Stars
My learning notes/codes for ML SYS.
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
This is the repository of HaluEval, a large-scale hallucination evaluation benchmark for Large Language Models.
BeHonest: Benchmarking Honesty in Large Language Models
A curated list of Human Preference Datasets for LLM fine-tuning, RLHF, and eval.
A reading list on LLM based Synthetic Data Generation 🔥
Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, exciting jailbreak methods on LLMs. It contains papers, codes, datasets, evaluations, and analyses.
A bibliography and survey of the papers surrounding o1
[2025-TMLR] A Survey on the Honesty of Large Language Models
These papers will provide unique insightful concepts that will broaden your perspective on neural networks and deep learning
The Paper List on Data Contamination for Large Language Models Evaluation.
Paper list for the survey "Combating Misinformation in the Age of LLMs: Opportunities and Challenges" and the initiative "LLMs Meet Misinformation", accepted by AI Magazine 2024
A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..
A survey on harmful fine-tuning attack for large language model
Industrial-level evaluation benchmarks for Coding LLMs in the full life-cycle of AI native software developing.企业级代码大模型评测体系,持续开放中
A paper & resource list of large language models, including course, paper, demo, figures
Curated list of datasets and tools for post-training.
Attack to induce LLMs within hallucinations
DAMO-ConvAI: The official repository which contains the codebase for Alibaba DAMO Conversational AI.
This is the repository of the Ape210K dataset and baseline models.
[ACL'24] Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning
A collection for math word problem (MWP) works, including datasets, algorithms and so on.