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 951–975 of 1135 papers

TitleStatusHype
Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative InstructionsCode2
Zhongjing: Enhancing the Chinese Medical Capabilities of Large Language Model through Expert Feedback and Real-world Multi-turn DialogueCode2
AgentBench: Evaluating LLMs as AgentsCode4
Toward Zero-Shot Instruction FollowingCode0
Evaluating Correctness and Faithfulness of Instruction-Following Models for Question AnsweringCode1
ETHER: Aligning Emergent Communication for Hindsight Experience Replay—0
L-Eval: Instituting Standardized Evaluation for Long Context Language ModelsCode6
Instruction-following Evaluation through Verbalizer Manipulation—0
FLASK: Fine-grained Language Model Evaluation based on Alignment Skill SetsCode2
LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?—0
ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction Tuning—0
AlpaGasus: Training A Better Alpaca with Fewer DataCode1
BuboGPT: Enabling Visual Grounding in Multi-Modal LLMsCode2
Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical StudyCode1
Exploring the Integration of Large Language Models into Automatic Speech Recognition Systems: An Empirical Study—0
MMBench: Is Your Multi-modal Model an All-around Player?Code5
Instruction Mining: Instruction Data Selection for Tuning Large Language Models—0
Opening up ChatGPT: Tracking openness, transparency, and accountability in instruction-tuned text generatorsCode1
Becoming self-instruct: introducing early stopping criteria for minimal instruct tuning—0
What Matters in Training a GPT4-Style Language Model with Multimodal Inputs?Code2
Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language ModelsCode1
Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Control—0
KITE: Keypoint-Conditioned Policies for Semantic Manipulation—0
LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image UnderstandingCode2
On the Exploitability of Instruction TuningCode1
Show:102550
← PrevPage 39 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