no code implementations • 26 Apr 2024 • Yunxiang Zhang, Muhammad Khalifa, Lajanugen Logeswaran, Jaekyeom Kim, Moontae Lee, Honglak Lee, Lu Wang
Self-correction has emerged as a promising solution to boost the reasoning performance of large language models (LLMs), where LLMs refine their solutions using self-generated critiques that pinpoint the errors.
1 code implementation • 1 Apr 2024 • Muhammad Khalifa, David Wadden, Emma Strubell, Honglak Lee, Lu Wang, Iz Beltagy, Hao Peng
We investigate the problem of intrinsic source citation, where LLMs are required to cite the pretraining source supporting a generated response.
1 code implementation • 30 Oct 2023 • Xin Liu, Muhammad Khalifa, Lu Wang
For evaluation, we construct CaT, a benchmark consisting of eight text generation tasks, covering responses ranging from short phrases to paragraphs.
1 code implementation • 22 Oct 2023 • Yunxiang Zhang, Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, Lu Wang
Open-domain question answering (QA) systems are often built with retrieval modules.
1 code implementation • 17 Aug 2023 • Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, Lu Wang
The standard approach for ICL is to prompt the LM with concatenated demonstrations followed by the test input.
1 code implementation • 24 May 2023 • Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, Lu Wang
To address this issue, we propose Guiding chain-of-thought ReAsoning with a CorrectnEss Discriminator (GRACE), a stepwise decoding approach that steers the decoding process towards producing correct reasoning steps.
no code implementations • 21 May 2023 • Oana Ignat, Zhijing Jin, Artem Abzaliev, Laura Biester, Santiago Castro, Naihao Deng, Xinyi Gao, Aylin Gunal, Jacky He, Ashkan Kazemi, Muhammad Khalifa, Namho Koh, Andrew Lee, Siyang Liu, Do June Min, Shinka Mori, Joan Nwatu, Veronica Perez-Rosas, Siqi Shen, Zekun Wang, Winston Wu, Rada Mihalcea
Not surprisingly, this has, in turn, made many NLP researchers -- especially those at the beginning of their careers -- worry about what NLP research area they should focus on.
2 code implementations • 19 May 2023 • Xin Liu, Muhammad Khalifa, Lu Wang
Energy-based models (EBMs) have gained popularity for controlled text generation due to their high applicability to a wide range of constraints.
no code implementations • 9 Nov 2022 • Hardy Hardy, Miguel Ballesteros, Faisal Ladhak, Muhammad Khalifa, Vittorio Castelli, Kathleen McKeown
Summarizing novel chapters is a difficult task due to the input length and the fact that sentences that appear in the desired summaries draw content from multiple places throughout the chapter.
no code implementations • 11 Oct 2022 • Muhammad Khalifa, Yogarshi Vyas, Shuai Wang, Graham Horwood, Sunil Mallya, Miguel Ballesteros
The standard classification setting where categories are fixed during both training and testing falls short in dynamic environments where new document categories could potentially emerge.
2 code implementations • 25 May 2022 • Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, Lu Wang
To alleviate the need for a large number of labeled question-document pairs for retriever training, we propose PromptRank, which relies on large language models prompting for multi-hop path reranking.
no code implementations • EMNLP 2021 • Muhammad Khalifa, Miguel Ballesteros, Kathleen McKeown
Dialogue summarization comes with its own peculiar challenges as opposed to news or scientific articles summarization.
no code implementations • 14 Apr 2021 • Muhammad Khalifa, Hesham Hassan, Aly Fahmy
In this paper, we investigate the zero-shot performance on Dialectal Arabic (DA) when fine-tuning a PLM on modern standard Arabic (MSA) data only -- identifying a significant performance drop when evaluating such models on DA.
1 code implementation • EACL 2021 • Muhammad Khalifa, Muhammad Abdul-Mageed, Khaled Shaalan
We propose to self-train pre-trained language models in zero- and few-shot scenarios to improve performance on data-scarce varieties using only resources from data-rich ones.
1 code implementation • ICLR 2021 • Muhammad Khalifa, Hady Elsahar, Marc Dymetman
From that optimal representation we then train a target controlled Autoregressive LM through an adaptive distributional variant of Policy Gradient.
no code implementations • EACL (GWC) 2021 • Mustafa Jarrar, Eman Karajah, Muhammad Khalifa, Khaled Shaalan
We present our progress in developing a novel algorithm to extract synonyms from bilingual dictionaries.
no code implementations • 21 Jul 2020 • Muhammad Khalifa, Aminul Islam
Predicting the potential success of a book in advance is vital in many applications.
no code implementations • 15 Aug 2019 • Muhammad Khalifa
With the recent explosion in the size and complexity of source codebases and software projects, the need for efficient source code search engines has increased dramatically.