Related papers: Critic-Driven Decoding for Mitigating Hallucinatio…
Neural text generation (data- or text-to-text) demonstrates remarkable performance when training data is abundant which for many applications is not the case. To collect a large corpus of parallel data, heuristic rules are often used but…
Large language models (LLMs) can generate fluent natural language texts when given relevant documents as background context. This ability has attracted considerable interest in developing industry applications of LLMs. However, LLMs are…
Language models have shown strong capabilities across a wide range of tasks in software engineering, such as code generation, yet they suffer from hallucinations. While hallucinations have been studied independently in natural language and…
Multimodal Large Language Models frequently suffer from inference hallucinations, partially stemming from language priors dominating visual evidence. Existing training-free mitigation methods either perturb the visual representation and…
Existing vision-language models (VLMs) often suffer from visual hallucination, where the generated responses contain inaccuracies that are not grounded in the visual input. Efforts to address this issue without model finetuning primarily…
In the realm of medical report generation (MRG), the integration of natural language processing has emerged as a vital tool to alleviate the workload of radiologists. Despite the impressive capabilities demonstrated by large vision language…
Large Language Models (LLMs) are adept at text manipulation -- tasks such as machine translation and text summarization. However, these models can also be prone to hallucination, which can be detrimental to the faithfulness of any answers…
Decoding strategies for generative large language models (LLMs) are a critical but often underexplored aspect of text generation tasks. Guided by specific hyperparameters, these strategies aim to transform the raw probability distributions…
Despite improvements in performances on different natural language generation tasks, deep neural models are prone to hallucinating facts that are incorrect or nonexistent. Different hypotheses are proposed and examined separately for…
As Large Language Models (LLMs) continue to advance in their ability to write human-like text, a key challenge remains around their tendency to hallucinate generating content that appears factual but is ungrounded. This issue of…
The emergence of large language models (LLMs) has significantly advanced the development of natural language processing (NLP), especially in text generation tasks like question answering. However, model hallucinations remain a major…
While large language models have demonstrated exceptional performance across a wide range of tasks, they remain susceptible to hallucinations -- generating plausible yet factually incorrect contents. Existing methods to mitigating such risk…
We present a novel neurosymbolic framework for RDF-to-text generation, in which the model is "trained" through collaborative interactions among multiple LLM agents rather than traditional backpropagation. The LLM agents produce rule-based…
Hallucination mitigation remains a persistent challenge for large language models (LLMs), even as model scales grow. Existing approaches often rely on external knowledge sources, such as structured databases or knowledge graphs, accessed…
Large Language Models (LLMs) are powerful tools for text generation, translation, and summarization, but they often suffer from hallucinations-instances where they fail to maintain the fidelity and coherence of contextual information during…
Recently developed large language models have achieved remarkable success in generating fluent and coherent text. However, these models often tend to 'hallucinate' which critically hampers their reliability. In this work, we address this…
Model hallucination is one of the most critical challenges faced by Large Language Models (LLMs), especially in high-stakes code intelligence tasks. As LLMs become increasingly integrated into software engineering tasks, understanding and…
To address hallucination issues in large language models (LLMs), this paper proposes a method for mitigating prompt-induced hallucinations. Building on a knowledge distillation chain-style model, we introduce a code module to guide…
Large language models (LLMs) frequently generate confident yet inaccurate responses, introducing significant risks for deployment in safety-critical domains. We present a novel, test-time approach to detecting model hallucination through…
Hallucinations in large language models (LLMs), defined as fluent yet incorrect or incoherent outputs, pose a significant challenge to the automatic generation of educational multiple-choice questions (MCQs). We identified four key…