Related papers: From Prerequisites to Predictions: Validating a Ge…

Large Vision-Language Models (LVLMs) are susceptible to object hallucinations, an issue in which their generated text contains non-existent objects, greatly limiting their reliability and practicality. Current approaches often rely on the…

Large language models suffer from "hallucinations"-logical inconsistencies induced by semantic noise. We propose that current architectures operate in a "Metric Phase," where causal order is vulnerable to spontaneous symmetry breaking.…

Large language models (LLMs) are known to "hallucinate" by generating false or misleading outputs. Hallucinations pose various harms, from erosion of trust to widespread misinformation. Existing hallucination evaluation, however, focuses…

Large language models generate outputs stochastically and may produce fluent but invalid responses, including factual hallucinations. Existing mitigation strategies reduce average error rates but do not provide explicit control over the…

Large language models (LLMs) are increasingly deployed across diverse domains, yet they are prone to generating factually incorrect outputs - commonly known as "hallucinations." Among existing mitigation strategies, uncertainty-based…

Hallucination of text ungrounded in the input is a well-known problem in neural data-to-text generation. Many methods have been proposed to mitigate it, but they typically require altering model architecture or collecting additional data,…

Contemporary Language Models (LMs), while impressively fluent, often generate content that is factually incorrect or unfaithful to the input context - a critical issue commonly referred to as 'hallucination'. This tendency of LMs to…

Automated clinical ICD-10 coding is a high-impact healthcare task requiring a balance between coverage, precision, and safety. While neural approaches achieve strong performance, they suffer from hallucination-generating invalid or…

Neural sequence generation models are known to "hallucinate", by producing outputs that are unrelated to the source text. These hallucinations are potentially harmful, yet it remains unclear in what conditions they arise and how to mitigate…

State-of-the-art deep learning algorithms generally require large amounts of data for model training. Lack thereof can severely deteriorate the performance, particularly in scenarios with fine-grained boundaries between categories. To this…

Hallucination correction is not a one-direction problem. We show that intermediate layers are neither uniformly more truthful than final layers nor uniformly less trustworthy. Yet hallucination reduction is usually instantiated through one…

Large Language Models (LLMs) have demonstrated impressive generative capabilities across diverse tasks but remain susceptible to hallucinations, confidently generated yet factually incorrect outputs. We introduce a reference-free,…

Large language models are extensively applied across a wide range of tasks, such as customer support, content creation, educational tutoring, and providing financial guidance. However, a well-known drawback is their predisposition to…

A common approach to hallucination detection casts it as a natural language inference (NLI) task, often using LLMs to classify whether the generated text is entailed by corresponding reference texts. Since entailment classification is a…

Large Reasoning Models (LRMs) have shown impressive capabilities in multi-step reasoning tasks. However, alongside these successes, a more deceptive form of model error has emerged--Reasoning Hallucination--where logically coherent but…

Context-grounded hallucinations are cases where model outputs contain information not verifiable against the source text. We study the applicability of LLMs for localizing such hallucinations, as a more practical alternative to existing…

Response consistency-based, reference-free hallucination detection (RFHD) methods do not depend on internal model states, such as generation probabilities or gradients, which Grey-box models typically rely on but are inaccessible in…

While the problem of hallucinations in neural machine translation has long been recognized, so far the progress on its alleviation is very little. Indeed, recently it turned out that without artificially encouraging models to hallucinate,…

Generative image reconstruction algorithms such as measurement conditioned diffusion models are increasingly popular in the field of medical imaging. These powerful models can transform low signal-to-noise ratio (SNR) inputs into outputs…

Point-Vision-Language Models promise to empower embodied agents with executable spatial reasoning, yet they frequently succumb to geometric hallucination where predicted 3D structures contradict the observed 2D reality. We identify a key…