Related papers: "Beware of deception": Detecting Half-Truth and De…
To reliably assist human decision-making, LLMs must maintain factual internal beliefs against misleading injections. While current models resist explicit misinformation, we uncover a fundamental vulnerability to sophisticated,…
Misinformation detection models often rely on superficial cues (i.e., \emph{shortcuts}) that correlate with misinformation in training data but fail to generalize to the diverse and evolving nature of real-world misinformation. This issue…
Why do language models trained on contradictory data prefer correct answers? In controlled experiments with small transformers (3.5M--86M parameters), we show that this preference tracks the compressibility structure of errors rather than…
The increased focus on misinformation has spurred development of data and systems for detecting the veracity of a claim as well as retrieving authoritative evidence. The Fact Extraction and VERification (FEVER) dataset provides such a…
We show that continual pretraining on plausible misinformation can overwrite specific factual knowledge in large language models without degrading overall performance. Unlike prior poisoning work under static pretraining, we study repeated…
The digital age has expanded social media and online forums, allowing free expression for nearly 45% of the global population. Yet, it has also fueled online harassment, bullying, and harmful behaviors like hate speech and toxic comments…
False information spread via the internet and social media influences public opinion and user activity, while generative models enable fake content to be generated faster and more cheaply than had previously been possible. In the not so…
As the first step of automatic fact checking, claim check-worthiness detection is a critical component of fact checking systems. There are multiple lines of research which study this problem: check-worthiness ranking from political speeches…
Automatic fact verification systems increasingly rely on large language models (LLMs). We investigate how parametric knowledge biases in these models affect fact-checking outcomes of the HerO system (baseline for FEVER-25). We examine how…
We present work on deception detection, where, given a spoken claim, we aim to predict its factuality. While previous work in the speech community has relied on recordings from staged setups where people were asked to tell the truth or to…
When a text description is extended with an additional detail, image-text similarity should drop if that detail is wrong. We show that CLIP-style dual encoders often violate this intuition: appending a plausible but incorrect object or…
Semi-supervised learning (SSL) provides an effective means of leveraging unlabelled data to improve a model performance. Even though the domain has received a considerable amount of attention in the past years, most methods present the…
Pseudo-labeling is a popular semi-supervised learning technique to leverage unlabeled data when labeled samples are scarce. The generation and selection of pseudo-labels heavily rely on labeled data. Existing approaches implicitly assume…
When testing multiple hypothesis in a survey --e.g. many different source locations, template waveforms, and so on-- the final result consists in a set of confidence intervals, each one at a desired confidence level. But the probability…
The proliferation of misinformation on social media has raised significant societal concerns, necessitating robust detection mechanisms. Large Language Models such as GPT-4 and LLaMA2 have been envisioned as possible tools for detecting…
This paper presents a new approach to the FNC-1 fake news classification task which involves employing pre-trained encoder models from similar NLP tasks, namely sentence similarity and natural language inference, and two neural network…
The spread of fake news has emerged as a critical challenge, undermining trust and posing threats to society. In the era of Large Language Models (LLMs), the capability to generate believable fake content has intensified these concerns. In…
In the evolving landscape of online discourse, misinformation increasingly adopts humorous tones to evade detection and gain traction. This work introduces Deceptive Humor as a novel research direction, emphasizing how false narratives,…
Online reviews have a significant influence on customers' purchasing decisions for any products or services. However, fake reviews can mislead both consumers and companies. Several models have been developed to detect fake reviews using…
Misinformation about climate change causes numerous negative impacts, necessitating corrective responses. Psychological research has offered various strategies for reducing the influence of climate misinformation, such as the…