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 826–850 of 1135 papers

TitleStatusHype
Releasing the CRaQAn (Coreference Resolution in Question-Answering): An open-source dataset and dataset creation methodology using instruction-following models—0
MoDS: Model-oriented Data Selection for Instruction TuningCode1
Towards Vision Enhancing LLMs: Empowering Multimodal Knowledge Storage and Sharing in LLMs—0
GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation—0
GeoChat: Grounded Large Vision-Language Model for Remote SensingCode2
CoachLM: Automatic Instruction Revisions Improve the Data Quality in LLM Instruction TuningCode1
Towards Improving Document Understanding: An Exploration on Text-Grounding via MLLMsCode1
HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction DataCode1
LIMIT: Less Is More for Instruction Tuning Across Evaluation Paradigms—0
Data Diversity Matters for Robust Instruction Tuning—0
RecExplainer: Aligning Large Language Models for Explaining Recommendation Models—0
Traffic Sign Interpretation in Real Road Scene—0
WatME: Towards Lossless Watermarking Through Lexical Redundancy—0
Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination—0
DocLens: Multi-aspect Fine-grained Evaluation for Medical Text GenerationCode1
FollowEval: A Multi-Dimensional Benchmark for Assessing the Instruction-Following Capability of Large Language Models—0
How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their VulnerabilitiesCode0
Can Query Expansion Improve Generalization of Strong Cross-Encoder Rankers?—0
PLUG: Leveraging Pivot Language in Cross-Lingual Instruction TuningCode1
Defending Large Language Models Against Jailbreaking Attacks Through Goal PrioritizationCode1
MAP's not dead yet: Uncovering true language model modes by conditioning away degeneracy—0
Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable SummarizationCode1
Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language ModelsCode3
How You Prompt Matters! Even Task-Oriented Constraints in Instructions Affect LLM-Generated Text DetectionCode0
Self-Evolved Diverse Data Sampling for Efficient Instruction TuningCode1
Show:102550
← PrevPage 34 of 46Next →

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