When large language models (LMs) are applied in zero- or few-shot settin...
While large language models (LLMs) are proficient at question-answering ...
Although counterfactual reasoning is a fundamental aspect of intelligenc...
Large language models (LLMs) exhibit remarkable performance across vario...
The surprising ability of Large Language Models (LLMs) to perform well o...
Recent methods demonstrate that data augmentation using counterfactual
k...
Recent work has shown that large language models are capable of generati...
Can we teach natural language understanding models to track their belief...
Mathematical reasoning skills are essential for general-purpose intellig...
Characterizing the implicit structure of the computation within neural
n...
Few-shot prompting is a surprisingly powerful way to use Large Language
...
We study the task of prompting large-scale language models to perform
mu...
We prove that transformer neural networks with logarithmic precision in ...
Question-answering datasets require a broad set of reasoning skills. We ...
Considerable progress has been made recently in open-domain question
ans...
The instruction learning paradigm – where a model learns to perform new
...
Investigating the reasoning abilities of transformer models, and discove...
Many real-world problems require the combined application of multiple
re...
Humans often solve complex problems by interacting (in natural language)...
To build challenging multi-hop question answering datasets, we propose a...
Is it possible to use natural language to intervene in a model's behavio...
While day-to-day questions come with a variety of answer types, the curr...
The problem of knowledge-based visual question answering involves answer...
We present the ARC-DA dataset, a direct-answer ("open response", "freefo...
While large-scale language models are extremely effective when directly
...
Existing works on temporal reasoning among events described in text focu...
While language embeddings have been shown to have stereotyping biases, h...
A common approach to solve complex tasks is by breaking them down into s...
Learned neural solvers have successfully been used to solve combinatoria...
The measurement of true progress in multihop question-answering has been...
Question answering (QA) tasks have been posed using a variety of formats...
State-of-the-art models for multi-hop question answering typically augme...
While recent models have achieved human-level scores on many NLP dataset...
Large neural models have demonstrated human-level performance on languag...
Open-domain question answering (QA) is known to involve several underlyi...
Computing the permanent of a non-negative matrix is a core problem with
...
Empirical research in Natural Language Processing (NLP) has adopted a na...
Composing knowledge from multiple pieces of texts is a key challenge in
...
Discrete integration in a high dimensional space of n variables poses
fu...
Multi-hop textual question answering requires combining information from...
Do state-of-the-art models for language understanding already have, or c...
AI has achieved remarkable mastery over games such as Chess, Go, and Pok...
We propose a novel method for exploiting the semantic structure of text ...
Question Answering (QA) naturally reduces to an entailment problem, name...
Recent systems for natural language understanding are strong at overcomi...
Many natural language questions require recognizing and reasoning with
q...
We focus on the task of multi-hop reading comprehension where a system i...
We present a new kind of question answering dataset, OpenBookQA, modeled...
Most textual entailment models focus on lexical gaps between the premise...
We consider the problem of learning textual entailment models with limit...