Related papers: Long Context Question Answering via Supervised Con…
Question-answering datasets require a broad set of reasoning skills. We show how to use question decompositions to teach language models these broad reasoning skills in a robust fashion. Specifically, we use widely available QDMR…
Contrastive explanations clarify why an event occurred in contrast to another. They are more inherently intuitive to humans to both produce and comprehend. We propose a methodology to produce contrastive explanations for classification…
Understanding long text is of great demands in practice but beyond the reach of most language-image pre-training (LIP) models. In this work, we empirically confirm that the key reason causing such an issue is that the training images are…
Long context inference scenarios have become increasingly important for large language models, yet they introduce significant computational latency. While prior research has optimized long-sequence inference through operators, model…
Recent advances in using retrieval components over external knowledge sources have shown impressive results for a variety of downstream tasks in natural language processing. Here, we explore the use of unstructured external knowledge…
The ability of large language models (LLMs) to process and reason over long textual inputs is critical for a wide range of real-world applications. However, progress in this area is significantly constrained by the absence of high-quality,…
One of the primary challenges limiting the applicability of deep learning is its susceptibility to learning spurious correlations rather than the underlying mechanisms of the task of interest. The resulting failure to generalise cannot be…
Reasoning quality in large language models depends not only on producing correct answers but also on generating valid intermediate steps. We study this through multiple-choice question answering (MCQA), which provides a controlled setting…
Prior work has uncovered a set of common problems in state-of-the-art context-based question answering (QA) systems: a lack of attention to the context when the latter conflicts with a model's parametric knowledge, little robustness to…
While self-supervised representation learning (SSL) has proved to be effective in the large model, there is still a huge gap between the SSL and supervised method in the lightweight model when following the same solution. We delve into this…
Pre-trained multimodal models have achieved significant success in retrieval-based question answering. However, current multimodal retrieval question-answering models face two main challenges. Firstly, utilizing compressed evidence features…
Pre-trained language models have proven their unique powers in capturing implicit language features. However, most pre-training approaches focus on the word-level training objective, while sentence-level objectives are rarely studied. In…
The context window of large language models (LLMs) has been extended significantly in recent years. However, while the context length that the LLM can process has grown, the capability of the model to accurately reason over that context…
Large language models (LLMs) have achieved substantial progress in processing long contexts but still struggle with long-context reasoning. Existing approaches typically involve fine-tuning LLMs with synthetic data, which depends on…
Multihop Question Answering (QA) requires systems to identify and synthesize information from multiple text passages. While most prior retrieval methods assist in identifying relevant passages for QA, further assessing the utility of the…
Large language models such as GPT-3 have demonstrated an impressive capability to adapt to new tasks without requiring task-specific training data. This capability has been particularly effective in settings such as narrative question…
While large language models (LLMs) are equipped with longer text input capabilities than before, they are struggling to seek correct information in long contexts. The "lost in the middle" problem challenges most LLMs, referring to the…
Question answering (QA) models for reading comprehension have been demonstrated to exploit unintended dataset biases such as question-context lexical overlap. This hinders QA models from generalizing to under-represented samples such as…
Question answering is one of the most important and difficult applications at the border of information retrieval and natural language processing, especially when we talk about complex science questions which require some form of inference…
Large language models have been shown to suffer from reasoning inconsistency issues. That is, they fail more in situations unfamiliar to the training data, even though exact or very similar reasoning paths exist in more common cases that…