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 521–530 of 1135 papers

TitleStatusHype
Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution BehaviorsCode0
HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages—0
Navigating the Alpha Jungle: An LLM-Powered MCTS Framework for Formulaic Factor Mining—0
When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs—0
GuideBench: Benchmarking Domain-Oriented Guideline Following for LLM Agents—0
UniEval: Unified Holistic Evaluation for Unified Multimodal Understanding and Generation—0
Judging the Judges: Can Large Vision-Language Models Fairly Evaluate Chart Comprehension and Reasoning?Code0
Tests as Prompt: A Test-Driven-Development Benchmark for LLM Code Generation—0
Efficient Telecom Specific LLM: TSLAM-Mini with QLoRA and Digital Twin Data—0
Assessing Robustness to Spurious Correlations in Post-Training Language Models—0
Show:102550
← PrevPage 53 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