We propose EAR, a query Expansion And Reranking approach for improving
p...
Evaluating the factuality of long-form text generated by large language
...
Interactive semantic parsing based on natural language (NL) feedback, wh...
In recent years, large pre-trained language models (LLMs) have demonstra...
We propose a new two-stage pre-training framework for video-to-text
gene...
The advent of large language models trained on code (code LLMs) has led ...
Various techniques have been developed in recent years to improve dense
...
We introduce REPLUG, a retrieval-augmented language modeling framework t...
Existing language models (LMs) predict tokens with a softmax over a fini...
Sampling diverse programs from a code language model and reranking with ...
Recent multimodal models such as DALL-E and CM3 have achieved remarkable...
Multi-vector retrieval methods combine the merits of sparse (e.g. BM25) ...
We study the problem of retrieval with instructions, where users of a
re...
We introduce RoMQA, the first benchmark for robust, multi-evidence,
mult...
We present an empirical study of adapting an existing pretrained text-to...
We propose structured prompt tuning, a simple and effective method to im...
Knowledge-intensive language tasks require NLP systems to both provide t...
We propose a simple and effective re-ranking method for improving passag...
Code is seldom written in a single left-to-right pass and is instead
rep...
In order to address the increasing demands of real-world applications, t...
We propose DrBoost, a dense retrieval ensemble inspired by boosting. DrB...
Many NLP tasks require processing long contexts beyond the length limit ...
With the rise of large-scale pre-trained language models, open-domain
qu...
Conventional fine-tuning of pre-trained language models tunes all model
...
Despite their recent popularity and well known advantages, dense retriev...
Pre-training on larger datasets with ever increasing model size is now a...
In adversarial data collection (ADC), a human workforce interacts with a...
Current NLP models are predominantly trained through a pretrain-then-fin...
In this paper, we introduce UnifiedM2, a general-purpose misinformation ...
We review the EfficientQA competition from NeurIPS 2020. The competition...
Retrieving relevant contexts from a large corpus is a crucial step for t...
Closed-book question-answering (QA) is a challenging task that requires ...
Natural language (NL) explanations of model predictions are gaining
popu...
Structured information is an important knowledge source for automatic
ve...
State-of-the-art Machine Reading Comprehension (MRC) models for Open-dom...
We present ELQ, a fast end-to-end entity linking model for questions, wh...
We propose a simple and efficient multi-hop dense retrieval approach for...
Recent work has suggested that language models (LMs) store both common-s...
Large pre-trained language models have been shown to store factual knowl...
Recent years have witnessed the burgeoning of pretrained language models...
Despite the widely successful applications, bootstrapping and fine-tunin...
Open-domain question answering relies on efficient passage retrieval to
...
We aim to improve question answering (QA) by decomposing hard questions ...
As a promising paradigm, interactive semantic parsing has shown to impro...
Our goal is to better comprehend procedural text, e.g., a paragraph abou...
Our goal is procedural text comprehension, namely tracking how the prope...
Many natural language questions require recognizing and reasoning with
q...
Conversational machine comprehension requires a deep understanding of th...
Semantic parsing from denotations faces two key challenges in model trai...
Comprehending procedural text, e.g., a paragraph describing photosynthes...