This paper introduces KnowHalu, a novel approach for detecting hallucinations in text generated by large language models (LLMs), utilizing step-wise reasoning, multi-formulation query, multi-form knowledge for factual checking, and fusion-based detection mechanism. As LLMs are increasingly applied across various domains, ensuring that their outputs are not hallucinated is critical. Recognizing the limitations of existing approaches that either rely on the self-consistency check of LLMs or perform post-hoc fact-checking without considering the complexity of queries or the form of knowledge, KnowHalu proposes a two-phase process for hallucination detection. In the first phase, it identifies non-fabrication hallucinations--responses that, while factually correct, are irrelevant or non-specific to the query. The second phase, multi-form based factual checking, contains five key steps: reasoning and query decomposition, knowledge retrieval, knowledge optimization, judgment generation, and judgment aggregation. Our extensive evaluations demonstrate that KnowHalu significantly outperforms SOTA baselines in detecting hallucinations across diverse tasks, e.g., improving by 15.65% in QA tasks and 5.50% in summarization tasks, highlighting its effectiveness and versatility in detecting hallucinations in LLM-generated content.
Knowledge graphs play a pivotal role in various applications, such as question-answering and fact-checking. Abstract Meaning Representation (AMR) represents text as knowledge graphs. Evaluating the quality of these graphs involves matching them structurally to each other and semantically to the source text. Existing AMR metrics are inefficient and struggle to capture semantic similarity. We also lack a systematic evaluation benchmark for assessing structural similarity between AMR graphs. To overcome these limitations, we introduce a novel AMR similarity metric, rematch, alongside a new evaluation for structural similarity called RARE. Among state-of-the-art metrics, rematch ranks second in structural similarity; and first in semantic similarity by 1--5 percentage points on the STS-B and SICK-R benchmarks. Rematch is also five times faster than the next most efficient metric.
Evaluating the veracity of everyday claims is time consuming and in some cases requires domain expertise. We empirically demonstrate that the commonly used fact checking pipeline, known as the retriever-reader, suffers from performance deterioration when it is trained on the labeled data from one domain and used in another domain. Afterwards, we delve into each component of the pipeline and propose novel algorithms to address this problem. We propose an adversarial algorithm to make the retriever component robust against distribution shift. Our core idea is to initially train a bi-encoder on the labeled source data, and then, to adversarially train two separate document and claim encoders using unlabeled target data. We then focus on the reader component and propose to train it such that it is insensitive towards the order of claims and evidence documents. Our empirical evaluations support the hypothesis that such a reader shows a higher robustness against distribution shift. To our knowledge, there is no publicly available multi-topic fact checking dataset. Thus, we propose a simple automatic method to re-purpose two well-known fact checking datasets. We then construct eight fact checking scenarios from these datasets, and compare our model to a set of strong baseline models, including recent domain adaptation models that use GPT4 for generating synthetic data.
Recent efforts to address hallucinations in Large Language Models (LLMs) have focused on attributed text generation, which supplements generated texts with citations of supporting sources for post-generation fact-checking and corrections. Yet, these citations often point to entire documents or paragraphs, burdening users with extensive verification work. In this paper, we introduce a locally-attributable text generation approach, prioritizing concise attributions. Our method, named "Attribute First, then Generate", breaks down the conventional end-to-end generation process into three intuitive steps: content selection, sentence planning, and sequential sentence generation. By initially identifying relevant source segments ("select first") and then conditioning the generation process on them ("then generate"), we ensure these segments also act as the output's fine-grained attributions ("select" becomes "attribute"). Tested on Multi-document Summarization and Long-form Question-answering, our method not only yields more concise citations than the baselines but also maintains - and in some cases enhances - both generation quality and attribution accuracy. Furthermore, it significantly reduces the time required for fact verification by human assessors.
Automated fact checking has gained immense interest to tackle the growing misinformation in the digital era. Existing systems primarily focus on synthetic claims on Wikipedia, and noteworthy progress has also been made on real-world claims. In this work, we release QuanTemp, a diverse, multi-domain dataset focused exclusively on numerical claims, encompassing temporal, statistical and diverse aspects with fine-grained metadata and an evidence collection without leakage. This addresses the challenge of verifying real-world numerical claims, which are complex and often lack precise information, not addressed by existing works that mainly focus on synthetic claims. We evaluate and quantify the limitations of existing solutions for the task of verifying numerical claims. We also evaluate claim decomposition based methods, numerical understanding based models and our best baselines achieves a macro-F1 of 58.32. This demonstrates that QuanTemp serves as a challenging evaluation set for numerical claim verification.
Fact-checking is the task of verifying the factuality of a given claim by examining the available evidence. High-quality evidence plays a vital role in enhancing fact-checking systems and facilitating the generation of explanations that are understandable to humans. However, the provision of both sufficient and relevant evidence for explainable fact-checking systems poses a challenge. To tackle this challenge, we propose a method based on a Large Language Model to automatically retrieve and summarize evidence from the Web. Furthermore, we construct RU22Fact, a novel multilingual explainable fact-checking dataset on the Russia-Ukraine conflict in 2022 of 16K samples, each containing real-world claims, optimized evidence, and referenced explanation. To establish a baseline for our dataset, we also develop an end-to-end explainable fact-checking system to verify claims and generate explanations. Experimental results demonstrate the prospect of optimized evidence in increasing fact-checking performance and also indicate the possibility of further progress in the end-to-end claim verification and explanation generation tasks.
Misinformation can seriously impact society, affecting anything from public opinion to institutional confidence and the political horizon of a state. Fake News (FN) proliferation on online websites and Online Social Networks (OSNs) has increased profusely. Various fact-checking websites include news in English and barely provide information about FN in regional languages. Thus the Urdu FN purveyors cannot be discerned using factchecking portals. SOTA approaches for Fake News Detection (FND) count upon appropriately labelled and large datasets. FND in regional and resource-constrained languages lags due to the lack of limited-sized datasets and legitimate lexical resources. The previous datasets for Urdu FND are limited-sized, domain-restricted, publicly unavailable and not manually verified where the news is translated from English into Urdu. In this paper, we curate and contribute the first largest publicly available dataset for Urdu FND, Ax-to-Grind Urdu, to bridge the identified gaps and limitations of existing Urdu datasets in the literature. It constitutes 10,083 fake and real news on fifteen domains collected from leading and authentic Urdu newspapers and news channel websites in Pakistan and India. FN for the Ax-to-Grind dataset is collected from websites and crowdsourcing. The dataset contains news items in Urdu from the year 2017 to the year 2023. Expert journalists annotated the dataset. We benchmark the dataset with an ensemble model of mBERT,XLNet, and XLM RoBERTa. The selected models are originally trained on multilingual large corpora. The results of the proposed model are based on performance metrics, F1-score, accuracy, precision, recall and MCC value.
Streaming text generation has become a common way of increasing the responsiveness of language model powered applications, such as chat assistants. At the same time, extracting semantic information from generated text is a useful tool for applications such as automated fact checking or retrieval augmented generation. Currently, this requires either separate models during inference, which increases computational cost, or destructive fine-tuning of the language model. Instead, we propose an approach called EMBER which enables streaming named entity recognition in decoder-only language models without fine-tuning them and while incurring minimal additional computational cost at inference time. Specifically, our experiments show that EMBER maintains high token generation rates, with only a negligible decrease in speed of around 1% compared to a 43.64% slowdown measured for a baseline. We make our code and data available online, including a toolkit for training, testing, and deploying efficient token classification models optimized for streaming text generation.
Real-world misinformation, often multimodal, can be partially or fully factual but misleading using diverse tactics like conflating correlation with causation. Such misinformation is severely understudied, challenging to address, and harms various social domains, particularly on social media, where it can spread rapidly. High-quality and timely correction of misinformation that identifies and explains its (in)accuracies effectively reduces false beliefs. Despite the wide acceptance of manual correction, it is difficult to be timely and scalable. While LLMs have versatile capabilities that could accelerate misinformation correction, they struggle due to a lack of recent information, a tendency to produce false content, and limitations in addressing multimodal information. We propose MUSE, an LLM augmented with access to and credibility evaluation of up-to-date information. By retrieving evidence as refutations or supporting context, MUSE identifies and explains content (in)accuracies with references. It conducts multimodal retrieval and interprets visual content to verify and correct multimodal content. Given the absence of a comprehensive evaluation approach, we propose 13 dimensions of misinformation correction quality. Then, fact-checking experts evaluate responses to social media content that are not presupposed to be misinformation but broadly include (partially) incorrect and correct posts that may (not) be misleading. Results demonstrate MUSE's ability to write high-quality responses to potential misinformation--across modalities, tactics, domains, political leanings, and for information that has not previously been fact-checked online--within minutes of its appearance on social media. Overall, MUSE outperforms GPT-4 by 37% and even high-quality responses from laypeople by 29%. Our work provides a general methodological and evaluative framework to correct misinformation at scale.
Large language models (LLMs) are notorious for hallucinating, i.e., producing erroneous claims in their output. Such hallucinations can be dangerous, as occasional factual inaccuracies in the generated text might be obscured by the rest of the output being generally factually correct, making it extremely hard for the users to spot them. Current services that leverage LLMs usually do not provide any means for detecting unreliable generations. Here, we aim to bridge this gap. In particular, we propose a novel fact-checking and hallucination detection pipeline based on token-level uncertainty quantification. Uncertainty scores leverage information encapsulated in the output of a neural network or its layers to detect unreliable predictions, and we show that they can be used to fact-check the atomic claims in the LLM output. Moreover, we present a novel token-level uncertainty quantification method that removes the impact of uncertainty about what claim to generate on the current step and what surface form to use. Our method Claim Conditioned Probability (CCP) measures only the uncertainty of a particular claim value expressed by the model. Experiments on the task of biography generation demonstrate strong improvements for CCP compared to the baselines for seven LLMs and four languages. Human evaluation reveals that the fact-checking pipeline based on uncertainty quantification is competitive with a fact-checking tool that leverages external knowledge.
The rapid spread of misinformation through social media platforms has raised concerns regarding its impact on public opinion. While misinformation is prevalent in other languages, the majority of research in this field has concentrated on the English language. Hence, there is a scarcity of datasets for other languages, including Turkish. To address this concern, we have introduced the FCTR dataset, consisting of 3238 real-world claims. This dataset spans multiple domains and incorporates evidence collected from three Turkish fact-checking organizations. Additionally, we aim to assess the effectiveness of cross-lingual transfer learning for low-resource languages, with a particular focus on Turkish. We demonstrate in-context learning (zero-shot and few-shot) performance of large language models in this context. The experimental results indicate that the dataset has the potential to advance research in the Turkish language.
Large Language Models (LLMs) have demonstrated impressive capabilities across various domains, prompting a surge in their practical applications. However, concerns have arisen regarding the trustworthiness of LLMs outputs, particularly in closed-book question-answering tasks, where non-experts may struggle to identify inaccuracies due to the absence of contextual or ground truth information. This paper introduces TrustScore, a framework based on the concept of Behavioral Consistency, which evaluates whether an LLMs response aligns with its intrinsic knowledge. Additionally, TrustScore can seamlessly integrate with fact-checking methods, which assesses alignment with external knowledge sources. The experimental results show that TrustScore achieves strong correlations with human judgments, surpassing existing reference-free metrics, and achieving results on par with reference-based metrics.
We present CFEVER, a Chinese dataset designed for Fact Extraction and VERification. CFEVER comprises 30,012 manually created claims based on content in Chinese Wikipedia. Each claim in CFEVER is labeled as "Supports", "Refutes", or "Not Enough Info" to depict its degree of factualness. Similar to the FEVER dataset, claims in the "Supports" and "Refutes" categories are also annotated with corresponding evidence sentences sourced from single or multiple pages in Chinese Wikipedia. Our labeled dataset holds a Fleiss' kappa value of 0.7934 for five-way inter-annotator agreement. In addition, through the experiments with the state-of-the-art approaches developed on the FEVER dataset and a simple baseline for CFEVER, we demonstrate that our dataset is a new rigorous benchmark for factual extraction and verification, which can be further used for developing automated systems to alleviate human fact-checking efforts. CFEVER is available at https://ikmlab.github.io/CFEVER.
Fact checking aims to predict claim veracity by reasoning over multiple evidence pieces. It usually involves evidence retrieval and veracity reasoning. In this paper, we focus on the latter, reasoning over unstructured text and structured table information. Previous works have primarily relied on fine-tuning pretrained language models or training homogeneous-graph-based models. Despite their effectiveness, we argue that they fail to explore the rich semantic information underlying the evidence with different structures. To address this, we propose a novel word-level Heterogeneous-graph-based model for Fact Checking over unstructured and structured information, namely HeterFC. Our approach leverages a heterogeneous evidence graph, with words as nodes and thoughtfully designed edges representing different evidence properties. We perform information propagation via a relational graph neural network, facilitating interactions between claims and evidence. An attention-based method is utilized to integrate information, combined with a language model for generating predictions. We introduce a multitask loss function to account for potential inaccuracies in evidence retrieval. Comprehensive experiments on the large fact checking dataset FEVEROUS demonstrate the effectiveness of HeterFC. Code will be released at: https://github.com/Deno-V/HeterFC.
With the rise of generative AI, automated fact-checking methods to combat misinformation are becoming more and more important. However, factual claim detection, the first step in a fact-checking pipeline, suffers from two key issues that limit its scalability and generalizability: (1) inconsistency in definitions of the task and what a claim is, and (2) the high cost of manual annotation. To address (1), we review the definitions in related work and propose a unifying definition of factual claims that focuses on verifiability. To address (2), we introduce AFaCTA (Automatic Factual Claim deTection Annotator), a novel framework that assists in the annotation of factual claims with the help of large language models (LLMs). AFaCTA calibrates its annotation confidence with consistency along three predefined reasoning paths. Extensive evaluation and experiments in the domain of political speech reveal that AFaCTA can efficiently assist experts in annotating factual claims and training high-quality classifiers, and can work with or without expert supervision. Our analyses also result in PoliClaim, a comprehensive claim detection dataset spanning diverse political topics.
Entity Linking in natural language processing seeks to match text entities to their corresponding entries in a dictionary or knowledge base. Traditional approaches rely on contextual models, which can be complex, hard to train, and have limited transferability across different domains. Generative large language models like GPT offer a promising alternative but often underperform with naive prompts. In this study, we introduce EntGPT, employing advanced prompt engineering to enhance EL tasks. Our three-step hard-prompting method (EntGPT-P) significantly boosts the micro-F_1 score by up to 36% over vanilla prompts, achieving competitive performance across 10 datasets without supervised fine-tuning. Additionally, our instruction tuning method (EntGPT-I) improves micro-F_1 scores by 2.1% on average in supervised EL tasks and outperforms several baseline models in six Question Answering tasks. Our methods are compatible with both open-source and proprietary LLMs. All data and code are available on GitHub at https://github.com/yifding/In_Context_EL.
The rapid dissemination of misinformation through social media increased the importance of automated fact-checking. Furthermore, studies on what deep neural models pay attention to when making predictions have increased in recent years. While significant progress has been made in this field, it has not yet reached a level of reasoning comparable to human reasoning. To address these gaps, we propose a multi-task explainable neural model for misinformation detection. Specifically, this work formulates an explanation generation process of the model's veracity prediction as a text summarization problem. Additionally, the performance of the proposed model is discussed on publicly available datasets and the findings are evaluated with related studies.
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. FACT-GPT, trained on a synthetic dataset, identifies social media content that aligns with, contradicts, or is irrelevant to previously debunked claims. Our evaluation shows that our specialized LLMs can match the accuracy of larger models in identifying related claims, closely mirroring human judgment. This research provides an automated solution for efficient claim matching, demonstrates the potential of LLMs in supporting fact-checkers, and offers valuable resources for further research in the field.
We contribute the first publicly available dataset of factual claims from different platforms and fake YouTube videos on the 2023 Israel-Hamas war for automatic fake YouTube video classification. The FakeClaim data is collected from 60 fact-checking organizations in 30 languages and enriched with metadata from the fact-checking organizations curated by trained journalists specialized in fact-checking. Further, we classify fake videos within the subset of YouTube videos using textual information and user comments. We used a pre-trained model to classify each video with different feature combinations. Our best-performing fine-tuned language model, Universal Sentence Encoder (USE), achieves a Macro F1 of 87\%, which shows that the trained model can be helpful for debunking fake videos using the comments from the user discussion. The dataset is available on Github\footnote{https://github.com/Gautamshahi/FakeClaim}
Automated fact-checking is a crucial task in the governance of internet content. Although various studies utilize advanced models to tackle this issue, a significant gap persists in addressing complex real-world rumors and deceptive claims. To address this challenge, this paper explores the novel task of flaw-oriented fact-checking, including aspect generation and flaw identification. We also introduce RefuteClaim, a new framework designed specifically for this task. Given the absence of an existing dataset, we present FlawCheck, a dataset created by extracting and transforming insights from expert reviews into relevant aspects and identified flaws. The experimental results underscore the efficacy of RefuteClaim, particularly in classifying and elucidating false claims.