A central component of rational behavior is logical inference: the process of determining which conclusions follow from a set of premises. Psychologists have documented several ways in which humans' inferences deviate from the rules of logic. Do language models, which are trained on text generated by humans, replicate such human biases, or are they able to overcome them? Focusing on the case of syllogisms -- inferences from two simple premises -- we show that, within the PaLM2 family of transformer language models, larger models are more logical than smaller ones, and also more logical than humans. At the same time, even the largest models make systematic errors, some of which mirror human reasoning biases: they show sensitivity to the (irrelevant) ordering of the variables in the syllogism, and draw confident but incorrect inferences from particular syllogisms (syllogistic fallacies). Overall, we find that language models often mimic the human biases included in their training data, but are able to overcome them in some cases.
This paper investigates the rational thinking capability of Large Language Models (LLMs) in multi-round argumentative debates by exploring the impact of fallacious arguments on their logical reasoning performance. More specifically, we present Logic Competence Measurement Benchmark (LOGICOM), a diagnostic benchmark to assess the robustness of LLMs against logical fallacies. LOGICOM involves two agents: a persuader and a debater engaging in a multi-round debate on a controversial topic, where the persuader tries to convince the debater of the correctness of its claim. First, LOGICOM assesses the potential of LLMs to change their opinions through reasoning. Then, it evaluates the debater's performance in logical reasoning by contrasting the scenario where the persuader employs logical fallacies against one where logical reasoning is used. We use this benchmark to evaluate the performance of GPT-3.5 and GPT-4 using a dataset containing controversial topics, claims, and reasons supporting them. Our findings indicate that both GPT-3.5 and GPT-4 can adjust their opinion through reasoning. However, when presented with logical fallacies, GPT-3.5 and GPT-4 are erroneously convinced 41% and 69% more often, respectively, compared to when logical reasoning is used. Finally, we introduce a new dataset containing over 5k pairs of logical vs. fallacious arguments. The source code and dataset of this work are made publicly available.
We present a human-in-the-loop dashboard tailored to diagnosing potential spurious features that NLI models rely on for predictions. The dashboard enables users to generate diverse and challenging examples by drawing inspiration from GPT-3 suggestions. Additionally, users can receive feedback from a trained NLI model on how challenging the newly created example is and make refinements based on the feedback. Through our investigation, we discover several categories of spurious correlations that impact the reasoning of NLI models, which we group into three categories: Semantic Relevance, Logical Fallacies, and Bias. Based on our findings, we identify and describe various research opportunities, including diversifying training data and assessing NLI models' robustness by creating adversarial test suites.
The ease and speed of spreading misinformation and propaganda on the Web motivate the need to develop trustworthy technology for detecting fallacies in natural language arguments. However, state-of-the-art language modeling methods exhibit a lack of robustness on tasks like logical fallacy classification that require complex reasoning. In this paper, we propose a Case-Based Reasoning method that classifies new cases of logical fallacy by language-modeling-driven retrieval and adaptation of historical cases. We design four complementary strategies to enrich input representation for our model, based on external information about goals, explanations, counterarguments, and argument structure. Our experiments in in-domain and out-of-domain settings indicate that Case-Based Reasoning improves the accuracy and generalizability of language models. Our ablation studies suggest that representations of similar cases have a strong impact on the model performance, that models perform well with fewer retrieved cases, and that the size of the case database has a negligible effect on the performance. Finally, we dive deeper into the relationship between the properties of the retrieved cases and the model performance.
The spread of misinformation, propaganda, and flawed argumentation has been amplified in the Internet era. Given the volume of data and the subtlety of identifying violations of argumentation norms, supporting information analytics tasks, like content moderation, with trustworthy methods that can identify logical fallacies is essential. In this paper, we formalize prior theoretical work on logical fallacies into a comprehensive three-stage evaluation framework of detection, coarse-grained, and fine-grained classification. We adapt existing evaluation datasets for each stage of the evaluation. We employ three families of robust and explainable methods based on prototype reasoning, instance-based reasoning, and knowledge injection. The methods combine language models with background knowledge and explainable mechanisms. Moreover, we address data sparsity with strategies for data augmentation and curriculum learning. Our three-stage framework natively consolidates prior datasets and methods from existing tasks, like propaganda detection, serving as an overarching evaluation testbed. We extensively evaluate these methods on our datasets, focusing on their robustness and explainability. Our results provide insight into the strengths and weaknesses of the methods on different components and fallacy classes, indicating that fallacy identification is a challenging task that may require specialized forms of reasoning to capture various classes. We share our open-source code and data on GitHub to support further work on logical fallacy identification.
Reasoning is central to human intelligence. However, fallacious arguments are common, and some exacerbate problems such as spreading misinformation about climate change. In this paper, we propose the task of logical fallacy detection, and provide a new dataset (Logic) of logical fallacies generally found in text, together with an additional challenge set for detecting logical fallacies in climate change claims (LogicClimate). Detecting logical fallacies is a hard problem as the model must understand the underlying logical structure of the argument. We find that existing pretrained large language models perform poorly on this task. In contrast, we show that a simple structure-aware classifier outperforms the best language model by 5.46% on Logic and 4.51% on LogicClimate. We encourage future work to explore this task as (a) it can serve as a new reasoning challenge for language models, and (b) it can have potential applications in tackling the spread of misinformation. Our dataset and code are available at https://github.com/causalNLP/logical-fallacy
Language modelling provides a step towards intelligent communication systems by harnessing large repositories of written human knowledge to better predict and understand the world. In this paper, we present an analysis of Transformer-based language model performance across a wide range of model scales -- from models with tens of millions of parameters up to a 280 billion parameter model called Gopher. These models are evaluated on 152 diverse tasks, achieving state-of-the-art performance across the majority. Gains from scale are largest in areas such as reading comprehension, fact-checking, and the identification of toxic language, but logical and mathematical reasoning see less benefit. We provide a holistic analysis of the training dataset and model's behaviour, covering the intersection of model scale with bias and toxicity. Finally we discuss the application of language models to AI safety and the mitigation of downstream harms.
In the design of user-friendly robots, human communication should be understood by the system beyond mere logics and literal meaning. Robot communication-design has long ignored the importance of communication and politeness rules that are 'forgiving' and 'suspending disbelief' and cannot handle the basically metaphorical way humans design their utterances. Through analysis of the psychological causes of illogical and non-literal statements, signal detection, fundamental attribution errors, and anthropomorphism, we developed a fail-safe protocol for fallacies and tropes that makes use of Frege's distinction between reference and sense, Beth's tableau analytics, Grice's maxim of quality, and epistemic considerations to have the robot politely make sense of a user's sometimes unintelligible demands. Keywords: social robots, logical fallacies, metaphors, reference, sense, maxim of quality, tableau reasoning, epistemics of the virtual
In the last decade Human-Computer Interaction (HCI) has started to focus attention on forms of persuasive interaction where computer technologies have the goal of changing users behavior and attitudes according to a predefined direction. In this work, we hypothesize a strong connection between logical fallacies (forms of reasoning which are logically invalid but cognitively effective) and some common persuasion strategies adopted within web technologies. With the aim of empirically evaluating our hypothesis, we carried out a pilot study on a sample of 150 e-commerce websites.