Related papers: Detecting Corpus-Level Knowledge Inconsistencies i…
Large Language Models (LLMs) have revolutionized numerous applications, making them an integral part of our digital ecosystem. However, their reliability becomes critical, especially when these models are exposed to misinformation. We…
Large Language Models (LLMs) are increasingly integrated into search services, providing direct answers that can reduce users' reliance on traditional result pages. Yet their factual reliability in non-English web ecosystems remains poorly…
In the summarization domain, a key requirement for summaries is to be factually consistent with the input document. Previous work has found that natural language inference (NLI) models do not perform competitively when applied to…
Large language models have become integral to question-answering applications despite their propensity for generating hallucinations and factually inaccurate content. Querying knowledge graphs to reduce hallucinations in LLM meets the…
The factuality of large language model (LLMs) tends to decay over time since events posterior to their training are "unknown" to them. One way to keep models up-to-date could be factual update: the task of inserting, replacing, or removing…
Retrieval-augmented large language models (LLMs) have demonstrated efficacy in knowledge-intensive tasks such as open-domain QA, addressing inherent challenges in knowledge update and factual inadequacy. However, inconsistencies between…
While large language models (LLMs) have shown remarkable capabilities to generate coherent text, they suffer from the issue of hallucinations -- factually inaccurate statements. Among numerous approaches to tackle hallucinations, especially…
Timely and accurate situational reports are essential for humanitarian decision-making, yet current workflows remain largely manual, resource intensive, and inconsistent. We present a fully automated framework that uses large language…
Our society is facing rampant misinformation harming public health and trust. To address the societal challenge, we introduce FACT-GPT, a system leveraging Large Language Models (LLMs) to automate the claim matching stage of fact-checking.…
The veracity of a factoid is largely independent of the language it is written in. However, language models are inconsistent in their ability to answer the same factual question across languages. This raises questions about how LLMs…
Knowledge augmentation has significantly enhanced the performance of Large Language Models (LLMs) in knowledge-intensive tasks. However, existing methods typically operate on the simplistic premise that model performance equates with…
Wikipedia is a popular web-based encyclopedia edited freely and collaboratively by its users. In this paper we present an analysis of Wikipedias in several languages as complex networks. The hyperlinks pointing from one Wikipedia article to…
Detecting factual errors in textual information, whether generated by large language models (LLM) or curated by humans, is crucial for making informed decisions. LLMs' inability to attribute their claims to external knowledge and their…
We propose DailyQA, an automatically updated dynamic dataset that updates questions weekly and contains answers to questions on any given date. DailyQA utilizes daily updates from Wikipedia revision logs to implement a fully automated…
Large language models are increasingly relied upon as sources of information, but their propensity for generating false or misleading statements with high confidence poses risks for users and society. In this paper, we confront the critical…
Wikipedia is among the largest examples of collective intelligence on the Web with over 61 million articles covering over 320 languages. Although edited and maintained by an active workforce of human volunteers, Wikipedia is highly reliant…
Recent studies demonstrate that query expansions generated by large language models (LLMs) can considerably enhance information retrieval systems by generating hypothetical documents that answer the queries as expansions. However,…
Many open-domain questions are under-specified and thus have multiple possible answers, each of which is correct under a different interpretation of the question. Answering such ambiguous questions is challenging, as it requires retrieving…
Retrieval Augmented Generation (RAG) is a commonly used approach for enhancing large language models (LLMs) with relevant and up-to-date information. However, the retrieved sources can often contain conflicting information and it remains…
Multi-entity question answering (MEQA) poses significant challenges for large language models (LLMs), which often struggle to consolidate scattered information across multiple documents. An example question might be "What is the…