Pinned Repositories
alpaca_eval
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
CRAFT
Code for ICLR 2024 paper "CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets"
FactMix
Code for COLING 2022 paper "FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognition"
FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
OOD_NLP
[NeurIPS 2023 D&B Track] Code and data for paper "Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evaluations".
OpenAttack
An Open-Source Package for Textual Adversarial Attack.
PLMCalibration
Code for ACL 2023 paper "A Close Look into the Calibration of Pre-trained Language Models"
FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
UltraFeedback
A large-scale, fine-grained, diverse preference dataset (and models).
OpenBackdoor
An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)
lifan-yuan's Repositories
lifan-yuan/CRAFT
Code for ICLR 2024 paper "CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets"
lifan-yuan/OOD_NLP
[NeurIPS 2023 D&B Track] Code and data for paper "Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evaluations".
lifan-yuan/FactMix
Code for COLING 2022 paper "FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognition"
lifan-yuan/PLMCalibration
Code for ACL 2023 paper "A Close Look into the Calibration of Pre-trained Language Models"
lifan-yuan/alpaca_eval
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
lifan-yuan/FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
lifan-yuan/OpenAttack
An Open-Source Package for Textual Adversarial Attack.