Related papers: Selective Question Answering under Domain Shift
The performance of a machine learning model degrades when it is applied to data from a similar but different domain than the data it has initially been trained on. To mitigate this domain shift problem, domain adaptation (DA) techniques…
Machine learning algorithms have achieved remarkable success across various disciplines, use cases and applications, under the prevailing assumption that training and test samples are drawn from the same distribution. Consequently, these…
Long-context question answering (QA) tasks require reasoning over a long document or multiple documents. Addressing these tasks often benefits from identifying a set of evidence spans (e.g., sentences), which provide supporting evidence for…
Why do language models trained on contradictory data prefer correct answers? In controlled experiments with small transformers (3.5M--86M parameters), we show that this preference tracks the compressibility structure of errors rather than…
Large language models often struggle to recognize their knowledge limits in closed-book question answering, leading to confident hallucinations. While decomposed prompting is typically used to improve accuracy, we investigate its impact on…
Ambiguous questions are a challenge for Question Answering models, as they require answers that cover multiple interpretations of the original query. To this end, these models are required to generate long-form answers that often combine…
We theoretically explore the relationship between sample-efficiency and adaptivity in reinforcement learning. An algorithm is sample-efficient if it uses a number of queries $n$ to the environment that is polynomial in the dimension $d$ of…
This project attempts to build a Question- Answering system in the News Domain, where Passages will be News articles, and anyone can ask a Question against it. We have built a span-based model using an Attention mechanism, where the model…
A question answering (QA) system is a type of conversational AI that generates natural language answers to questions posed by human users. QA systems often form the backbone of interactive dialogue systems, and have been studied extensively…
This thesis contributes to the mathematical foundation of domain adaptation as emerging field in machine learning. In contrast to classical statistical learning, the framework of domain adaptation takes into account deviations between…
Recent state-of-the-art open-domain QA models are typically based on a two stage retriever-reader approach in which the retriever first finds the relevant knowledge/passages and the reader then leverages that to predict the answer. Prior…
We propose a novel method for applying Transformer models to extractive question answering (QA) tasks. Recently, pretrained generative sequence-to-sequence (seq2seq) models have achieved great success in question answering. Contributing to…
The correct model response in the face of uncertainty is to abstain from answering a question so as not to mislead the user. In this work, we study the ability of LLMs to abstain from answering context-dependent science questions when…
Many applications of machine learning methods involve an iterative protocol in which data are collected, a model is trained, and then outputs of that model are used to choose what data to consider next. For example, one data-driven approach…
We study reinforcement learning for revenue management with delayed feedback, where a substantial fraction of value is determined by customer cancellations and modifications observed days after booking. We propose…
Visual Question Answering (VQA) models employ attention mechanisms to discover image locations that are most relevant for answering a specific question. For this purpose, several multimodal fusion strategies have been proposed, ranging from…
Change detection visual question answering (CDVQA) requires answering text queries by reasoning about semantic changes in bi-temporal remote sensing images. A straightforward approach is to boost CDVQA performance with generic…
Recent success in deep reinforcement learning for continuous control has been dominated by model-free approaches which, unlike model-based approaches, do not suffer from representational limitations in making assumptions about the world…
Domain shift refers to the well known problem that a model trained in one source domain performs poorly when applied to a target domain with different statistics. {Domain Generalization} (DG) techniques attempt to alleviate this issue by…
Machine learning models are often trained to predict the outcome resulting from a human decision. For example, if a doctor decides to test a patient for disease, will the patient test positive? A challenge is that historical decision-making…