Related papers: Counterfactual Samples Constructing and Training f…
This paper provides preliminary results on exploring the task of performing turn-level data augmentation for dialogue system based on different types of commonsense relationships, and the automatic evaluation of the generated synthetic…
Grammar-based test case generation has proven effective for competitive programming problems, but generating valid and general grammars from natural language specifications remains a key challenge, especially under limited supervision.…
As machine learning models evolve, maintaining transparency demands more human-centric explainable AI techniques. Counterfactual explanations, with roots in human reasoning, identify the minimal input changes needed to obtain a given output…
A common approach for testing fairness issues in text-based classifiers is through the use of counterfactuals: does the classifier output change if a sensitive attribute in the input is changed? Existing counterfactual generation methods…
Despite Visual Question Answering (VQA) has realized impressive progress over the last few years, today's VQA models tend to capture superficial linguistic correlations in the train set and fail to generalize to the test set with different…
Commonsense Knowledge Base (CSKB) Population aims at reasoning over unseen entities and assertions on CSKBs, and is an important yet hard commonsense reasoning task. One challenge is that it requires out-of-domain generalization ability as…
Progress on commonsense reasoning is usually measured from performance improvements on Question Answering tasks designed to require commonsense knowledge. However, fine-tuning large Language Models (LMs) on these specific tasks does not…
Learning from negative samples holds great promise for improving Large Language Model (LLM) reasoning capability, yet existing methods treat all incorrect responses as equally informative, overlooking the crucial role of sample quality. To…
Counterfactual explanations (CFEs) exemplify how to minimally modify a feature vector to achieve a different prediction for an instance. CFEs can enhance informational fairness and trustworthiness, and provide suggestions for users who…
Inferring commonsense knowledge is a key challenge in natural language processing, but due to the sparsity of training data, previous work has shown that supervised methods for commonsense knowledge mining underperform when evaluated on…
Existing knowledge-enhanced methods have achieved remarkable results in certain QA tasks via obtaining diverse knowledge from different knowledge bases. However, limited by the properties of retrieved knowledge, they still have trouble…
It is very challenging to curate a dataset for language-specific knowledge and common sense in order to evaluate natural language understanding capabilities of language models. Due to the limitation in the availability of annotators, most…
This paper focuses on sarcasm detection, which aims to identify whether given statements convey criticism, mockery, or other negative sentiment opposite to the literal meaning. To detect sarcasm, humans often require a comprehensive…
The web-scale of pretraining data has created an important evaluation challenge: to disentangle linguistic competence on cases well-represented in pretraining data from generalization to out-of-domain language, specifically the dynamic,…
Commonsense reasoning is an appealing topic in natural language processing (NLP) as it plays a fundamental role in supporting the human-like actions of NLP systems. With large-scale language models as the backbone, unsupervised pre-training…
Arguments often do not make explicit how a conclusion follows from its premises. To compensate for this lack, we enrich arguments with structured background knowledge to support knowledge-intense argumentation tasks. We present a new…
Counterfactual explanations (CFs) offer human-centric insights into machine learning predictions by highlighting minimal changes required to alter an outcome. Therefore, CFs can be used as (i) interventions for abnormality prevention and…
Recent advances in general purpose pre-trained language models have shown great potential in commonsense reasoning. However, current works still perform poorly on standard commonsense reasoning benchmarks including the Com2Sense Dataset. We…
Pre-trained Language Models (PTLMs) have been shown to perform well on natural language tasks. Many prior works have leveraged structured commonsense present in the form of entities linked through labeled relations in Knowledge Graphs (KGs)…
Fine-tuning of pre-trained transformer models has become the standard approach for solving common NLP tasks. Most of the existing approaches rely on a randomly initialized classifier on top of such networks. We argue that this fine-tuning…