相关论文: Decomposition Dilemmas: Does Claim Decomposition B…
In recent years, algorithms have been incorporated into fact-checking pipelines. They are used not only to flag previously fact-checked misinformation, but also to provide suggestions about which trending claims should be prioritized for…
As the modern tools of choice for text understanding and generation, large language models (LLMs) are expected to accurately output answers by leveraging the input context. This requires LLMs to possess both context-faithfulness and factual…
Large Reasoning Models (LRMs) achieve strong performance by generating long reasoning traces with reflection. Through a large-scale empirical analysis, we find that a substantial fraction of reflective steps consist of self-verification…
Fact-checking has become increasingly important due to the speed with which both information and misinformation can spread in the modern media ecosystem. Therefore, researchers have been exploring how fact-checking can be automated, using…
LLMs reliably correct false claims when presented in isolation, yet when the same claims are embedded in task-oriented requests, they often comply rather than correct. We term this failure mode \emph{correction suppression} and construct a…
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…
Self-distillation has emerged as an effective post-training paradigm for LLMs, often improving performance while shortening reasoning traces. However, in mathematical reasoning, we find that it can reduce response length while degrading…
To inhibit the spread of rumorous information and its severe consequences, traditional fact checking aims at retrieving relevant evidence to verify the veracity of a given claim. Fact checking methods typically use knowledge graphs (KGs) as…
Automatic fact-checking systems detect misinformation, such as fake news, by (i) selecting check-worthy sentences for fact-checking, (ii) gathering related information to the sentences, and (iii) inferring the factuality of the sentences.…
The development of technologies for easily and automatically falsifying video has raised practical questions about people's ability to detect false information online. How vulnerable are people to deepfake videos? What technologies can be…
Deep convolutional neural networks have achieved exceptional results on multiple detection and recognition tasks. However, the performance of such detectors are often evaluated in public benchmarks under constrained and non-realistic…
Automated fact checking systems have been proposed that quickly provide veracity prediction at scale to mitigate the negative influence of fake news on people and on public opinion. However, most studies focus on veracity classifiers of…
In real-world applications, computational constraints often require transforming large models into smaller, more efficient versions through model compression. While these techniques aim to reduce size and computational cost without…
Reasoning with LLMs increasingly unfolds inside a broader verification loop. Internally, systems use cheap checks, such as self-consistency or proxy rewards, which we call weak verification. Externally, users inspect outputs and steer the…
In this work, we study the impact of QA fine-tuning data on downstream factuality. We show that fine-tuning on lesser-known facts that are poorly stored during pretraining yields significantly worse factuality than fine-tuning on well-known…
Machine-learning systems such as self-driving cars or virtual assistants are composed of a large number of machine-learning models that recognize image content, transcribe speech, analyze natural language, infer preferences, rank options,…
Detecting digital face manipulation in images and video has attracted extensive attention due to the potential risk to public trust. To counteract the malicious usage of such techniques, deep learning-based deepfake detection methods have…
Recent advances in visual generative models have enabled high-fidelity image editing guided by human instructions. However, these models often struggle with complex instructions involving combinatorial editing operations or inter-step…
A fundamental problem in data fusion is to determine the veracity of multi-source data in order to resolve conflicts. While previous work in truth discovery has proved to be useful in practice for specific settings, sources' behavior or…
Recent research shows that pre-trained language models (PLMs) suffer from "prompt bias" in factual knowledge extraction, i.e., prompts tend to introduce biases toward specific labels. Prompt bias presents a significant challenge in…