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 721–730 of 1135 papers

TitleStatusHype
Long-Context Language Modeling with Parallel Context EncodingCode2
Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding—0
Defending Large Language Models against Jailbreak Attacks via Semantic SmoothingCode1
GraphWiz: An Instruction-Following Language Model for Graph ProblemsCode2
NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation—0
On the Multi-turn Instruction Following for Conversational Web AgentsCode1
Unintended Impacts of LLM Alignment on Global RepresentationCode0
INSTRUCTIR: A Benchmark for Instruction Following of Information Retrieval ModelsCode1
Towards Robust Instruction Tuning on Multimodal Large Language ModelsCode0
Zero-shot cross-lingual transfer in instruction tuning of large language models—0
Show:102550
← PrevPage 73 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