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 1081–1090 of 1135 papers

TitleStatusHype
Don't Copy the Teacher: Data and Model Challenges in Embodied DialogueCode0
A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning—0
Iterative Vision-and-Language Navigation—0
Language Models are General-Purpose Interfaces—0
GoalNet: Inferring Conjunctive Goal Predicates from Human Plan Demonstrations for Robot Instruction FollowingCode0
Summarizing a virtual robot's past actions in natural language—0
Compositionality as Lexical SymmetryCode0
Less is More: Generating Grounded Navigation Instructions from Landmarks—0
Explicit Object Relation Alignment for Vision and Language Navigation—0
Skill Induction and Planning with Latent Language—0
Show:102550
← PrevPage 109 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