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 201–250 of 1135 papers

TitleStatusHype
Ground-level Viewpoint Vision-and-Language Navigation in Continuous Environments—0
TextGames: Learning to Self-Play Text-Based Puzzle Games via Language Model ReasoningCode0
Rank1: Test-Time Compute for Reranking in Information RetrievalCode2
URO-Bench: A Comprehensive Benchmark for End-to-End Spoken Dialogue Models—0
Order Matters: Investigate the Position Bias in Multi-constraint Instruction FollowingCode0
ATEB: Evaluating and Improving Advanced NLP Tasks for Text Embedding Models—0
UrduLLaMA 1.0: Dataset Curation, Preprocessing, and Evaluation in Low-Resource Settings—0
Capability Instruction Tuning: A New Paradigm for Dynamic LLM RoutingCode0
Sequence-level Large Language Model Training with Contrastive Preference Optimization—0
NatSGLD: A Dataset with Speech, Gesture, Logic, and Demonstration for Robot Learning in Natural Human-Robot InteractionCode0
SOTOPIA-Ω: Dynamic Strategy Injection Learning and Social Instruction Following Evaluation for Social AgentsCode0
StructFlowBench: A Structured Flow Benchmark for Multi-turn Instruction FollowingCode1
OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment—0
Investigating Non-Transitivity in LLM-as-a-Judge—0
Instruction Tuning on Public Government and Cultural Data for Low-Resource Language: a Case Study in Kazakh—0
TESS 2: A Large-Scale Generalist Diffusion Language ModelCode2
MMTEB: Massive Multilingual Text Embedding BenchmarkCode0
TALKPLAY: Multimodal Music Recommendation with Large Language Models—0
Integrating Arithmetic Learning Improves Mathematical Reasoning in Smaller Models—0
Do we Really Need Visual Instructions? Towards Visual Instruction-Free Fine-tuning for Large Vision-Language Models—0
RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-FollowingCode0
SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models—0
MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive TrainingCode0
Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous Decoding—0
Step-Audio: Unified Understanding and Generation in Intelligent Speech InteractionCode7
Cuckoo: An IE Free Rider Hatched by Massive Nutrition in LLM's NestCode0
CORDIAL: Can Multimodal Large Language Models Effectively Understand Coherence Relationships?Code0
Enhancing Cross-Tokenizer Knowledge Distillation with Contextual Dynamical MappingCode1
Rewrite to Jailbreak: Discover Learnable and Transferable Implicit Harmfulness InstructionCode0
Large Language Diffusion ModelsCode7
E2LVLM:Evidence-Enhanced Large Vision-Language Model for Multimodal Out-of-Context Misinformation Detection—0
IHEval: Evaluating Language Models on Following the Instruction HierarchyCode1
BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language ModelsCode1
Who Taught You That? Tracing Teachers in Model Distillation—0
Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following—0
Hypencoder: Hypernetworks for Information Retrieval—0
M-IFEval: Multilingual Instruction-Following EvaluationCode1
Verifiable Format Control for Large Language Model Generations—0
UltraIF: Advancing Instruction Following from the WildCode1
LLMs can be easily Confused by Instructional Distractions—0
Training an LLM-as-a-Judge Model: Pipeline, Insights, and Practical Lessons—0
SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model—0
Shuttle Between the Instructions and the Parameters of Large Language Models—0
CoDe: Blockwise Control for Denoising Diffusion ModelsCode0
BARE: Leveraging Base Language Models for Few-Shot Synthetic Data Generation—0
Learning Human Perception Dynamics for Informative Robot Communication—0
Disentangling Length Bias In Preference Learning Via Response-Conditioned Modeling—0
ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Format Restriction, and Column Exploration—0
mFollowIR: a Multilingual Benchmark for Instruction Following in RetrievalCode2
Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models—0
Show:102550
← PrevPage 5 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