1 code implementation • 13 Feb 2025 • Yung-Sung Chuang, Benjamin Cohen-Wang, Shannon Zejiang Shen, Zhaofeng Wu, Hu Xu, Xi Victoria Lin, James Glass, Shang-Wen Li, Wen-tau Yih
We introduce SelfCite, a novel self-supervised approach that aligns LLMs to generate high-quality, fine-grained, sentence-level citations for the statements in their generated responses.
1 code implementation • 7 Nov 2024 • Zhaofeng Wu, Xinyan Velocity Yu, Dani Yogatama, Jiasen Lu, Yoon Kim
We hypothesize that models acquire this capability through learning a shared representation space across heterogeneous data types (e. g., different languages and modalities), which places semantically similar inputs near one another, even if they are from different modalities/languages.
no code implementations • 21 Oct 2024 • Yihong Tang, Ao Qu, Zhaokai Wang, Dingyi Zhuang, Zhaofeng Wu, Wei Ma, Shenhao Wang, Yunhan Zheng, Zhan Zhao, Jinhua Zhao
Our central hypothesis is that mastering these basic spatial capabilities can significantly enhance a model's performance on composite spatial tasks requiring advanced spatial understanding and combinatorial problem-solving, with generalized improvements in visual-spatial tasks.
no code implementations • 18 Apr 2024 • Zhaofeng Wu, Ananth Balashankar, Yoon Kim, Jacob Eisenstein, Ahmad Beirami
In this work, we evaluate a simple approach for zero-shot cross-lingual alignment, where a reward model is trained on preference data in one source language and directly applied to other target languages.
no code implementations • 21 Mar 2024 • Margaret Y. Li, Alisa Liu, Zhaofeng Wu, Noah A. Smith
Ambiguity is an critical component of language that allows for more effective communication between speakers, but is often ignored in NLP.
1 code implementation • 21 Feb 2024 • William Merrill, Zhaofeng Wu, Norihito Naka, Yoon Kim, Tal Linzen
Do LMs infer the semantics of text from co-occurrence patterns in their training data?
1 code implementation • 11 Feb 2024 • Yihong Tang, Zhaokai Wang, Ao Qu, Yihao Yan, Zhaofeng Wu, Dingyi Zhuang, Jushi Kai, Kebing Hou, Xiaotong Guo, Han Zheng, Tiange Luo, Jinhua Zhao, Zhan Zhao, Wei Ma
Citywalk, a recently popular form of urban travel, requires genuine personalization and understanding of fine-grained requests compared to traditional itinerary planning.
no code implementations • 4 Dec 2023 • Chao Shen, Wenkang Zhan, Jian Tang, Zhaofeng Wu, Bo Xu, Chao Zhao, Zhanguo Wang
It standardizes deoxidation temperatures across various equipment and substrate materials, advancing the standardization research process in semiconductor preparation, a significant milestone in thin film growth technology.
1 code implementation • 5 Jul 2023 • Zhaofeng Wu, Linlu Qiu, Alexis Ross, Ekin Akyürek, Boyuan Chen, Bailin Wang, Najoung Kim, Jacob Andreas, Yoon Kim
The impressive performance of recent language models across a wide range of tasks suggests that they possess a degree of abstract reasoning skills.
no code implementations • 22 Jun 2023 • Chao Shen, Wenkang Zhan, Kaiyao Xin, Manyang Li, Zhenyu Sun, Hui Cong, Chi Xu, Jian Tang, Zhaofeng Wu, Bo Xu, Zhongming Wei, Chunlai Xue, Chao Zhao, Zhanguo Wang
Self-assembled InAs/GaAs quantum dots (QDs) have properties highly valuable for developing various optoelectronic devices such as QD lasers and single photon sources.
1 code implementation • 27 Apr 2023 • Alisa Liu, Zhaofeng Wu, Julian Michael, Alane Suhr, Peter West, Alexander Koller, Swabha Swayamdipta, Noah A. Smith, Yejin Choi
We find that the task remains extremely challenging, including for GPT-4, whose generated disambiguations are considered correct only 32% of the time in human evaluation, compared to 90% for disambiguations in our dataset.
1 code implementation • 19 Oct 2022 • Zhaofeng Wu, Robert L. Logan IV, Pete Walsh, Akshita Bhagia, Dirk Groeneveld, Sameer Singh, Iz Beltagy
We demonstrate that a simple recipe, continued pretraining that incorporates a trainable prompt during multi-task learning, leads to improved promptability in both zero- and few-shot settings compared to existing methods, up to 31% relative.
1 code implementation • 16 Oct 2022 • Zhaofeng Wu, Hao Peng, Nikolaos Pappas, Noah A. Smith
Document-level machine translation leverages inter-sentence dependencies to produce more coherent and consistent translations.
1 code implementation • 14 Oct 2022 • Zhaofeng Wu, William Merrill, Hao Peng, Iz Beltagy, Noah A. Smith
Many current NLP systems are built from language models trained to optimize unsupervised objectives on large amounts of raw text.
no code implementations • 3 Jan 2022 • Zhaofeng Wu
While end-to-end learning with fully differentiable models has enabled tremendous success in natural language process (NLP) and machine learning, there have been significant recent interests in learning with latent discrete structures to incorporate better inductive biases for improved end-task performance and better interpretability.
no code implementations • ACL 2022 • Hao Peng, Jungo Kasai, Nikolaos Pappas, Dani Yogatama, Zhaofeng Wu, Lingpeng Kong, Roy Schwartz, Noah A. Smith
One way to improve the efficiency is to bound the memory size.
1 code implementation • 10 Dec 2020 • Zhaofeng Wu, Hao Peng, Noah A. Smith
For natural language processing systems, two kinds of evidence support the use of text representations from neural language models "pretrained" on large unannotated corpora: performance on application-inspired benchmarks (Peters et al., 2018, inter alia), and the emergence of syntactic abstractions in those representations (Tenney et al., 2019, inter alia).
no code implementations • CRAC (ACL) 2021 • Zhaofeng Wu, Matt Gardner
Despite significant recent progress in coreference resolution, the quality of current state-of-the-art systems still considerably trails behind human-level performance.
no code implementations • 16 May 2020 • Zhaofeng Wu, Ding Zhao, Qiao Liang, Jiahui Yu, Anmol Gulati, Ruoming Pang
In automatic speech recognition (ASR), model pruning is a widely adopted technique that reduces model size and latency to deploy neural network models on edge devices with resource constraints.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
1 code implementation • WS 2019 • Zhaofeng Wu, Yan Song, Sicong Huang, Yuanhe Tian, Fei Xia
Natural language inference (NLI) is challenging, especially when it is applied to technical domains such as biomedical settings.