Back-translation Improves Complex Instruction Following of Large Language ModelsCode1
MDCure: A Scalable Pipeline for Multi-Document Instruction-FollowingCode0
FALCON: Feedback-driven Adaptive Long/short-term memory reinforced Coding Optimization systemCode0
UFT: Unifying Fine-Tuning of SFT and RLHF/DPO/UNA through a Generalized Implicit Reward Function—0
SWITCH: Studying with Teacher for Knowledge Distillation of Large Language Models—0
Open6DOR: Benchmarking Open-instruction 6-DoF Object Rearrangement and A VLM-based ApproachCode2
BioMistral-NLU: Towards More Generalizable Medical Language Understanding through Instruction Tuning—0
DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate HallucinationsCode1
Unbounded: A Generative Infinite Game of Character Life Simulation—0
Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks—0
Cross-model Control: Improving Multiple Large Language Models in One-time TrainingCode1
Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language ModelsCode2
Cross-lingual Transfer of Reward Models in Multilingual AlignmentCode0
SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains—0
ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language TuningCode1
Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions FollowingCode2
GATEAU: Selecting Influential Samples for Long Context AlignmentCode1
Griffon-G: Bridging Vision-Language and Vision-Centric Tasks via Large Multimodal Models—0
Large Language Models for Autonomous Driving (LLM4AD): Concept, Benchmark, Experiments, and Challenges—0
Show:102550
← PrevPage 15 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