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 401–450 of 1135 papers

TitleStatusHype
Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language ModelsCode1
On the Exploitability of Instruction TuningCode1
OphGLM: Training an Ophthalmology Large Language-and-Vision Assistant based on Instructions and DialogueCode1
From Pixels to UI Actions: Learning to Follow Instructions via Graphical User InterfacesCode1
Bactrian-X: Multilingual Replicable Instruction-Following Models with Low-Rank AdaptationCode1
PathAsst: A Generative Foundation AI Assistant Towards Artificial General Intelligence of PathologyCode1
TOAST: Transfer Learning via Attention SteeringCode1
PIVOINE: Instruction Tuning for Open-world Information ExtractionCode1
Schema-Driven Information Extraction from Heterogeneous TablesCode1
LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and GenerationCode1
Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation ExtractorsCode1
M3KE: A Massive Multi-Level Multi-Subject Knowledge Evaluation Benchmark for Chinese Large Language ModelsCode1
Enhancing Large Language Model with Self-Controlled Memory FrameworkCode1
Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLMCode1
ParroT: Translating during Chat using Large Language Models tuned with Human Translation and FeedbackCode1
Lana: A Language-Capable Navigator for Instruction Following and GenerationCode1
CB2: Collaborative Natural Language Interaction Research PlatformCode1
ChatGPT may Pass the Bar Exam soon, but has a Long Way to Go for the LexGLUE benchmarkCode1
Alexa Arena: A User-Centric Interactive Platform for Embodied AICode1
Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction FollowingCode1
"No, to the Right" -- Online Language Corrections for Robotic Manipulation via Shared AutonomyCode1
On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot ReasoningCode1
Language-Conditioned Reinforcement Learning to Solve Misunderstandings with Action CorrectionsCode1
Instruction-Following Agents with Multimodal TransformerCode1
DANLI: Deliberative Agent for Following Natural Language InstructionsCode1
Efficiently Enhancing Zero-Shot Performance of Instruction Following Model via Retrieval of Soft PromptCode1
Engineering flexible machine learning systems by traversing functionally-invariant pathsCode1
Inferring Rewards from Language in ContextCode1
Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language NavigationCode1
Combining Modular Skills in Multitask LearningCode1
DialFRED: Dialogue-Enabled Agents for Embodied Instruction FollowingCode1
Guiding Multi-Step Rearrangement Tasks with Natural Language InstructionsCode1
FILM: Following Instructions in Language with Modular MethodsCode1
Waypoint Models for Instruction-guided Navigation in Continuous EnvironmentsCode1
Lexicon Learning for Few Shot Sequence ModelingCode1
Room-and-Object Aware Knowledge Reasoning for Remote Embodied Referring ExpressionCode1
Lexicon Learning for Few-Shot Neural Sequence ModelingCode1
A modular vision language navigation and manipulation framework for long horizon compositional tasks in indoor environmentCode1
Factorizing Perception and Policy for Interactive Instruction FollowingCode1
Few-shot Object Grounding and Mapping for Natural Language Robot Instruction FollowingCode1
RMM: A Recursive Mental Model for Dialogue NavigationCode1
AllenAct: A Framework for Embodied AI ResearchCode1
RMM: A Recursive Mental Model for Dialog NavigationCode1
Zero-Shot Compositional Policy Learning via Language GroundingCode1
Learning to Map Natural Language Instructions to Physical Quadcopter Control using Simulated FlightCode1
Following High-level Navigation Instructions on a Simulated Quadcopter with Imitation LearningCode1
AnyCap Project: A Unified Framework, Dataset, and Benchmark for Controllable Omni-modal Captioning—0
How Many Instructions Can LLMs Follow at Once?—0
Multilingual Multimodal Software Developer for Code Generation—0
TuneShield: Mitigating Toxicity in Conversational AI while Fine-tuning on Untrusted Data—0
Show:102550
← PrevPage 9 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