Abstract Retrieval-Augmented Language Modeling (RALM) methods, which condition a
language model (LM) on relevant documents from a grounding corpus during generation …

Language models (LMs) are becoming the foundation for almost all major language
technologies, but their capabilities, limitations, and risks are not well understood. We present …

As a primary means of information acquisition, information retrieval (IR) systems, such as
search engines, have integrated themselves into our daily lives. These systems also serve …

Ranking documents using Large Language Models (LLMs) by directly feeding the query and
candidate documents into the prompt is an interesting and practical problem. However …

Abstract Knowledge-intensive language tasks require NLP systems to both provide the
correct answer and retrieve supporting evidence for it in a given corpus. Autoregressive …

Transformer-based language models (LMs) are powerful and widely-applicable tools, but
their usefulness is constrained by a finite context window and the expensive computational …

Sampling diverse programs from a code language model and reranking with model
likelihood is a popular method for code generation but it is prone to preferring degenerate …

Pretrained language models such as BERT have been shown to be exceptionally effective
for text ranking. However, there are limited studies on how to leverage more powerful …

We propose a novel zero-shot document ranking approach based on Large Language
Models (LLMs): the Setwise prompting approach. Our approach complements existing …

Long-form question answering (LFQA) enables answering a wide range of questions, but its
flexibility poses enormous challenges for evaluation. We perform the first targeted study of …