We introduce a new task called *entity-centric question generation* (ECQG), motivated by real-world applications such as topic-specific learning, assisted reading, and fact-checking. The task aims to generate questions from an entity perspective. To solve ECQG, we propose a coherent PLM-based framework GenCONE with two novel modules: content focusing and question verification. The content focusing module first identifies a focus as "what to ask" to form draft questions, and the question verification module refines the questions afterwards by verifying the answerability. We also construct a large-scale open-domain dataset from SQuAD to support this task. Our extensive experiments demonstrate that GenCONE significantly and consistently outperforms various baselines, and two modules are effective and complementary in generating high-quality questions.
Automated fact-checking, using machine learning to verify claims, has grown vital as misinformation spreads beyond human fact-checking capacity. Large Language Models (LLMs) like GPT-4 are increasingly trusted to write academic papers, lawsuits, and news articles and to verify information, emphasizing their role in discerning truth from falsehood and the importance of being able to verify their outputs. Understanding the capacities and limitations of LLMs in fact-checking tasks is therefore essential for ensuring the health of our information ecosystem. Here, we evaluate the use of LLM agents in fact-checking by having them phrase queries, retrieve contextual data, and make decisions. Importantly, in our framework, agents explain their reasoning and cite the relevant sources from the retrieved context. Our results show the enhanced prowess of LLMs when equipped with contextual information. GPT-4 outperforms GPT-3, but accuracy varies based on query language and claim veracity. While LLMs show promise in fact-checking, caution is essential due to inconsistent accuracy. Our investigation calls for further research, fostering a deeper comprehension of when agents succeed and when they fail.
Fusion-in-Decoder (FiD) is an effective retrieval-augmented language model applied across a variety of open-domain tasks, such as question answering, fact checking, etc. In FiD, supporting passages are first retrieved and then processed using a generative model (Reader), which can cause a significant bottleneck in decoding time, particularly with long outputs. In this work, we analyze the contribution and necessity of all the retrieved passages to the performance of reader models, and propose eliminating some of the retrieved information, at the token level, that might not contribute essential information to the answer generation process. We demonstrate that our method can reduce run-time by up to 62.2%, with only a 2% reduction in performance, and in some cases, even improve the performance results.
Reasoning over spans of tokens from different parts of the input is essential for natural language understanding (NLU) tasks such as fact-checking (FC), machine reading comprehension (MRC) or natural language inference (NLI). However, existing highlight-based explanations primarily focus on identifying individual important tokens or interactions only between adjacent tokens or tuples of tokens. Most notably, there is a lack of annotations capturing the human decision-making process w.r.t. the necessary interactions for informed decision-making in such tasks. To bridge this gap, we introduce SpanEx, a multi-annotator dataset of human span interaction explanations for two NLU tasks: NLI and FC. We then investigate the decision-making processes of multiple fine-tuned large language models in terms of the employed connections between spans in separate parts of the input and compare them to the human reasoning processes. Finally, we present a novel community detection based unsupervised method to extract such interaction explanations from a model's inner workings.
Large Language Models (LLMs) are increasingly used for accessing information on the web. Their truthfulness and factuality are thus of great interest. To help users make the right decisions about the information they get, LLMs should not only provide information but also help users fact-check it. Our experiments with 80 crowdworkers compare language models with search engines (information retrieval systems) at facilitating fact-checking. We prompt LLMs to validate a given claim and provide corresponding explanations. Users reading LLM explanations are significantly more efficient than those using search engines while achieving similar accuracy. However, they over-rely on the LLMs when the explanation is wrong. To reduce over-reliance on LLMs, we ask LLMs to provide contrastive information - explain both why the claim is true and false, and then we present both sides of the explanation to users. This contrastive explanation mitigates users' over-reliance on LLMs, but cannot significantly outperform search engines. Further, showing both search engine results and LLM explanations offers no complementary benefits compared to search engines alone. Taken together, our study highlights that natural language explanations by LLMs may not be a reliable replacement for reading the retrieved passages, especially in high-stakes settings where over-relying on wrong AI explanations could lead to critical consequences.
It is commonly perceived that fake news and real news exhibit distinct writing styles, such as the use of sensationalist versus objective language. However, we emphasize that style-related features can also be exploited for style-based attacks. Notably, the advent of powerful Large Language Models (LLMs) has empowered malicious actors to mimic the style of trustworthy news sources, doing so swiftly, cost-effectively, and at scale. Our analysis reveals that LLM-camouflaged fake news content significantly undermines the effectiveness of state-of-the-art text-based detectors (up to 38% decrease in F1 Score), implying a severe vulnerability to stylistic variations. To address this, we introduce SheepDog, a style-robust fake news detector that prioritizes content over style in determining news veracity. SheepDog achieves this resilience through (1) LLM-empowered news reframings that inject style diversity into the training process by customizing articles to match different styles; (2) a style-agnostic training scheme that ensures consistent veracity predictions across style-diverse reframings; and (3) content-focused veracity attributions that distill content-centric guidelines from LLMs for debunking fake news, offering supplementary cues and potential intepretability that assist veracity prediction. Extensive experiments on three real-world benchmarks demonstrate SheepDog's style robustness and adaptability to various backbones.
In today's digital era, the rapid spread of misinformation poses threats to public well-being and societal trust. As online misinformation proliferates, manual verification by fact checkers becomes increasingly challenging. We introduce FACT-GPT (Fact-checking Augmentation with Claim matching Task-oriented Generative Pre-trained Transformer), a framework designed to automate the claim matching phase of fact-checking using Large Language Models (LLMs). This framework identifies new social media content that either supports or contradicts claims previously debunked by fact-checkers. Our approach employs GPT-4 to generate a labeled dataset consisting of simulated social media posts. This data set serves as a training ground for fine-tuning more specialized LLMs. We evaluated FACT-GPT on an extensive dataset of social media content related to public health. The results indicate that our fine-tuned LLMs rival the performance of larger pre-trained LLMs in claim matching tasks, aligning closely with human annotations. This study achieves three key milestones: it provides an automated framework for enhanced fact-checking; demonstrates the potential of LLMs to complement human expertise; offers public resources, including datasets and models, to further research and applications in the fact-checking domain.
Fact-checking is a crucial task as it ensures the prevention of misinformation. However, manual fact-checking cannot keep up with the rate at which false information is generated and disseminated online. Automated fact-checking by machines is significantly quicker than by humans. But for better trust and transparency of these automated systems, explainability in the fact-checking process is necessary. Fact-checking often entails contrasting a factual assertion with a body of knowledge for such explanations. An effective way of representing knowledge is the Knowledge Graph (KG). There have been sufficient works proposed related to fact-checking with the usage of KG but not much focus is given to the application of reinforcement learning (RL) in such cases. To mitigate this gap, we propose an RL-based KG reasoning approach for explainable fact-checking. Extensive experiments on FB15K-277 and NELL-995 datasets reveal that reasoning over a KG is an effective way of producing human-readable explanations in the form of paths and classifications for fact claims. The RL reasoning agent computes a path that either proves or disproves a factual claim, but does not provide a verdict itself. A verdict is reached by a voting mechanism that utilizes paths produced by the agent. These paths can be presented to human readers so that they themselves can decide whether or not the provided evidence is convincing or not. This work will encourage works in this direction for incorporating RL for explainable fact-checking as it increases trustworthiness by providing a human-in-the-loop approach.
Fact-checking real-world claims often requires complex, multi-step reasoning due to the absence of direct evidence to support or refute them. However, existing fact-checking systems often lack transparency in their decision-making, making it challenging for users to comprehend their reasoning process. To address this, we propose the Question-guided Multi-hop Fact-Checking (QACHECK) system, which guides the model's reasoning process by asking a series of questions critical for verifying a claim. QACHECK has five key modules: a claim verifier, a question generator, a question-answering module, a QA validator, and a reasoner. Users can input a claim into QACHECK, which then predicts its veracity and provides a comprehensive report detailing its reasoning process, guided by a sequence of (question, answer) pairs. QACHECK also provides the source of evidence supporting each question, fostering a transparent, explainable, and user-friendly fact-checking process. A recorded video of QACHECK is at https://www.youtube.com/watch?v=ju8kxSldM64
While Large language models (LLMs) have garnered widespread applications across various domains due to their powerful language understanding and generation capabilities, the detection of non-factual or hallucinatory content generated by LLMs remains scarce. Currently, one significant challenge in hallucination detection is the laborious task of time-consuming and expensive manual annotation of the hallucinatory generation. To address this issue, this paper first introduces a method for automatically constructing model-specific hallucination datasets based on existing fact-checking datasets called AutoHall. Furthermore, we propose a zero-resource and black-box hallucination detection method based on self-contradiction. We conduct experiments towards prevalent open-/closed-source LLMs, achieving superior hallucination detection performance compared to extant baselines. Moreover, our experiments reveal variations in hallucination proportions and types among different models.
Unsupported and unfalsifiable claims we encounter in our daily lives can influence our view of the world. Characterizing, summarizing, and -- more generally -- making sense of such claims, however, can be challenging. In this work, we focus on fine-grained debate topics and formulate a new task of distilling, from such claims, a countable set of narratives. We present a crowdsourced dataset of 12 controversial topics, comprising more than 120k arguments, claims, and comments from heterogeneous sources, each annotated with a narrative label. We further investigate how large language models (LLMs) can be used to synthesise claims using In-Context Learning. We find that generated claims with supported evidence can be used to improve the performance of narrative classification models and, additionally, that the same model can infer the stance and aspect using a few training examples. Such a model can be useful in applications which rely on narratives , e.g. fact-checking.
We study how a Bayesian decision maker (DM) learns about the biases of novel information sources to predict a random state. Absent frictions, the DM uses familiar sources as yardsticks to accurately discern the biases of novel sources. We derive the distortion of the DM's long-run prediction when he holds misspecified beliefs about the biases of several familiar sources. The distortion aggregates misspecifications across familiar sources independently of the number and nature of the novel sources the DM learns about. This has implications for labor market discrimination, media bias, and project finance and oversight.
The expansion of online social media platforms has led to a surge in online content consumption. However, this has also paved the way for disseminating false claims and misinformation. As a result, there is an escalating demand for a substantial workforce to sift through and validate such unverified claims. Currently, these claims are manually verified by fact-checkers. Still, the volume of online content often outweighs their potency, making it difficult for them to validate every single claim in a timely manner. Thus, it is critical to determine which assertions are worth fact-checking and prioritize claims that require immediate attention. Multiple factors contribute to determining whether a claim necessitates fact-checking, encompassing factors such as its factual correctness, potential impact on the public, the probability of inciting hatred, and more. Despite several efforts to address claim check-worthiness, a systematic approach to identify these factors remains an open challenge. To this end, we introduce a new task of fine-grained claim check-worthiness, which underpins all of these factors and provides probable human grounds for identifying a claim as check-worthy. We present CheckIt, a manually annotated large Twitter dataset for fine-grained claim check-worthiness. We benchmark our dataset against a unified approach, CheckMate, that jointly determines whether a claim is check-worthy and the factors that led to that conclusion. We compare our suggested system with several baseline systems. Finally, we report a thorough analysis of results and human assessment, validating the efficacy of integrating check-worthiness factors in detecting claims worth fact-checking.
Understanding when two pieces of text convey the same information is a goal touching many subproblems in NLP, including textual entailment and fact-checking. This problem becomes more complex when those two pieces of text are in different languages. Here, we introduce X-PARADE (Cross-lingual Paragraph-level Analysis of Divergences and Entailments), the first cross-lingual dataset of paragraph-level information divergences. Annotators label a paragraph in a target language at the span level and evaluate it with respect to a corresponding paragraph in a source language, indicating whether a given piece of information is the same, new, or new but can be inferred. This last notion establishes a link with cross-language NLI. Aligned paragraphs are sourced from Wikipedia pages in different languages, reflecting real information divergences observed in the wild. Armed with our dataset, we investigate a diverse set of approaches for this problem, including token alignment from machine translation, textual entailment methods that localize their decisions, and prompting LLMs. Our results show that these methods vary in their capability to handle inferable information, but they all fall short of human performance.
Fact-checking in financial domain is under explored, and there is a shortage of quality dataset in this domain. In this paper, we propose Fin-Fact, a benchmark dataset for multimodal fact-checking within the financial domain. Notably, it includes professional fact-checker annotations and justifications, providing expertise and credibility. With its multimodal nature encompassing both textual and visual content, Fin-Fact provides complementary information sources to enhance factuality analysis. Its primary objective is combating misinformation in finance, fostering transparency, and building trust in financial reporting and news dissemination. By offering insightful explanations, Fin-Fact empowers users, including domain experts and end-users, to understand the reasoning behind fact-checking decisions, validating claim credibility, and fostering trust in the fact-checking process. The Fin-Fact dataset, along with our experimental codes is available at https://github.com/IIT-DM/Fin-Fact/.
In the digital age, seeking health advice on the Internet has become a common practice. At the same time, determining the trustworthiness of online medical content is increasingly challenging. Fact-checking has emerged as an approach to assess the veracity of factual claims using evidence from credible knowledge sources. To help advance automated Natural Language Processing (NLP) solutions for this task, in this paper we introduce a novel dataset HealthFC. It consists of 750 health-related claims in German and English, labeled for veracity by medical experts and backed with evidence from systematic reviews and clinical trials. We provide an analysis of the dataset, highlighting its characteristics and challenges. The dataset can be used for NLP tasks related to automated fact-checking, such as evidence retrieval, claim verification, or explanation generation. For testing purposes, we provide baseline systems based on different approaches, examine their performance, and discuss the findings. We show that the dataset is a challenging test bed with a high potential for future use.
Multimodal Video Search by Examples (MVSE) investigates using video clips as the query term for information retrieval, rather than the more traditional text query. This enables far richer search modalities such as images, speaker, content, topic, and emotion. A key element for this process is highly rapid and flexible search to support large archives, which in MVSE is facilitated by representing video attributes with embeddings. This work aims to compensate for any performance loss from this rapid archive search by examining reranking approaches. In particular, zero-shot reranking methods using large language models (LLMs) are investigated as these are applicable to any video archive audio content. Performance is evaluated for topic-based retrieval on a publicly available video archive, the BBC Rewind corpus. Results demonstrate that reranking significantly improves retrieval ranking without requiring any task-specific in-domain training data. Furthermore, three sources of information (ASR transcriptions, automatic summaries and synopses) as input for LLM reranking were compared. To gain a deeper understanding and further insights into the performance differences and limitations of these text sources, we employ a fact-checking approach to analyse the information consistency among them.
The paper considers the possibility of fine-tuning Llama 2 large language model (LLM) for the disinformation analysis and fake news detection. For fine-tuning, the PEFT/LoRA based approach was used. In the study, the model was fine-tuned for the following tasks: analysing a text on revealing disinformation and propaganda narratives, fact checking, fake news detection, manipulation analytics, extracting named entities with their sentiments. The obtained results show that the fine-tuned Llama 2 model can perform a deep analysis of texts and reveal complex styles and narratives. Extracted sentiments for named entities can be considered as predictive features in supervised machine learning models.
Extensive studies have been devoted to privatizing general-domain Large Language Models (LLMs) as Domain-Specific LLMs via feeding specific-domain data. However, these privatization efforts often ignored a critical aspect: Dual Logic Ability, which is a core reasoning ability for LLMs. The dual logic ability of LLMs ensures that they can maintain a consistent stance when confronted with both positive and negative statements about the same fact. Our study focuses on how the dual logic ability of LLMs is affected during the privatization process in the medical domain. We conduct several experiments to analyze the dual logic ability of LLMs by examining the consistency of the stance in responses to paired questions about the same fact. In our experiments, interestingly, we observed a significant decrease in the dual logic ability of existing LLMs after privatization. Besides, our results indicate that incorporating general domain dual logic data into LLMs not only enhances LLMs' dual logic ability but also further improves their accuracy. These findings underscore the importance of prioritizing LLMs' dual logic ability during the privatization process. Our study establishes a benchmark for future research aimed at exploring LLMs' dual logic ability during the privatization process and offers valuable guidance for privatization efforts in real-world applications.
Automatic fact-checking plays a crucial role in combating the spread of misinformation. Large Language Models (LLMs) and Instruction-Following variants, such as InstructGPT and Alpaca, have shown remarkable performance in various natural language processing tasks. However, their knowledge may not always be up-to-date or sufficient, potentially leading to inaccuracies in fact-checking. To address this limitation, we propose combining the power of instruction-following language models with external evidence retrieval to enhance fact-checking performance. Our approach involves leveraging search engines to retrieve relevant evidence for a given input claim. This external evidence serves as valuable supplementary information to augment the knowledge of the pretrained language model. Then, we instruct-tune an open-sourced language model, called LLaMA, using this evidence, enabling it to predict the veracity of the input claim more accurately. To evaluate our method, we conducted experiments on two widely used fact-checking datasets: RAWFC and LIAR. The results demonstrate that our approach achieves state-of-the-art performance in fact-checking tasks. By integrating external evidence, we bridge the gap between the model's knowledge and the most up-to-date and sufficient context available, leading to improved fact-checking outcomes. Our findings have implications for combating misinformation and promoting the dissemination of accurate information on online platforms. Our released materials are accessible at: https://thcheung.github.io/factllama.