57 citations · 147 across the 34 of their papers we have counts for
6 papers · 2 filters
From Heuristic to Analytic: Cognitively Motivated Strategies for Coherent Physical Commonsense Reasoning
Zheyuan Zhang, Shane Storks, Fengyuan Hu +4
Pre-trained language models (PLMs) have shown impressive performance in various language tasks. However, they are prone to spurious correlations, and often generate illusory inform…
Merging Generated and Retrieved Knowledge for Open-Domain QA
Yunxiang Zhang, Muhammad Khalifa, Lajanugen Logeswaran +3
Open-domain question answering (QA) systems are often built with retrieval modules. However, retrieving passages from a given source is known to suffer from insufficient knowledge…
Exploring Demonstration Ensembling for In-context Learning
Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee +2
In-context learning (ICL) operates by showing language models (LMs) examples of input-output pairs for a given task, i.e., demonstrations. The standard approach for ICL is to promp…
When to Read Documents or QA History: On Unified and Selective Open-domain QA
Kyungjae Lee, Sang-eun Han, Seung-won Hwang +1
This paper studies the problem of open-domain question answering, with the aim of answering a diverse range of questions leveraging knowledge resources. Two types of sources, QA-pa…
GRACE: Discriminator-Guided Chain-of-Thought Reasoning
Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee +2
In the context of multi-step reasoning, e.g., with chain-of-thought, language models (LMs) can easily assign a high likelihood to incorrect steps. As a result, decoding strategies…
Exploring the Benefits of Training Expert Language Models over Instruction Tuning
Joel Jang, Seungone Kim, Seonghyeon Ye +5
Recently, Language Models (LMs) instruction-tuned on multiple tasks, also known as multitask-prompted fine-tuning (MT), have shown the capability to generalize to unseen tasks. Pre…