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 551–600 of 1135 papers

TitleStatusHype
AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language ModelsCode1
Evaluation of Instruction-Following Ability for Large Language Models on Story-Ending Generation—0
Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMsCode1
AudioBench: A Universal Benchmark for Audio Large Language ModelsCode3
RuleR: Improving LLM Controllability by Rule-based Data RecyclingCode1
Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization—0
DEM: Distribution Edited Model for Training with Mixed Data Distributions—0
Hybrid Alignment Training for Large Language ModelsCode1
AdaGrad under Anisotropic Smoothness—0
VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of Thought—0
LLaSA: A Multimodal LLM for Human Activity Analysis Through Wearable and Smartphone SensorsCode1
IWISDM: Assessing instruction following in multimodal models at scaleCode0
Finding Blind Spots in Evaluator LLMs with Interpretable ChecklistsCode1
Biomedical Visual Instruction Tuning with Clinician Preference AlignmentCode0
Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language ModelsCode3
The Comparative Trap: Pairwise Comparisons Amplifies Biased Preferences of LLM Evaluators—0
Unveiling the Flaws: Exploring Imperfections in Synthetic Data and Mitigation Strategies for Large Language Models—0
ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All ToolsCode14
Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal TransportCode0
RS-GPT4V: A Unified Multimodal Instruction-Following Dataset for Remote Sensing Image UnderstandingCode1
Refine Large Language Model Fine-tuning via Instruction Vector—0
ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat TemplatesCode1
Grade Score: Quantifying LLM Performance in Option SelectionCode0
Generative Visual Instruction TuningCode0
Enhancing and Assessing Instruction-Following with Fine-Grained Instruction Variants—0
How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignment—0
WPO: Enhancing RLHF with Weighted Preference OptimizationCode1
GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning AbilitiesCode2
Refusal in Language Models Is Mediated by a Single DirectionCode3
Embodied Instruction Following in Unknown Environments—0
Reminding Multimodal Large Language Models of Object-aware Knowledge with Retrieved Tags—0
DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding—0
Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference FeedbackCode7
MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM FinetuningCode3
Comparison Visual Instruction Tuning—0
Mimicking User Data: On Mitigating Fine-Tuning Risks in Closed Large Language Models—0
TasTe: Teaching Large Language Models to Translate through Self-ReflectionCode1
OPTune: Efficient Online Preference Tuning—0
CoEvol: Constructing Better Responses for Instruction Finetuning through Multi-Agent CooperationCode0
3D-Properties: Identifying Challenges in DPO and Charting a Path Forward—0
FaceGPT: Self-supervised Learning to Chat about 3D Human Faces—0
RS-Agent: Automating Remote Sensing Tasks through Intelligent AgentCode2
SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific LiteratureCode1
The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language ModelsCode5
F-LMM: Grounding Frozen Large Multimodal ModelsCode2
CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuningCode2
GenAI Arena: An Open Evaluation Platform for Generative ModelsCode2
BLSP-Emo: Towards Empathetic Large Speech-Language ModelsCode2
Synthetic Programming Elicitation for Text-to-Code in Very Low-Resource Programming and Formal LanguagesCode0
Large Language Models as Evaluators for Recommendation ExplanationsCode1
Show:102550
← PrevPage 12 of 23Next →

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