tianyi-lab Goto Github PK

cherry_llm

[NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other models

debatune

[ACL'24] Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements

discl

Official repo for DisCL

hallusionbench

[CVPR'24] HallusionBench: You See What You Think? Or You Think What You See? An Image-Context Reasoning Benchmark Challenging for GPT-4V(ision), LLaVA-1.5, and Other Multi-modality Models

mosaic-it

reflection_tuning

[ACL'24] Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning

superfiltering

[ACL'24] Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning