WENGSYX / ControlLM
ControlLM is a method to control the personality traits and behaviors of language models in real-time at inference without costly training interventions.
☆10Updated 6 months ago
Related projects: ⓘ
- Code for Findings of EMNLP2023 paper "Coarse-to-Fine Dual Encoders are Better Frame Identification Learners"☆12Updated 11 months ago
- Code for "Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective"☆28Updated 4 months ago
- Offical code repository for PromptMix: A Class Boundary Augmentation Method for Large Language Model Distillation, EMNLP 2023☆10Updated 9 months ago
- [ICLR'24 spotlight] Tool-Augmented Reward Modeling☆33Updated 6 months ago
- Source code for Truth-Aware Context Selection: Mitigating the Hallucinations of Large Language Models Being Misled by Untruthful Contexts☆13Updated 2 weeks ago
- ☆24Updated 7 months ago
- ☆13Updated last month
- Visual and Embodied Concepts evaluation benchmark☆21Updated 11 months ago
- SpyGame: An interactive multi-agent framework to evaluate intelligence with large language models :D☆14Updated 10 months ago
- The official GitHub page for paper "NegativePrompt: Leveraging Psychology for Large Language Models Enhancement via Negative Emotional St…☆15Updated 4 months ago
- Official implementation for "MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?"☆34Updated 2 months ago
- Model Editing Can Hurt General Abilities of Large Language Models☆29Updated 7 months ago
- This repository includes the official implementation of our paper "Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness …☆19Updated last year
- An automatic MLLM hallucination detection framework☆17Updated 11 months ago
- The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":☆31Updated 5 months ago
- ☆14Updated 7 months ago
- Code for "Inducer-tuning: Connecting Prefix-tuning and Adapter-tuning" (EMNLP 2022) and "Empowering Parameter-Efficient Transfer Learning…☆11Updated last year
- We introduce EMMET and unify model editing with popular algorithms ROME and MEMIT.☆11Updated 3 weeks ago
- Source code for a LoRA-based continual relation extraction method.☆10Updated 11 months ago
- Mosaic IT: Enhancing Instruction Tuning with Data Mosaics☆13Updated 2 months ago
- This repository contains the data and code for the paper "Diverse Text Generation via Variational Encoder-Decoder Models with Gaussian Pr…☆24Updated 2 years ago
- PyTorch implementation of StableMask (ICML'24)☆11Updated 2 months ago
- ☆11Updated 2 weeks ago
- Official PyTorch Implementation of MLLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced …☆22Updated 2 weeks ago
- Official implementation of "Investigating How Large Language Models Leverage Internal Knowledge to Perform Complex Reasoning"☆10Updated 2 months ago
- ☆31Updated 3 months ago
- GPT as Human☆17Updated 7 months ago
- [ICML 2024] Language Models Represent Beliefs of Self and Others☆24Updated 2 months ago
- ☆12Updated 2 months ago
- A Closer Look into Mixture-of-Experts in Large Language Models☆38Updated last month