Latest Articles for Hallucinations

A new method to detect and classify errors in language model outputs.

A look into issues and solutions for hallucinations in language models.

Exploring new ways to categorize inaccuracies in language models for better understanding.

A look into the pitfalls of instruction tuning for AI language models.

Evaluating how language models support medical claims with reliable references.

Learn about the challenges and methods to improve the accuracy of LLMs.

A simple comparison between LLMs and a two-player game reveals insights into their training.

Learn how data-to-text generation makes complex information easier to understand.

This research examines how language models respond to accurate versus false information.

Research reveals LLMs can process structured knowledge effectively, even when messy.

A new model enhances dialogue system evaluations through improved user simulation techniques.

This article discusses a new framework for assessing hallucinations in LVLMs.

This paper introduces a new method to examine inaccuracies in language models.

This research examines the shift from intentional to unintentional actions in videos.

Exploring the inaccuracies in large language models and their implications.

Introducing a method to assess reliability in language model outputs.

HILL helps users spot inaccuracies in language model responses.

SHROOM aims to identify and improve the accuracy of language generation systems.

Examining human factors in detecting errors in AI-generated content.

Improving chatbot accuracy on controversial issues through diverse perspectives.

This article assesses Large Language Models in predicting medical codes.

A look into the causes and detection of inaccuracies in AI decision-making.

This article explains how language models produce incorrect information and studies their causes.

Learn about language models, hallucination, and ways to improve accuracy.

Addressing hallucinations to enhance the reliability of language models.

Enhancing model accuracy by fixing input data issues.

Examining inaccuracies in AI text generation and their implications.

A study comparing the safety performance of popular language models.

A new benchmark improves how we assess LVLMs and their accuracy.

A concise look at hallucinations in MLLMs and strategies to improve reliability.

A new method aims to enhance truthfulness in language models while maintaining accuracy.

A new method enhances topic modelling using language models, reducing hallucination and improving granularity.

Study examines AI's effectiveness in generating patient discharge summaries.

Multicalibration enhances LLM accuracy by refining confidence scores and addressing hallucinations.

This article examines how fine-tuning affects language models' accuracy and hallucinations.

CrossCheckGPT provides a new way to evaluate model reliability and accuracy.

A framework for better detecting false claims in language models.

Researchers investigate the challenges faced by LLMs with ambiguous questions.

This article discusses hallucinations in LVLMs and proposes methods to tackle them.

A study on how language models express and measure their confidence.