Related papers: A Discrete Hard EM Approach for Weakly Supervised …
To date, most of recent work under the retrieval-reader framework for open-domain QA focuses on either extractive or generative reader exclusively. In this paper, we study a hybrid approach for leveraging the strengths of both models. We…
Vector Quantization (VQ) is a method for discretizing latent representations and has become a major part of the deep learning toolkit. It has been theoretically and empirically shown that discretization of representations leads to improved…
Curriculum learning--ordering training examples in a sequence to aid machine learning--takes inspiration from human learning, but has not gained widespread acceptance. Static strategies for scoring item difficulty rely on indirect proxy…
Visual question answering (VQA) is challenging not only because the model has to handle multi-modal information, but also because it is just so hard to collect sufficient training examples -- there are too many questions one can ask about…
In this paper we propose a simple yet powerful method for learning representations in supervised learning scenarios where each original input datapoint is described by a set of vectors and their associated outputs may be given by soft…
Reinforcement learning improves the reasoning ability of large language models but remains costly and sample-inefficient, as many rollouts provide weak learning signals. Difficulty-aware data selection methods attempt to address this by…
Neural networks have shown significant potential in solving partial differential equations (PDEs). While deep networks are capable of approximating complex functions, direct one-shot training often faces limitations in both accuracy and…
Training data attribution (TDA) methods ask which training documents are responsible for a model behavior. However, models often learn broad concepts shared across many examples. Moreover, existing TDA methods are supervised -- they require…
In this paper, we propose a new solution to reward adaptation (RA) in reinforcement learning, where the agent adapts to a target reward function based on one or more existing source behaviors learned a priori under the same domain dynamics…
The availability of large, high-quality datasets has been one of the main drivers of recent progress in question answering (QA). Such annotated datasets however are difficult and costly to collect, and rarely exist in languages other than…
Existing work on understanding deep learning often employs measures that compress all data-dependent information into a few numbers. In this work, we adopt a perspective based on the role of individual examples. We introduce a measure of…
We show that the task of question answering (QA) can significantly benefit from the transfer learning of models trained on a different large, fine-grained QA dataset. We achieve the state of the art in two well-studied QA datasets, WikiQA…
Answering open-ended questions is an essential capability for any intelligent agent. One of the most interesting recent open-ended question answering challenges is Visual Question Answering (VQA) which attempts to evaluate a system's visual…
In this paper, we investigate the principle that `good explanations are hard to vary' in the context of deep learning. We show that averaging gradients across examples -- akin to a logical OR of patterns -- can favor memorization and…
LLM benchmarks are increasingly dynamic: instead of containing a fixed set of questions, they define templates and parameters that can generate an effectively unlimited number of question variants. This flexibility is valuable, but it makes…
Open-domain complex Question Answering (QA) is a difficult task with challenges in evidence retrieval and reasoning. The complexity of such questions could stem from questions being compositional, hybrid evidence, or ambiguity in questions.…
Multi-hop question answering (QA) requires reasoning over multiple documents to answer a complex question and provide interpretable supporting evidence. However, providing supporting evidence is not enough to demonstrate that a model has…
In simple open-domain question answering (QA), dense retrieval has become one of the standard approaches for retrieving the relevant passages to infer an answer. Recently, dense retrieval also achieved state-of-the-art results in multi-hop…
The rapid development of LLMs has sparked extensive research into their factual knowledge. Current works find that LLMs fall short on questions around low-frequency entities. However, such proofs are unreliable since the questions can…
Sequential learning of multiple tasks in artificial neural networks using gradient descent leads to catastrophic forgetting, whereby previously learned knowledge is erased during learning of new, disjoint knowledge. Here, we propose a new…