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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 491–500 of 1135 papers

Title	Date	Tasks	Status	Score
HalLoc: Token-level Localization of Hallucinations for Vision Language Models	Jun 12, 2025	HallucinationImage Captioning	CodeCode Available	5
Guiding Policies with Language via Meta-Learning	Nov 19, 2018	Imitation LearningInstruction Following	CodeCode Available	5
Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language Models	Jul 31, 2024	Instruction FollowingMulti-Task Learning	CodeCode Available	5
On the Loss of Context-awareness in General Instruction Fine-tuning	Nov 5, 2024	BenchmarkingInstruction Following	CodeCode Available	5
Aligning Large Language Models by On-Policy Self-Judgment	Feb 17, 2024	Instruction Following	CodeCode Available	5
CORDIAL: Can Multimodal Large Language Models Effectively Understand Coherence Relationships?	Feb 16, 2025	Instruction Following	CodeCode Available	5
Grade Score: Quantifying LLM Performance in Option Selection	Jun 17, 2024	Decision MakingFairness	CodeCode Available	5
MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training	Feb 17, 2025	Instruction Following	CodeCode Available	5
GoalNet: Inferring Conjunctive Goal Predicates from Human Plan Demonstrations for Robot Instruction Following	May 14, 2022	Decision MakingInstruction Following	CodeCode Available	5
Automated curriculum generation for Policy Gradients from Demonstrations	Dec 1, 2019	Instruction Following	CodeCode Available	5

Show:10 25 50

← PrevPage 50 of 114Next →

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	AutoIF (Llama3 70B)	Inst-level loose-accuracy	90.4	—	Unverified
2	AutoIF (Qwen2 72B)	Inst-level loose-accuracy	88	—	Unverified
3	GPT-4	Inst-level loose-accuracy	85.37	—	Unverified
4	PaLM 2 S	Inst-level loose-accuracy	59.11	—	Unverified