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 1111–1120 of 1135 papers

TitleStatusHype
Language-Conditioned Goal Generation: a New Approach to Language Grounding for RL—0
Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Text—0
Language Conditioned Imitation Learning over Unstructured Data—0
Following Instructions by Imagining and Reaching Visual Goals—0
Automated curriculum generation for Policy Gradients from DemonstrationsCode0
Language-guided Semantic Mapping and Mobile Manipulation in Partially Observable Environments—0
HIGhER : Improving instruction following with Hindsight Generation for Experience Replay—0
Robust Instruction-Following in a Situated Agent via Transfer-Learning from Text—0
Self-Educated Language Agent with Hindsight Experience Replay for Instruction Following—0
Guided Adaptive Credit Assignment for Sample Efficient Policy Optimization—0
Show:102550
← PrevPage 112 of 114Next →

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