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 1091–1100 of 1135 papers

TitleStatusHype
Compositional Data and Task Augmentation for Instruction Following—0
Improving the Robustness to Variations of Objects and Instructions with a Neuro-Symbolic Approach for Interactive Instruction Following—0
Hierarchical Modular Framework for Long Horizon Instruction FollowingCode0
Procedures as Programs: Hierarchical Control of Situated Agents through Natural Language—0
Analysis of Language Change in Collaborative Instruction FollowingCode0
Modular Framework for Visuomotor Language Grounding—0
Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning—0
Draw Me a Flower: Processing and Grounding Abstraction in Natural Language—0
Zero-shot Task Adaptation using Natural Language—0
Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following TasksCode0
Show:102550
← PrevPage 110 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