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 726–750 of 1135 papers

TitleStatusHype
SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understanding—0
Improving Instruction-Following in Language Models through Activation Steering—0
Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling—0
ForgeryGPT: Multimodal Large Language Model For Explainable Image Forgery Detection and Localization—0
DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model—0
Optimizing Instruction Synthesis: Effective Exploration of Evolutionary Space with Tree Search—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
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
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
Evolutionary Contrastive Distillation for Language Model Alignment—0
Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy—0
LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints—0
Self-Boosting Large Language Models with Synthetic Preference Data—0
HERM: Benchmarking and Enhancing Multimodal LLMs for Human-Centric Understanding—0
Large Language Model Compression with Neural Architecture Search—0
ReIFE: Re-evaluating Instruction-Following EvaluationCode0
Direct Preference Optimization for LLM-Enhanced Recommendation Systems—0
Multimodal Situational Safety—0
TOWER: Tree Organized Weighting for Evaluating Complex Instructions—0
Only-IF:Revealing the Decisive Effect of Instruction Diversity on Generalization—0
Show:102550
← PrevPage 30 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