Projects sharing features with Less Is More

✨✨Woodpecker: Hallucination Correction for Multimodal Large Language Models

ICLR '25 Official Pytorch implementation of "Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations"

ACL 2024 Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models. Detect and mitigate object hallucinations in LVLMs by itself through logical closed loops.

ICLR 2024 Analyzing and Mitigating Object Hallucination in Large Vision-Language Models

HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data (Accepted by CVPR 2024)

Aligning LMMs with Factually Augmented RLHF

CVPR 2024 Highlight Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding

CVPR 2025 Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention

CVPR 2024 Highlight OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation

ICLR'24 Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning

ChatLaw is a specialized large language model legal assistant designed to provide automated consulting and question answering within Chinese legal frameworks. It functions as a system for legal knowledge management, processing complex legal texts to deliver accurate statutory answers and advisory services. The system utilizes a mixture-of-experts modeling approach and multi-agent coordination to research information and generate professional consultation reports. To ensure factual reliability and minimize hallucinations, it integrates a legal knowledge graph and a standardized operating proce

This project serves as an educational resource and guide for prompt engineering, providing a structured methodology for interacting with large language models. It focuses on teaching core strategies to improve the reliability, accuracy, and consistency of model outputs across a variety of natural language processing tasks. The framework emphasizes the use of standardized templates and logical decomposition to manage complex instructions. By implementing techniques such as few-shot context injection, iterative refinement, and delimiter-based segmentation, the project demonstrates how to guide

This repo contains the code for the paper: Mitigating Hallucinations in Large Vision-Language Models by Adaptively Constraining Information Flow. AAAI 2025

Official PyTorch Implementation for the "What if...?: Thinking Counterfactual Keywords Helps to Mitigate Hallucination in Large Multi-modal Models" paper (EMNLP Findings 2024).

This is the official implementation of the paper "The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering".

This repository contains the official pytorch implementation of the CVPR2025 paper: "Octopus: Alleviating Hallucination via Dynamic Contrastive Decoding".

Following the VCD, use `bash conda create -yn imccd python=3.9 conda activate imccd cd IMCCD pip install -r requirements.txt `

Diagram of Self-Introspective Decoding.

Official PyTorch implementation of "LPOI: Listwise Preference Optimization for Vision Language Models", (ACL 2025 Main)

Paper: PAINT: PAYING ATTENTION TO INFORMED TOKENS TO MITIGATE HALLUCINATION IN LARGE VISION-LANGUAGE MODEL

Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs What doesn't kill me makes me stronger!

The official repository of the paper "The Instinctive Bias: Spurious Images lead to Hallucination in MLLMs"

TODO

\NAACL 2024\ This is the official github for "Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision". Volcano employs a single LMM to generate initial responses, feedback, and revisions, as well as decisions to accept revisions. It follows a sequential procedure of…