相关论文: Counterfactual Samples Constructing and Training f…

Commonsense reasoning (CSR) requires the model to be equipped with general world knowledge. While CSR is a language-agnostic process, most comprehensive knowledge sources are in few popular languages, especially English. Thus, it remains…

Hate speech and misinformation frequently co-occur online, amplifying prejudice and polarization. Given their scale, using Large Language Models (LLMs) to assist expert counterspeech (CS) writing has gained interest, yet prior work has…

Decision-makers are faced with the challenge of estimating what is likely to happen when they take an action. For instance, if I choose not to treat this patient, are they likely to die? Practitioners commonly use supervised learning…

Counterfactual explanations (CEs) are a powerful means for understanding how decisions made by algorithms can be changed. Researchers have proposed a number of desiderata that CEs should meet to be practically useful, such as requiring…

Commonsense question answering has demonstrated considerable potential across various applications like assistants and social robots. Although fully fine-tuned pre-trained Language Models(LM) have achieved remarkable performance in…

Current language models are unable to quickly learn new concepts on the fly, often requiring a more involved finetuning process to learn robustly. Prompting in-context is not robust to context distractions, and often fails to confer much…

Counterfactuals, serving as one of the emerging type of model interpretations, have recently received attention from both researchers and practitioners. Counterfactual explanations formalize the exploration of ``what-if'' scenarios, and are…

Generating commonsense assertions within a given story context remains a difficult task for modern language models. Previous research has addressed this problem by aligning commonsense inferences with stories and training language…

Causal learning is the cognitive process of developing the capability of making causal inferences based on available information, often guided by normative principles. This process is prone to errors and biases, such as the illusion of…

Large language models can produce correct answers while relying on flawed reasoning traces, partly because common training objectives reward final-answer correctness rather than faithful intermediate reasoning. This undermines…

We introduce MCCE: Monte Carlo sampling of valid and realistic Counterfactual Explanations for tabular data, a novel counterfactual explanation method that generates on-manifold, actionable and valid counterfactuals by modeling the joint…

Automatic counterspeech generation methods have been developed to assist efforts in combating hate speech. Existing research focuses on generating counterspeech with linguistic attributes such as being polite, informative, and…

This paper describes our approach to hierarchical multi-label detection of persuasion techniques in meme texts. Our model, developed as a part of the recent SemEval task, is based on fine-tuning individual language models (BERT,…

Evaluating the quality of generated text automatically remains a significant challenge. Conventional reference-based metrics have been shown to exhibit relatively weak correlation with human evaluations. Recent research advocates the use of…

Commonsense reasoning is omnipresent in human communications and thus is an important feature for open-domain dialogue systems. However, evaluating commonsense in dialogue systems is still an open challenge. We take the first step by…

Data augmentation techniques have been proven useful in many applications in NLP fields. Most augmentations are task-specific, and cannot be used as a general-purpose tool. In our work, we present AugCSE, a unified framework to utilize…

This paper proposes an approach to cross-language sentence selection in a low-resource setting. It uses data augmentation and negative sampling techniques on noisy parallel sentence data to directly learn a cross-lingual embedding-based…

Causal generative modeling is essential for developing reliable and transparent AI systems capable of counterfactual reasoning. While existing approaches focus on integrating causal constraints during the training of generative models, they…

In the recent advances of natural language processing, the scale of the state-of-the-art models and datasets is usually extensive, which challenges the application of sample-based explanation methods in many aspects, such as explanation…

Plausible counterfactual explanations (p-CFEs) are perturbations that minimally modify inputs to change classifier decisions while remaining plausible under the data distribution. In this study, we demonstrate that classifiers can be…