The repository for ACL 2024 paper "When to Trust LLMs: Aligning Confidence with Response Quality"

This is the official implementation of the Video Dialog as Conversation about Objects Living in Space-Time paper

Code and data for TACL paper It’s not Rocket Science: Interpreting Figurative Language in Narratives

Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with …

SEED-Story: Multimodal Long Story Generation with Large Language Model

Source code of our paper MIND, ACL 2024 Long Paper

[ACL 2024] Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models

Official Code and data for ACL 2024 finding, "An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models"

Code for the paper: Metacognitive Retrieval-Augmented Large Language Models

Tools for understanding how transformer predictions are built layer-by-layer

总结Prompt&LLM论文，开源数据&模型，AIGC应用

欢迎来到 LLM-Dojo，这里是一个开源大模型学习场所，使用简洁且易阅读的代码构建模型训练框架(支持各种主流模型如Qwen、Llama、GLM等等)、RLHF框架(DPO/CPO/KTO/PPO)等各种功能。👩‍🎓👨‍🎓

The first Chinese metaphor corpus serving for identification and generation. 中文比喻数据集. Presented at COLING 2022.

[EMNLP'24] Official code for "Hate Personified: Investigating the role of LLMs in content moderation"

An expert benchmark aiming to comprehensively evaluate the aesthetic perception capacities of MLLMs.

Github Repository for EMNLP 2024 Paper: Unveiling the Invisible: Captioning Videos with Metaphors

Dataset for the investigation of visual semiotics, and how specific visual features and design choices can elicit specific emotions, thoughts and beliefs.

[NeurIPS 2023] Github repository for "Composing Parameter-Efficient Modules with Arithmetic Operations"

This repository hosts the code, data and model weight of PanoSent.

LAVIS - A One-stop Library for Language-Vision Intelligence

Implementation of ACL 2024 paper "Zero-Shot Cross-Domain Dialogue State Tracking via Dual Low-Rank Adaptation".

Meta-CoT: Generalizable Chain-of-Thought Prompting in Mixed-task Scenarios with Large Language Models

Code for PHATGOOSE introduced in "Learning to Route Among Specialized Experts for Zero-Shot Generalization"

LLM-Merging: Building LLMs Efficiently through Merging

Mixture-of-Experts for Large Vision-Language Models