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 376–400 of 1135 papers

TitleStatusHype
LLaVA-Ultra: Large Chinese Language and Vision Assistant for Ultrasound—0
LoGU: Long-form Generation with Uncertainty ExpressionsCode1
Do LLMs "know" internally when they follow instructions?Code1
Do LLMs estimate uncertainty well in instruction-following?Code0
Boosting LLM Translation Skills without General Ability Loss via Rationale Distillation—0
LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-TuningCode0
POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference OptimizationCode0
Meta-Chunking: Learning Text Segmentation and Semantic Completion via Logical PerceptionCode3
Evaluating the Instruction-following Abilities of Language Models using Knowledge TasksCode0
RuleRAG: Rule-guided retrieval-augmented generation with language models for question answeringCode1
Improving Instruction-Following in Language Models through Activation Steering—0
Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling—0
SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understanding—0
Balancing Continuous Pre-Training and Instruction Fine-Tuning: Optimizing Instruction-Following in LLMs—0
How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning PerspectiveCode0
ForgeryGPT: Multimodal Large Language Model For Explainable Image Forgery Detection and Localization—0
Optimizing Instruction Synthesis: Effective Exploration of Evolutionary Space with Tree Search—0
DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model—0
Thinking LLMs: General Instruction Following with Thought Generation—0
Conversational Code Generation: a Case Study of Designing a Dialogue System for Generating Driving Scenarios for Testing Autonomous Vehicles—0
Surgical-LLaVA: Toward Surgical Scenario Understanding via Large Language and Vision Models—0
Toward General Instruction-Following Alignment for Retrieval-Augmented GenerationCode2
Are You Human? An Adversarial Benchmark to Expose LLMs—0
SeRA: Self-Reviewing and Alignment of Large Language Models using Implicit Reward Margins—0
Nudging: Inference-time Alignment of LLMs via Guided Decoding—0
Show:102550
← PrevPage 16 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