相关论文: Towards Robust Extractive Question Answering Model…

Event argument extraction (EAE) is an important task for information extraction to discover specific argument roles. In this study, we cast EAE as a question-based cloze task and empirically analyze fixed discrete token template…

While search-augmented large language models (LLMs) exhibit impressive capabilities, their reliability in complex multi-hop reasoning remains limited. This limitation arises from three fundamental challenges: decomposition errors, where…

Retrieval augmented language models have recently become the standard for knowledge intensive tasks. Rather than relying purely on latent semantics within the parameters of large neural models, these methods enlist a semi-parametric memory…

We propose a new Q-learning variant, called 2RA Q-learning, that addresses some weaknesses of existing Q-learning methods in a principled manner. One such weakness is an underlying estimation bias which cannot be controlled and often…

The confidentiality of trained AI models on edge devices is at risk from side-channel attacks exploiting power and electromagnetic emissions. This paper proposes a novel training methodology to enhance resilience against such threats by…

Existing pre-training methods for extractive Question Answering (QA) generate cloze-like queries different from natural questions in syntax structure, which could overfit pre-trained models to simple keyword matching. In order to address…

Adversarial training is an effective defense method to protect classification models against adversarial attacks. However, one limitation of this approach is that it can require orders of magnitude additional training time due to high cost…

We implement a method for re-ranking top-10 results of a state-of-the-art question answering (QA) system. The goal of our re-ranking approach is to improve the answer selection given the user question and the top-10 candidates. We focus on…

Existing works have shown that fine-tuned textual transformer models achieve state-of-the-art prediction performances but are also vulnerable to adversarial text perturbations. Traditional adversarial evaluation is often done \textit{only…

In conversational question answering (CQA), the task of question rewriting~(QR) in context aims to rewrite a context-dependent question into an equivalent self-contained question that gives the same answer. In this paper, we are interested…

While the Large Language Models (LLMs) dominate a majority of language understanding tasks, previous work shows that some of these results are supported by modelling spurious correlations of training datasets. Authors commonly assess model…

Any system which performs goal-directed continual learning must not only learn incrementally but process and absorb information incrementally. Such a system also has to understand when its goals have been achieved. In this paper, we…

Multimodal reward models are crucial for aligning multimodal large language models with human preferences. Recent works have incorporated reasoning capabilities into these models, achieving promising results. However, training these models…

Adversarial training (i.e., training on adversarially perturbed input data) is a well-studied method for making neural networks robust to potential adversarial attacks during inference. However, the improved robustness does not come for…

Current textual question answering models achieve strong performance on in-domain test sets, but often do so by fitting surface-level patterns in the data, so they fail to generalize to out-of-distribution settings. To make a more robust…

We study continually improving an extractive question answering (QA) system via human user feedback. We design and deploy an iterative approach, where information-seeking users ask questions, receive model-predicted answers, and provide…

Deep Learning has revolutionized machine learning and artificial intelligence, achieving superhuman performance in several standard benchmarks. It is well-known that deep learning models are inefficient to train; they learn by processing…

Open Domain Question Answering (ODQA) within natural language processing involves building systems that answer factual questions using large-scale knowledge corpora. Recent advances stem from the confluence of several factors, such as…

A safe and trustworthy use of Large Language Models (LLMs) requires an accurate expression of confidence in their answers. We propose a novel Reinforcement Learning approach that allows to directly fine-tune LLMs to express calibrated…

Recent work has explored integrating autoregressive language models with energy-based models (EBMs) to enhance text generation capabilities. However, learning effective EBMs for text is challenged by the discrete nature of language. This…