MTTM: Metamorphic Testing for Textual Content Moderation Software

basically all the things I used for this article

Narrative movie understanding benchmark

Code and data for our paper "On the Resilience of Multi-Agent Systems with Malicious Agents"

A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.

Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

Benchmarking LLMs' Gaming Ability in Multi-Agent Environments

TransferAttack is a pytorch framework to boost the adversarial transferability for image classification.

[CVPR 2024] Aligning and Prompting Everything All at Once for Universal Visual Perception

SpyGame: An interactive multi-agent framework to evaluate intelligence with large language models :D

Multilingual safety benchmark for Large Language Models

Benchmarking LLMs' Psychological Portrayal

✨✨Woodpecker: Hallucination Correction for Multimodal Large Language Models. The first work to correct hallucinations in MLLMs

👨‍💻 An awesome and curated list of best code-LLM for research.

A framework to evaluate the generalization capability of safety alignment for LLMs

Benchmarking LLMs' Emotional Alignment with Humans

Recent papers on (1) Psychology of LLMs; (2) Biases in LLMs.

[TACL 2024] MAPS enables LLMs🤖 to mimic the human😁 translation process.

Macaw-LLM: Multi-Modal Language Modeling with Image, Video, Audio, and Text Integration

MAD: The first work to explore Multi-Agent Debate with Large Language Models :D

The ParroT framework to enhance and regulate the Translation Abilities during Chat based on open-sourced LLMs (e.g., LLaMA-7b, Bloomz-7b1-mt) and human written translation and evaluation data.

A preliminary evaluation of ChatGPT/GPT-4 for machine translation.

This is the tool released in ICSE 2022 paper "Static Inference Meets Deep Learning: A Hybrid Type Inference Approach for Python"

Must-read papers on graph neural networks (GNN)

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)