Diaspora communities are disproportionately impacted by off-the-radar misinformation and often neglected by mainstream fact-checking efforts, creating a critical need to scale-up efforts of nascent fact-checking initiatives. In this paper we present SynDy, a framework for Synthetic Dynamic Dataset Generation to leverage the capabilities of the largest frontier Large Language Models (LLMs) to train local, specialized language models. To the best of our knowledge, SynDy is the first paper utilizing LLMs to create fine-grained synthetic labels for tasks of direct relevance to misinformation mitigation, namely Claim Matching, Topical Clustering, and Claim Relationship Classification. SynDy utilizes LLMs and social media queries to automatically generate distantly-supervised, topically-focused datasets with synthetic labels on these three tasks, providing essential tools to scale up human-led fact-checking at a fraction of the cost of human-annotated data. Training on SynDy's generated labels shows improvement over a standard baseline and is not significantly worse compared to training on human labels (which may be infeasible to acquire). SynDy is being integrated into Meedan's chatbot tiplines that are used by over 50 organizations, serve over 230K users annually, and automatically distribute human-written fact-checks via messaging apps such as WhatsApp. SynDy will also be integrated into our deployed Co-Insights toolkit, enabling low-resource organizations to launch tiplines for their communities. Finally, we envision SynDy enabling additional fact-checking tools such as matching new misinformation claims to high-quality explainers on common misinformation topics.
This paper presents a comprehensive analysis of explainable fact-checking through a series of experiments, focusing on the ability of large language models to verify public health claims and provide explanations or justifications for their veracity assessments. We examine the effectiveness of zero/few-shot prompting and parameter-efficient fine-tuning across various open and closed-source models, examining their performance in both isolated and joint tasks of veracity prediction and explanation generation. Importantly, we employ a dual evaluation approach comprising previously established automatic metrics and a novel set of criteria through human evaluation. Our automatic evaluation indicates that, within the zero-shot scenario, GPT-4 emerges as the standout performer, but in few-shot and parameter-efficient fine-tuning contexts, open-source models demonstrate their capacity to not only bridge the performance gap but, in some instances, surpass GPT-4. Human evaluation reveals yet more nuance as well as indicating potential problems with the gold explanations.
Fact-checking is essential due to the explosion of misinformation in the media ecosystem. Although false information exists in every language and country, most research to solve the problem mainly concentrated on huge communities like English and Chinese. Low-resource languages like Vietnamese are necessary to explore corpora and models for fact verification. To bridge this gap, we construct ViWikiFC, the first manual annotated open-domain corpus for Vietnamese Wikipedia Fact Checking more than 20K claims generated by converting evidence sentences extracted from Wikipedia articles. We analyze our corpus through many linguistic aspects, from the new dependency rate, the new n-gram rate, and the new word rate. We conducted various experiments for Vietnamese fact-checking, including evidence retrieval and verdict prediction. BM25 and InfoXLM (Large) achieved the best results in two tasks, with BM25 achieving an accuracy of 88.30% for SUPPORTS, 86.93% for REFUTES, and only 56.67% for the NEI label in the evidence retrieval task, InfoXLM (Large) achieved an F1 score of 86.51%. Furthermore, we also conducted a pipeline approach, which only achieved a strict accuracy of 67.00% when using InfoXLM (Large) and BM25. These results demonstrate that our dataset is challenging for the Vietnamese language model in fact-checking tasks.
The increased use of large language models (LLMs) across a variety of real-world applications calls for mechanisms to verify the factual accuracy of their outputs. Difficulties lie in assessing the factuality of free-form responses in open domains. Also, different papers use disparate evaluation benchmarks and measurements, which renders them hard to compare and hampers future progress. To mitigate these issues, we propose OpenFactCheck, a unified framework for building customized automatic fact-checking systems, benchmarking their accuracy, evaluating factuality of LLMs, and verifying claims in a document. OpenFactCheck consists of three modules: (i) CUSTCHECKER allows users to easily customize an automatic fact-checker and verify the factual correctness of documents and claims, (ii) LLMEVAL, a unified evaluation framework assesses LLM's factuality ability from various perspectives fairly, and (iii) CHECKEREVAL is an extensible solution for gauging the reliability of automatic fact-checkers' verification results using human-annotated datasets. Data and code are publicly available at https://github.com/yuxiaw/openfactcheck.
We conducted in-person ethnography in India and the US to investigate how young people (18-24) trusted online content, just as generative AI (genAI) became mainstream. We found that when online, how participants determined what content to trust was shaped by emotional states, which we term "information modes." Our participants reflexively shifted between modes to maintain "emotional equilibrium," and eschewed engaging literacy skills in the more passive modes in which they spent the most time. We found participants imported trust heuristics from established online contexts into emerging ones (i.e., genAI). This led them to use ill-fitting trust heuristics, and exposed them to the risk of trusting false and misleading information. While many had reservations about AI, prioritizing efficiency, they used genAI and habitual heuristics to quickly achieve goals at the expense of accuracy. We conclude that literacy interventions designed to match users' distinct information modes will be most effective.
We introduce 'FactCheck Editor', an advanced text editor designed to automate fact-checking and correct factual inaccuracies. Given the widespread issue of misinformation, often a result of unintentional mistakes by content creators, our tool aims to address this challenge. It supports over 90 languages and utilizes transformer models to assist humans in the labor-intensive process of fact verification. This demonstration showcases a complete workflow that detects text claims in need of verification, generates relevant search engine queries, and retrieves appropriate documents from the web. It employs Natural Language Inference (NLI) to predict the veracity of claims and uses LLMs to summarize the evidence and suggest textual revisions to correct any errors in the text. Additionally, the effectiveness of models used in claim detection and veracity assessment is evaluated across multiple languages.
Automated fact-checking (AFC) is garnering increasing attention by researchers aiming to help fact-checkers combat the increasing spread of misinformation online. While many existing AFC methods incorporate external information from the Web to help examine the veracity of claims, they often overlook the importance of verifying the source and quality of collected "evidence". One overlooked challenge involves the reliance on "leaked evidence", information gathered directly from fact-checking websites and used to train AFC systems, resulting in an unrealistic setting for early misinformation detection. Similarly, the inclusion of information from unreliable sources can undermine the effectiveness of AFC systems. To address these challenges, we present a comprehensive approach to evidence verification and filtering. We create the "CREDible, Unreliable or LEaked" (CREDULE) dataset, which consists of 91,632 articles classified as Credible, Unreliable and Fact checked (Leaked). Additionally, we introduce the EVidence VERification Network (EVVER-Net), trained on CREDULE to detect leaked and unreliable evidence in both short and long texts. EVVER-Net can be used to filter evidence collected from the Web, thus enhancing the robustness of end-to-end AFC systems. We experiment with various language models and show that EVVER-Net can demonstrate impressive performance of up to 91.5% and 94.4% accuracy, while leveraging domain credibility scores along with short or long texts, respectively. Finally, we assess the evidence provided by widely-used fact-checking datasets including LIAR-PLUS, MOCHEG, FACTIFY, NewsCLIPpings+ and VERITE, some of which exhibit concerning rates of leaked and unreliable evidence.
Nigerians have a notable online presence and actively discuss political and topical matters. This was particularly evident throughout the 2023 general election, where Twitter was used for campaigning, fact-checking and verification, and even positive and negative discourse. However, little or none has been done in the detection of abusive language and hate speech in Nigeria. In this paper, we curated code-switched Twitter data directed at three musketeers of the governorship election on the most populous and economically vibrant state in Nigeria; Lagos state, with the view to detect offensive speech in political discussions. We developed EkoHate -- an abusive language and hate speech dataset for political discussions between the three candidates and their followers using a binary (normal vs offensive) and fine-grained four-label annotation scheme. We analysed our dataset and provided an empirical evaluation of state-of-the-art methods across both supervised and cross-lingual transfer learning settings. In the supervised setting, our evaluation results in both binary and four-label annotation schemes show that we can achieve 95.1 and 70.3 F1 points respectively. Furthermore, we show that our dataset adequately transfers very well to three publicly available offensive datasets (OLID, HateUS2020, and FountaHate), generalizing to political discussions in other regions like the US.
This paper presents a partial reproduction of Generating Fact Checking Explanations by Anatanasova et al (2020) as part of the ReproHum element of the ReproNLP shared task to reproduce the findings of NLP research regarding human evaluation. This shared task aims to investigate the extent to which NLP as a field is becoming more or less reproducible over time. Following the instructions provided by the task organisers and the original authors, we collect relative rankings of 3 fact-checking explanations (comprising a gold standard and the outputs of 2 models) for 40 inputs on the criteria of Coverage. The results of our reproduction and reanalysis of the original work's raw results lend support to the original findings, with similar patterns seen between the original work and our reproduction. Whilst we observe slight variation from the original results, our findings support the main conclusions drawn by the original authors pertaining to the efficacy of their proposed models.
Retrieval-augmented language models have exhibited promising performance across various areas of natural language processing (NLP), including fact-critical tasks. However, due to the black-box nature of advanced large language models (LLMs) and the non-retrieval-oriented supervision signal of specific tasks, the training of retrieval model faces significant challenges under the setting of black-box LLM. We propose an approach leveraging Fine-grained Feedback with Reinforcement Retrieval (FFRR) to enhance fact-checking on news claims by using black-box LLM. FFRR adopts a two-level strategy to gather fine-grained feedback from the LLM, which serves as a reward for optimizing the retrieval policy, by rating the retrieved documents based on the non-retrieval ground truth of the task. We evaluate our model on two public datasets for real-world news claim verification, and the results demonstrate that FFRR achieves significant improvements over strong LLM-enabled and non-LLM baselines.
This study explores the use of Large Language Models (LLMs) for automatic evaluation of knowledge graph (KG) completion models. Historically, validating information in KGs has been a challenging task, requiring large-scale human annotation at prohibitive cost. With the emergence of general-purpose generative AI and LLMs, it is now plausible that human-in-the-loop validation could be replaced by a generative agent. We introduce a framework for consistency and validation when using generative models to validate knowledge graphs. Our framework is based upon recent open-source developments for structural and semantic validation of LLM outputs, and upon flexible approaches to fact checking and verification, supported by the capacity to reference external knowledge sources of any kind. The design is easy to adapt and extend, and can be used to verify any kind of graph-structured data through a combination of model-intrinsic knowledge, user-supplied context, and agents capable of external knowledge retrieval.
Existing datasets for automated fact-checking have substantial limitations, such as relying on artificial claims, lacking annotations for evidence and intermediate reasoning, or including evidence published after the claim. In this paper we introduce AVeriTeC, a new dataset of 4,568 real-world claims covering fact-checks by 50 different organizations. Each claim is annotated with question-answer pairs supported by evidence available online, as well as textual justifications explaining how the evidence combines to produce a verdict. Through a multi-round annotation process, we avoid common pitfalls including context dependence, evidence insufficiency, and temporal leakage, and reach a substantial inter-annotator agreement of $\kappa=0.619$ on verdicts. We develop a baseline as well as an evaluation scheme for verifying claims through several question-answering steps against the open web.
The increasing threat of disinformation calls for automating parts of the fact-checking pipeline. Identifying text segments requiring fact-checking is known as claim detection (CD) and claim check-worthiness detection (CW), the latter incorporating complex domain-specific criteria of worthiness and often framed as a ranking task. Zero- and few-shot LLM prompting is an attractive option for both tasks, as it bypasses the need for labeled datasets and allows verbalized claim and worthiness criteria to be directly used for prompting. We evaluate the LLMs' predictive and calibration accuracy on five CD/CW datasets from diverse domains, each utilizing a different worthiness criterion. We investigate two key aspects: (1) how best to distill factuality and worthiness criteria into a prompt and (2) what amount of context to provide for each claim. To this end, we experiment with varying the level of prompt verbosity and the amount of contextual information provided to the model. Our results show that optimal prompt verbosity is domain-dependent, adding context does not improve performance, and confidence scores can be directly used to produce reliable check-worthiness rankings.
The escalating challenge of misinformation, particularly in political discourse, requires advanced fact-checking solutions; this is even clearer in the more complex scenario of multimodal claims. We tackle this issue using a multimodal large language model in conjunction with retrieval-augmented generation (RAG), and introduce two novel reasoning techniques: Chain of RAG (CoRAG) and Tree of RAG (ToRAG). They fact-check multimodal claims by extracting both textual and image content, retrieving external information, and reasoning subsequent questions to be answered based on prior evidence. We achieve a weighted F1-score of 0.85, surpassing a baseline reasoning technique by 0.14 points. Human evaluation confirms that the vast majority of our generated fact-check explanations contain all information from gold standard data.
Recognizing if LLM output can be grounded in evidence is central to many tasks in NLP: retrieval-augmented generation, summarization, document-grounded dialogue, and more. Current approaches to this kind of fact-checking are based on verifying each piece of a model generation against potential evidence using an LLM. However, this process can be very computationally expensive, requiring many calls to a model to check a single response. In this work, we show how to build small fact-checking models that have GPT-4-level performance but for 400x lower cost. We do this by constructing synthetic training data with GPT-4, which involves creating realistic yet challenging instances of factual errors via a structured generation procedure. Training on this data teaches models to check each fact in the claim and recognize synthesis of information across sentences. For evaluation, we unify datasets from recent work on fact-checking and grounding LLM generations into a new benchmark, LLM-AggreFact. Our best system MiniCheck-FT5 (770M parameters) outperforms all systems of comparable size and reaches GPT-4 accuracy. We release LLM-AggreFact, code for data synthesis, and models.
Evaluating the reliability of news sources is a routine task for journalists and organizations committed to acquiring and disseminating accurate information. Recent research has shown that predicting sources' reliability represents an important first-prior step in addressing additional challenges such as fake news detection and fact-checking. In this paper, we introduce a novel approach for source reliability estimation that leverages reinforcement learning strategies for estimating the reliability degree of news sources. Contrary to previous research, our proposed approach models the problem as the estimation of a reliability degree, and not a reliability label, based on how all the news media sources interact with each other on the Web. We validated the effectiveness of our method on a news media reliability dataset that is an order of magnitude larger than comparable existing datasets. Results show that the estimated reliability degrees strongly correlates with journalists-provided scores (Spearman=0.80) and can effectively predict reliability labels (macro-avg. F$_1$ score=81.05). We release our implementation and dataset, aiming to provide a valuable resource for the NLP community working on information verification.
We build a novel database of around 285,000 notes from the Twitter Community Notes program to analyze the causal influence of appending contextual information to potentially misleading posts on their dissemination. Employing a difference in difference design, our findings reveal that adding context below a tweet reduces the number of retweets by almost half. A significant, albeit smaller, effect is observed when focusing on the number of replies or quotes. Community Notes also increase by 80% the probability that a tweet is deleted by its creator. The post-treatment impact is substantial, but the overall effect on tweet virality is contingent upon the timing of the contextual information's publication. Our research concludes that, although crowdsourced fact-checking is effective, its current speed may not be adequate to substantially reduce the dissemination of misleading information on social media.
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.
This paper is a preliminary report of the research plan and a digest of the results and discussions. On research note explores the complex dynamics of fake news dissemination and fact-checking costs within the framework of information markets and analyzes the equilibrium between supply and demand using the concepts of droop quotas, Meek's method, and marginal contributions. By adopting a two-sided matching market perspective, we delve into scenarios in which markets are stable under the influence of fake news perceived as truth and those in which credibility prevails. Through the application of iterated dilemma game theory, we investigate the strategic choices of news providers affected by the costs associated with spreading fake news and fact-checking efforts. We further examine the maximum reward problem and strategies to minimize the cost path for spreading fake news, and consider a nuanced understanding of market segmentation into "cheap" and "premium" segments based on the nature of the information being spread. Our analysis uses mathematical models and computational processes to identify stable equilibrium points that ensure market stability in the face of deceptive information practices and provide insight into effective strategies to enhance the informational health of the market. Through this comprehensive approach, this paper aims for a more truthful and reliable perspective from which to observe information markets. This paper is partially an attempt to utilize "Generative AI" and was written with educational intent. There are currently no plans for it to become a peer-reviewed paper.