Skip to content
View leondz's full-sized avatar
🏗️
vibing
🏗️
vibing

Organizations

@ITUnlp

Block or report leondz

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
leondz/README.md

Hi there 👋

  • 🔭 I research natural language processing and machine learning. I'm currently looking at:
    • 🔒 LLM security: hazards manifest if we don't treat language models as unreliable and subvertible. Or as demons!
    • 🛡️ Online harms: content safety, misinformation processing, hate speech & abusive language detection. Enumerate risks with Language Model Risk Cards

Pinned Loading

  1. NVIDIA/garak NVIDIA/garak Public

    the LLM vulnerability scanner

    Python 2.3k 214

  2. lm_risk_cards lm_risk_cards Public

    Risks and targets for assessing LLMs & LLM vulnerabilities

    Python 25 7

  3. hatespeechdata hatespeechdata Public

    Catalog of abusive language data (PLoS 2020)

    Python 304 75

  4. generalised-brown generalised-brown Public

    Forked from sean-chester/generalised-brown

    C++ implementation of Generalised Brown clustering and python scripts for feature generation (AAAI 2016)

    C++ 2

  5. GateNLP/broad_twitter_corpus GateNLP/broad_twitter_corpus Public

    The Broad Twitter Corpus, an NER dataset in English stratified for time, location, social media genre, socioeconomic factors (COLING 2016)

    Jupyter Notebook 65 6

  6. emerging_entities_17 emerging_entities_17 Public

    Dataset for the Emerging & Novel Entity NER task (WNUT '17)

    111 24