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 301–325 of 1135 papers

TitleStatusHype
BLEUBERI: BLEU is a surprisingly effective reward for instruction followingCode1
LIONs: An Empirically Optimized Approach to Align Language ModelsCode1
AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source DataCode1
Lexicon Learning for Few Shot Sequence ModelingCode1
Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New LanguagesCode1
Lexicon Learning for Few-Shot Neural Sequence ModelingCode1
Ex3: Automatic Novel Writing by Extracting, Excelsior and ExpandingCode1
Learning to Map Natural Language Instructions to Physical Quadcopter Control using Simulated FlightCode1
AceGPT, Localizing Large Language Models in ArabicCode1
ChatGPT may Pass the Bar Exam soon, but has a Long Way to Go for the LexGLUE benchmarkCode1
EventHallusion: Diagnosing Event Hallucinations in Video LLMsCode1
LLaSA: A Multimodal LLM for Human Activity Analysis Through Wearable and Smartphone SensorsCode1
Language Imbalance Driven Rewarding for Multilingual Self-improvingCode1
FaithScore: Fine-grained Evaluations of Hallucinations in Large Vision-Language ModelsCode1
ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat TemplatesCode1
Language-Conditioned Reinforcement Learning to Solve Misunderstandings with Action CorrectionsCode1
Evaluating LLMs at Detecting Errors in LLM ResponsesCode1
Evaluating Large Language Models at Evaluating Instruction FollowingCode1
AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic ScenariosCode1
Evaluating Correctness and Faithfulness of Instruction-Following Models for Question AnsweringCode1
Lana: A Language-Capable Navigator for Instruction Following and GenerationCode1
Jatmo: Prompt Injection Defense by Task-Specific FinetuningCode1
ChartInstruct: Instruction Tuning for Chart Comprehension and ReasoningCode1
Agri-LLaVA: Knowledge-Infused Large Multimodal Assistant on Agricultural Pests and DiseasesCode1
KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language ModelsCode1
Show:102550
← PrevPage 13 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