Hallucination in Large Foundation Models

This repository will be updated to include all the contemporary papers related to hallucination in foundation models. We broadly categorize the papers into four major categories as follows.

Text

LLMs

1. SELFCHECKGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models
2. Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators
3. HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models
4. Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation
5. PURR: Efficiently Editing Language Model Hallucinations by Denoising Language Model Corruptions
6. Mitigating Language Model Hallucination with Interactive Question-Knowledge Alignment
7. How Language Model Hallucinations Can Snowball
8. Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback
9. The Internal State of an LLM Knows When its Lying
10. Chain of Knowledge: A Framework for Grounding Large Language Models with Structured Knowledge Bases
11. HALO: Estimation and Reduction of Hallucinations in Open-Source Weak Large Language Models
12. A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation
13. Dehallucinating Large Language Models Using Formal Methods Guided Iterative Prompting
14. Sources of Hallucination by Large Language Models on Inference Tasks
15. Citation: A Key to Building Responsible and Accountable Large Language Models
16. Zero-resource hallucination prevention for large language models
17. RARR: Researching and Revising What Language Models Say, Using Language Models

Multilingual LLMs

1. Hallucinations in Large Multilingual Translation Models

Domain-specific LLMs

1. Med-HALT: Medical Domain Hallucination Test for Large Language Models
2. ChatLawLLM

Image

1. Evaluating Object Hallucination in Large Vision-Language Models
2. Detecting and Preventing Hallucinations in Large Vision Language Models
3. Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training
4. Hallucination Improves the Performance of Unsupervised Visual Representation Learning

Video

1. Let’s Think Frame by Frame: Evaluating Video Chain of Thought with Video Infilling and Prediction
2. Putting People in Their Place: Affordance-Aware Human Insertion into Scenes
3. VideoChat : Chat-Centric Video Understanding

Audio

1. LP-MusicCaps: LLM-Based Pseudo Music Captioning
2. Audio-Journey: Efficient Visual+LLM-aided Audio Encodec Diffusion