1 code implementation • 25 Nov 2024 • Haozhan Shen, Kangjia Zhao, Tiancheng Zhao, Ruochen Xu, Zilun Zhang, Mingwei Zhu, Jianwei Yin
An image, especially with high-resolution, typically consists of numerous visual elements, ranging from dominant large objects to fine-grained detailed objects.
no code implementations • 6 Jul 2024 • Tiancheng Zhao, Qianqian Zhang, Kyusong Lee, Peng Liu, Lu Zhang, Chunxin Fang, Jiajia Liao, Kelei Jiang, Yibo Ma, Ruochen Xu
To further evaluate the model's capabilities, we proposed a benchmark dataset named Temporal Visual Needle in a Haystack.
no code implementations • 17 Jun 2024 • Zilun Zhang, Yutao Sun, Tiancheng Zhao, Leigang Sha, Ruochen Xu, Kyusong Lee, Jianwei Yin
Humans can retain old knowledge while learning new information, but Large Language Models (LLMs) often suffer from catastrophic forgetting when post-pretrained or supervised fine-tuned (SFT) on domain-specific data.
3 code implementations • 11 Apr 2024 • Zhenghao Lin, Zhibin Gou, Yeyun Gong, Xiao Liu, Yelong Shen, Ruochen Xu, Chen Lin, Yujiu Yang, Jian Jiao, Nan Duan, Weizhu Chen
Unlike traditional LMs that learn to predict every next token in a corpus, Rho-1 employs Selective Language Modeling (SLM), which selectively trains on useful tokens that aligned with the desired distribution.
1 code implementation • 8 Mar 2024 • Jio Oh, Soyeon Kim, Junseok Seo, Jindong Wang, Ruochen Xu, Xing Xie, Steven Euijong Whang
Unlike knowledge graphs, which are also used to evaluate LLMs, relational databases have integrity constraints that can be used to better construct complex in-depth questions and verify answers: (1) functional dependencies can be used to pinpoint critical keywords that an LLM must know to properly answer a given question containing certain attribute values; and (2) foreign key constraints can be used to join relations and construct multi-hop questions, which can be arbitrarily long and used to debug intermediate answers.
2 code implementations • 21 Feb 2024 • Kaijie Zhu, Jindong Wang, Qinlin Zhao, Ruochen Xu, Xing Xie
Our multifaceted analysis demonstrated the strong correlation between the basic abilities and an implicit Matthew effect on model size, i. e., larger models possess stronger correlations of the abilities.
no code implementations • 18 Feb 2024 • Yubo Ma, Zhibin Gou, Junheng Hao, Ruochen Xu, Shuohang Wang, Liangming Pan, Yujiu Yang, Yixin Cao, Aixin Sun, Hany Awadalla, Weizhu Chen
To make this task more practical and solvable for LLMs, we introduce a new task setting named tool-augmented scientific reasoning.
1 code implementation • 26 Dec 2023 • Linyi Yang, Shuibai Zhang, Zhuohao Yu, Guangsheng Bao, Yidong Wang, Jindong Wang, Ruochen Xu, Wei Ye, Xing Xie, Weizhu Chen, Yue Zhang
Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering.
no code implementations • 10 Nov 2023 • Jiazhan Feng, Ruochen Xu, Junheng Hao, Hiteshi Sharma, Yelong Shen, Dongyan Zhao, Weizhu Chen
Despite their impressive performance, any parsing errors will inevitably result in the failure of the execution of the external logical solver and no answer to the logical questions.
1 code implementation • 24 May 2023 • Dan Iter, Reid Pryzant, Ruochen Xu, Shuohang Wang, Yang Liu, Yichong Xu, Chenguang Zhu
Our method is based on the observation that the effectiveness of in-context demonstrations negatively correlates with the perplexity of the test example by a language model that was finetuned on that demonstration.
no code implementations • 22 May 2023 • Ruochen Xu, Song Wang, Yang Liu, Shuohang Wang, Yichong Xu, Dan Iter, Chenguang Zhu, Michael Zeng
We hypothesize that there is a hidden query for each summary sentence in a generic summarization annotation, and we utilize a large-scale pretrained language model to recover it.
no code implementations • 22 May 2023 • Yichong Xu, Ruochen Xu, Dan Iter, Yang Liu, Shuohang Wang, Chenguang Zhu, Michael Zeng
While large models such as GPT-3 demonstrate exceptional performance in zeroshot and fewshot summarization tasks, their extensive serving and fine-tuning costs hinder their utilization in various applications.
2 code implementations • 29 Mar 2023 • Yang Liu, Dan Iter, Yichong Xu, Shuohang Wang, Ruochen Xu, Chenguang Zhu
In this work, we present G-Eval, a framework of using large language models with chain-of-thoughts (CoT) and a form-filling paradigm, to assess the quality of NLG outputs.
1 code implementation • 17 Nov 2022 • Yulong Chen, Yang Liu, Ruochen Xu, ZiYi Yang, Chenguang Zhu, Michael Zeng, Yue Zhang
The high annotation costs and diverse demands of various summarization tasks motivate the development of few-shot summarization.
1 code implementation • 21 Aug 2022 • Pengcheng He, Baolin Peng, Liyang Lu, Song Wang, Jie Mei, Yang Liu, Ruochen Xu, Hany Hassan Awadalla, Yu Shi, Chenguang Zhu, Wayne Xiong, Michael Zeng, Jianfeng Gao, Xuedong Huang
Z-Code++ creates new state of the art on 9 out of 13 text summarization tasks across 5 languages.
1 code implementation • 26 Jul 2022 • Haoxuan You, Luowei Zhou, Bin Xiao, Noel Codella, Yu Cheng, Ruochen Xu, Shih-Fu Chang, Lu Yuan
Large-scale multi-modal contrastive pre-training has demonstrated great utility to learn transferable features for a range of downstream tasks by mapping multiple modalities into a shared embedding space.
1 code implementation • 22 May 2022 • Zhenhailong Wang, Manling Li, Ruochen Xu, Luowei Zhou, Jie Lei, Xudong Lin, Shuohang Wang, ZiYi Yang, Chenguang Zhu, Derek Hoiem, Shih-Fu Chang, Mohit Bansal, Heng Ji
The goal of this work is to build flexible video-language models that can generalize to various video-to-text tasks from few examples, such as domain-specific captioning, question answering, and future event prediction.
1 code implementation • ACL 2022 • Shuohang Wang, Yichong Xu, Yuwei Fang, Yang Liu, Siqi Sun, Ruochen Xu, Chenguang Zhu, Michael Zeng
Surprisingly, we found that REtrieving from the traINing datA (REINA) only can lead to significant gains on multiple NLG and NLU tasks.
2 code implementations • CVPR 2022 • Manling Li, Ruochen Xu, Shuohang Wang, Luowei Zhou, Xudong Lin, Chenguang Zhu, Michael Zeng, Heng Ji, Shih-Fu Chang
Vision-language (V+L) pretraining models have achieved great success in supporting multimedia applications by understanding the alignments between images and text.
no code implementations • Findings (ACL) 2022 • Yuwei Fang, Shuohang Wang, Yichong Xu, Ruochen Xu, Siqi Sun, Chenguang Zhu, Michael Zeng
Then we utilize a diverse of 4 English knowledge sources to provide more comprehensive coverage of knowledge in different formats.
no code implementations • 29 Sep 2021 • Haoxuan You, Luowei Zhou, Bin Xiao, Noel C Codella, Yu Cheng, Ruochen Xu, Shih-Fu Chang, Lu Yuan
Large-scale multimodal contrastive pretraining has demonstrated great utility to support high performance in a range of downstream tasks by mapping multiple modalities into a shared embedding space.
no code implementations • 1 Sep 2021 • Ruochen Xu, Yuwei Fang, Chenguang Zhu, Michael Zeng
It is often observed in knowledge-centric tasks (e. g., common sense question and answering, relation classification) that the integration of external knowledge such as entity representation into language models can help provide useful information to boost the performance.
2 code implementations • Findings (ACL) 2021 • Yichong Xu, Chenguang Zhu, Ruochen Xu, Yang Liu, Michael Zeng, Xuedong Huang
However, although a KG contains rich structural information, it lacks the context to provide a more precise understanding of the concepts.
Ranked #5 on
Common Sense Reasoning
on CommonsenseQA
(using extra training data)
1 code implementation • Asian Chapter of the Association for Computational Linguistics 2020 • Ruochen Xu, Chenguang Zhu, Yu Shi, Michael Zeng, Xuedong Huang
Cross-lingual Summarization (CLS) aims at producing a summary in the target language for an article in the source language.
1 code implementation • ACL 2020 • Mengzhou Xia, Antonios Anastasopoulos, Ruochen Xu, Yiming Yang, Graham Neubig
Given the complexity of combinations of tasks, languages, and domains in natural language processing (NLP) research, it is computationally prohibitive to exhaustively test newly proposed models on each possible experimental setting.
3 code implementations • Findings of the Association for Computational Linguistics 2020 • Chenguang Zhu, Ruochen Xu, Michael Zeng, Xuedong Huang
With the abundance of automatic meeting transcripts, meeting summarization is of great interest to both participants and other parties.
no code implementations • NAACL 2021 • Chenguang Zhu, William Hinthorn, Ruochen Xu, Qingkai Zeng, Michael Zeng, Xuedong Huang, Meng Jiang
Automatic abstractive summaries are found to often distort or fabricate facts in the article.
2 code implementations • ICLR 2020 • Zirui Wang, Jiateng Xie, Ruochen Xu, Yiming Yang, Graham Neubig, Jaime Carbonell
Learning multilingual representations of text has proven a successful method for many cross-lingual transfer learning tasks.
no code implementations • 15 Mar 2019 • Ruochen Xu, Tao Ge, Furu Wei
Its challenge is the lack of large-scale sentence-aligned parallel data.
no code implementations • 24 Feb 2019 • Aditi Chaudhary, Siddharth Dalmia, Junjie Hu, Xinjian Li, Austin Matthews, Aldrian Obaja Muis, Naoki Otani, Shruti Rijhwani, Zaid Sheikh, Nidhi Vyas, Xinyi Wang, Jiateng Xie, Ruochen Xu, Chunting Zhou, Peter J. Jansen, Yiming Yang, Lori Levin, Florian Metze, Teruko Mitamura, David R. Mortensen, Graham Neubig, Eduard Hovy, Alan W. black, Jaime Carbonell, Graham V. Horwood, Shabnam Tafreshi, Mona Diab, Efsun S. Kayi, Noura Farra, Kathleen McKeown
This paper describes the ARIEL-CMU submissions to the Low Resource Human Language Technologies (LoReHLT) 2018 evaluations for the tasks Machine Translation (MT), Entity Discovery and Linking (EDL), and detection of Situation Frames in Text and Speech (SF Text and Speech).
1 code implementation • EMNLP 2018 • Ruochen Xu, Yiming Yang, Naoki Otani, Yuexin Wu
Supervised methods for this problem rely on the availability of cross-lingual supervision, either using parallel corpora or bilingual lexicons as the labeled data for training, which may not be available for many low resource languages.
1 code implementation • ACL 2017 • Ruochen Xu, Yiming Yang
Using soft probabilistic predictions for the documents in a label-rich language as the (induced) supervisory labels in a parallel corpus of documents, we train classifiers successfully for new languages in which labeled training data are not available.
no code implementations • COLING 2016 • Andrew Hsi, Yiming Yang, Jaime Carbonell, Ruochen Xu
Event extraction has become one of the most important topics in information extraction, but to date, there is very limited work on leveraging cross-lingual training to boost performance.