Related papers: Using Counterexample Generation and Theory Explora…

Counterfactual data augmentation (CDA) -- i.e., adding minimally perturbed inputs during training -- helps reduce model reliance on spurious correlations and improves generalization to out-of-distribution (OOD) data. Prior work on…

Language models are often trained to maximize the likelihood of the next token given past tokens in the training dataset. However, during inference time, they are utilized differently, generating text sequentially and auto-regressively by…

Data-driven methods that detect anomalies in times series data are ubiquitous in practice, but they are in general unable to provide helpful explanations for the predictions they make. In this work we propose a model-agnostic algorithm that…

Estimating the counterfactual outcome of treatment is essential for decision-making in public health and clinical science, among others. Often, treatments are administered in a sequential, time-varying manner, leading to an exponentially…

Generating diverse responses from large language models (LLMs) is crucial for applications such as planning/search and synthetic data generation, where diversity provides distinct answers across generations. Prior approaches rely on…

Retrieval-augmented generation (RAG) enhances LLMs with external knowledge, yet generation remains vulnerable to retrieval-induced noise and uncertain placement of relevant chunks, often causing hallucinations. We present Ext2Gen, an…

Question Generation (QG) is a task of Natural Language Processing (NLP) that aims at automatically generating questions from text. Many applications can benefit from automatically generated questions, but often it is necessary to curate…

Counterfactuals are widely used to explain ML model predictions by providing alternative scenarios for obtaining the more desired predictions. They can be generated by a variety of methods that optimize different, sometimes conflicting,…

Counterfactual explanations elucidate algorithmic decisions by pointing to scenarios that would have led to an alternative, desired outcome. Giving insight into the model's behavior, they hint users towards possible actions and give grounds…

The growing capability of large language models to produce fluent, contextually coherent text has created mounting pressure on the systems and institutions responsible for ensuring the authenticity of digital content. Advanced generative…

Knowledge-grounded dialogue generation aims to mitigate the issue of text degeneration by incorporating external knowledge to supplement the context. However, the model often fails to internalize this information into responses in a…

Machine learning models that operate on graph-structured data, such as molecular graphs or social networks, often make accurate predictions but offer little insight into why certain predictions are made. Counterfactual explanations address…

There are now many explainable AI methods for understanding the decisions of a machine learning model. Among these are those based on counterfactual reasoning, which involve simulating features changes and observing the impact on the…

Legal professionals need to write analyses that rely on citations to relevant precedents, i.e., previous case decisions. Intelligent systems assisting legal professionals in writing such documents provide great benefits but are challenging…

Automatic and efficient verification of multiplier designs, especially through a provably correct method, is a difficult problem. We show how to utilize a theorem prover, ACL2, to implement an efficient rewriting algorithm for multiplier…

Retrieval-augmented generation has gained significant attention due to its ability to integrate relevant external knowledge, enhancing the accuracy and reliability of the LLMs' responses. Most of the existing methods apply a dynamic…

Product descriptions on e-commerce websites often suffer from missing important aspects. Clarification question generation (CQGen) can be a promising approach to help alleviate the problem. Unlike traditional QGen assuming the existence of…

Despite the evolution of language models, they continue to portray harmful societal biases and stereotypes inadvertently learned from training data. These inherent biases often result in detrimental effects in various applications.…

Synthetic data is essential for assessing clustering techniques, complementing and extending real data, and allowing for more complete coverage of a given problem's space. In turn, synthetic data generators have the potential of creating…

Machine learning algorithms that learn black-box predictive models (which cannot be directly interpreted) are increasingly used to make predictions affecting the lives of people. It is important that users understand the predictions of such…