AmritaBh

AmritaBh.github.io

awesome-llm-security

A curation of awesome tools, documents and projects about LLM Security.

bert-DANN

ChatGPT-as-Detector

Code and links to data for the paper "Fighting Fire with Fire: Can ChatGPT Detect AI-generated Text?"

ConDA-gen-text-detection

Code for the paper: ConDA: Contrastive Domain Adaptation for AI-generated Text Detection

CSE472_Fall20_Files

Project related demo code and files

DeepCore-CL

Using DeepCore for Continual Learning experiments

sbp24-llm-attack-defense-tutorial

Materials and paper list for the SBP-BRiMS 2024 tutorial: "Defending Against Generative AI Threats in NLP"

shield

Code for the paper: Towards Interpretable Hate Speech Detection using Large Language Model-extracted Rationales, accepted at NAACL WOAH 2024

zero-shot-llm-counterfactual

AmritaBh/ConDA-gen-text-detection

Code for the paper: ConDA: Contrastive Domain Adaptation for AI-generated Text Detection

AmritaBh/ChatGPT-as-Detector

Code and links to data for the paper "Fighting Fire with Fire: Can ChatGPT Detect AI-generated Text?"

AmritaBh/shield

Code for the paper: Towards Interpretable Hate Speech Detection using Large Language Model-extracted Rationales, accepted at NAACL WOAH 2024

AmritaBh/sbp24-llm-attack-defense-tutorial

Materials and paper list for the SBP-BRiMS 2024 tutorial: "Defending Against Generative AI Threats in NLP"

AmritaBh/bert-DANN

AmritaBh/CSE472_Fall20_Files

Project related demo code and files

AmritaBh/zero-shot-llm-counterfactual

AmritaBh/AmritaBh.github.io

AmritaBh/awesome-llm-security

A curation of awesome tools, documents and projects about LLM Security.

AmritaBh/DeepCore-CL

Using DeepCore for Continual Learning experiments

AmritaBh/DIML-Project-BERT

scripts for course project for CSE 598 - Data Intensive Systems for Machine Learning

AmritaBh/dom-gen-eagle

AmritaBh/FakeNews

Extension of https://github.com/arnavc1712/Cross-Domain-Fake-News-Detection

AmritaBh/llm-political-bias

A repo containing resources related to the research area of political bias in large language models (LLMs). This includes papers, code and other resources. Not an exhaustive list. Feel free to contribute! :)

AmritaBh/markov-network

Code for filtering raw dev comment data, building comment network and generating M2 network from this network.

AmritaBh/MixText

MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification

AmritaBh/do-not-answer

Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs