Latest

I will provide my solution to the Trojan Detection Challenge 2023 (LLM Edition), a competition at NeurIPS 2023, which aims to advance our understanding and development of methods for detecting hidden functionality in large language models (LLMs). The primary task is to reverse-engineer the trigger prompts associated with a given target string.

The BLEU (Bilingual Evaluation Understudy) score is a metric used in Natural Language Processing (NLP) to evaluate the quality of text generated by machines, such as translations. It operates as a precision-based metric, examining the overlap of words or n-grams between the generated text and a reference text.

Working on Google Colab and storing files on Google Drive offers a streamlined workflow for managing and sharing data. In this post, I will guide you through the process of saving and reading model predictions in JSON format to Google Drive from Google Colab.

Exploring Recent Techniques to Uncover and Mitigate Undesirable Behaviors in Language Models

Using Bayesian Optimization for Red Teaming Large Language Models