1 code implementation • 4 Apr 2024 • Ryo Kamoi, Sarkar Snigdha Sarathi Das, Renze Lou, Jihyun Janice Ahn, Yilun Zhao, Xiaoxin Lu, Nan Zhang, Yusen Zhang, Ranran Haoran Zhang, Sujeeth Reddy Vummanthala, Salika Dave, Shaobo Qin, Arman Cohan, Wenpeng Yin, Rui Zhang
This work introduces ReaLMistake, the first error detection benchmark consisting of objective, realistic, and diverse errors made by LLMs.
1 code implementation • 6 Mar 2024 • Hanzi Xu, Muhao Chen, Lifu Huang, Slobodan Vucetic, Wenpeng Yin
In recent years, few-shot and zero-shot learning, which learn to predict labels with limited annotated instances, have garnered significant attention.
1 code implementation • 28 Feb 2024 • Congying Xia, Chen Xing, Jiangshu Du, Xinyi Yang, Yihao Feng, ran Xu, Wenpeng Yin, Caiming Xiong
This paper presents FoFo, a pioneering benchmark for evaluating large language models' (LLMs) ability to follow complex, domain-specific formats, a crucial yet underexamined capability for their application as AI agents.
no code implementations • 24 Feb 2024 • Ying Shen, Zhiyang Xu, Qifan Wang, Yu Cheng, Wenpeng Yin, Lifu Huang
Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in diverse tasks across different domains, with an increasing focus on improving their zero-shot generalization capabilities for unseen multimodal tasks.
1 code implementation • 17 Feb 2024 • Tianyi Yan, Fei Wang, James Y. Huang, Wenxuan Zhou, Fan Yin, Aram Galstyan, Wenpeng Yin, Muhao Chen
Instruction tuning has been used as a promising approach to improve the performance of large language models (LLMs) on unseen tasks.
no code implementations • 16 Feb 2024 • Zihao Lin, Mohammad Beigi, Hongxuan Li, Yufan Zhou, Yuxiang Zhang, Qifan Wang, Wenpeng Yin, Lifu Huang
Our in-depth study advocates more careful use of ME in real-world scenarios.
no code implementations • 31 Jan 2024 • Janice Ahn, Rishu Verma, Renze Lou, Di Liu, Rui Zhang, Wenpeng Yin
Mathematical reasoning serves as a cornerstone for assessing the fundamental cognitive capabilities of human intelligence.
1 code implementation • 30 Jan 2024 • Ibraheem Muhammad Moosa, Rui Zhang, Wenpeng Yin
Traditionally, Machine Translation (MT) Evaluation has been treated as a regression problem -- producing an absolute translation-quality score.
no code implementations • 11 Dec 2023 • Jiaxu Zhao, Meng Fang, Shirui Pan, Wenpeng Yin, Mykola Pechenizkiy
In this work, we propose a bias evaluation framework named GPTBIAS that leverages the high performance of LLMs (e. g., GPT-4 \cite{openai2023gpt4}) to assess bias in models.
no code implementations • 5 Dec 2023 • Renze Lou, Kai Zhang, Jian Xie, Yuxuan Sun, Janice Ahn, Hanzi Xu, Yu Su, Wenpeng Yin
In the realm of large language models (LLMs), enhancing instruction-following capability often involves curating expansive training data.
1 code implementation • 7 Nov 2023 • Sarkar Snigdha Sarathi Das, Ranran Haoran Zhang, Peng Shi, Wenpeng Yin, Rui Zhang
Unfortunately, this requires formatting them into specialized augmented format unknown to the base pretrained language model (PLMs) necessitating finetuning to the target format.
no code implementations • 7 Sep 2023 • Jiangshu Du, Congying Xia, Wenpeng Yin, TingTing Liang, Philip S. Yu
In intent detection tasks, leveraging meaningful semantic information from intent labels can be particularly beneficial for few-shot scenarios.
1 code implementation • 4 Aug 2023 • Renze Lou, Wenpeng Yin
This work proposes a challenging yet more realistic setting for zero-shot cross-task generalization: zero-shot instruction following, presuming the existence of a paragraph-style task definition while no demonstrations exist.
1 code implementation • 18 Mar 2023 • Renze Lou, Kai Zhang, Wenpeng Yin
This survey paper tries to summarize and provide insights to the current research on instruction following, particularly, by answering the following questions: (i) What is task instruction, and what instruction types exist?
1 code implementation • 7 Dec 2022 • Jiasheng Gu, Hongyu Zhao, Hanzi Xu, Liangyu Nie, Hongyuan Mei, Wenpeng Yin
To our knowledge, this is the first work that systematically studies how robust a PLM is when it is supervised by instructions with different factors of variability.
1 code implementation • 1 Dec 2022 • Jiangshu Du, Wenpeng Yin, Congying Xia, Philip S. Yu
To deal with the two issues, this work first proposes a contextualized TE model (Context-TE) by appending other k options as the context of the current (P, H) modeling.
1 code implementation • 25 Oct 2022 • Hanzi Xu, Slobodan Vucetic, Wenpeng Yin
To our knowledge, this is the first work that studies stance detection under the open-domain zero-shot setting.
no code implementations • Findings (NAACL) 2022 • Chang Tian, Wenpeng Yin, Marie-Francine Moens
This problem is detrimental to RL-based dialogue policy learning.
1 code implementation • 23 Mar 2022 • Tian Xie, Xinyi Yang, Angela S. Lin, Feihong Wu, Kazuma Hashimoto, Jin Qu, Young Mo Kang, Wenpeng Yin, Huan Wang, Semih Yavuz, Gang Wu, Michael Jones, Richard Socher, Yingbo Zhou, Wenhao Liu, Caiming Xiong
At the core of the struggle is the need to script every single turn of interactions between the bot and the human user.
no code implementations • ACL 2022 • Wenpeng Yin, Jia Li, Caiming Xiong
This work defines a new learning paradigm ConTinTin (Continual Learning from Task Instructions), in which a system should learn a sequence of new tasks one by one, each task is explained by a piece of textual instruction.
1 code implementation • 12 Feb 2022 • Bangzheng Li, Wenpeng Yin, Muhao Chen
The task of ultra-fine entity typing (UFET) seeks to predict diverse and free-form words or phrases that describe the appropriate types of entities mentioned in sentences.
Ranked #1 on Entity Typing on FIGER
1 code implementation • 15 Dec 2021 • Xiaodong Yu, Wenpeng Yin, Nitish Gupta, Dan Roth
Third, we retrain and evaluate two state-of-the-art (SOTA) entity linking models, showing the challenges of event linking, and we propose an event-specific linking system EVELINK to set a competitive result for the new task.
no code implementations • 20 Nov 2021 • Wenpeng Yin, Shelby Heinecke, Jia Li, Nitish Shirish Keskar, Michael Jones, Shouzhong Shi, Stanislav Georgiev, Kurt Milich, Joseph Esposito, Caiming Xiong
The distribution gap between training datasets and data encountered in production is well acknowledged.
1 code implementation • Findings (ACL) 2021 • Wenpeng Yin, Dragomir Radev, Caiming Xiong
It has been studied intensively in the past few years thanks to the availability of large-scale labeled datasets.
1 code implementation • NAACL 2021 • Congying Xia, Wenpeng Yin, Yihao Feng, Philip Yu
Two major challenges exist in this new task: (i) For the learning process, the system should incrementally learn new classes round by round without re-training on the examples of preceding classes; (ii) For the performance, the system should perform well on new classes without much loss on preceding classes.
1 code implementation • NAACL 2021 • Bailin Wang, Wenpeng Yin, Xi Victoria Lin, Caiming Xiong
Moreover, explicitly modeling compositions using PCFG leads to a better exploration of unseen programs, thus generate more diverse data.
no code implementations • *SEM (NAACL) 2022 • Xiaodong Yu, Wenpeng Yin, Dan Roth
Natural Language Processing tasks such as resolving the coreference of events require understanding the relations between two text snippets.
1 code implementation • EMNLP 2020 • Wenpeng Yin, Nazneen Fatema Rajani, Dragomir Radev, Richard Socher, Caiming Xiong
We demonstrate that this framework enables a pretrained entailment model to work well on new entailment domains in a few-shot setting, and show its effectiveness as a unified solver for several downstream NLP tasks such as question answering and coreference resolution when the end-task annotations are limited.
no code implementations • COLING 2020 • Lichao Sun, Congying Xia, Wenpeng Yin, TingTing Liang, Philip S. Yu, Lifang He
Our studies show that mixup is a domain-independent data augmentation technique to pre-trained language models, resulting in significant performance improvement for transformer-based models.
no code implementations • 19 Jul 2020 • Wenpeng Yin
If the target task itself cannot provide more information, how about collecting more tasks equipped with rich annotations to help the model learning?
no code implementations • 17 Jun 2020 • Andre Esteva, Anuprit Kale, Romain Paulus, Kazuma Hashimoto, Wenpeng Yin, Dragomir Radev, Richard Socher
The COVID-19 global pandemic has resulted in international efforts to understand, track, and mitigate the disease, yielding a significant corpus of COVID-19 and SARS-CoV-2-related publications across scientific disciplines.
no code implementations • 27 Feb 2020 • Lichao Sun, Kazuma Hashimoto, Wenpeng Yin, Akari Asai, Jia Li, Philip Yu, Caiming Xiong
There is an increasing amount of literature that claims the brittleness of deep neural networks in dealing with adversarial examples that are created maliciously.
4 code implementations • IJCNLP 2019 • Wenpeng Yin, Jamaal Hay, Dan Roth
0Shot-TC aims to associate an appropriate label with a piece of text, irrespective of the text domain and the aspect (e. g., topic, emotion, event, etc.)
no code implementations • 16 Aug 2019 • Jianquan Li, Xiaokang Liu, Wenpeng Yin, Min Yang, Liqun Ma, Yaohong Jin
Multi-Task Learning (MTL) aims at boosting the overall performance of each individual task by leveraging useful information contained in multiple related tasks.
1 code implementation • 8 Jun 2019 • Sihao Chen, Daniel Khashabi, Wenpeng Yin, Chris Callison-Burch, Dan Roth
Inherently, this is a natural language understanding task, and we propose to address it as such.
1 code implementation • NAACL 2019 • Sihao Chen, Daniel Khashabi, Wenpeng Yin, Chris Callison-Burch, Dan Roth
Inherently, this is a natural language understanding task, and we propose to address it as such.
1 code implementation • EMNLP 2018 • Wenpeng Yin, Dan Roth
We develop TwoWingOS (two-wing optimization strategy), a system that, while identifying appropriate evidence for a claim, also determines whether or not the claim is supported by the evidence.
no code implementations • COLING 2018 • Wenpeng Yin, Yadollah Yaghoobzadeh, Hinrich Schütze
Large scale knowledge graphs (KGs) such as Freebase are generally incomplete.
no code implementations • SEMEVAL 2018 • Wenpeng Yin, Dan Roth
Existing methods of hypernymy detection mainly rely on statistics over a big corpus, either mining some co-occurring patterns like "animals such as cats" or embedding words of interest into context-aware vectors.
1 code implementation • ACL 2018 • Wenpeng Yin, Hinrich Schütze, Dan Roth
This work deals with SciTail, a natural entailment challenge derived from a multi-choice question answering problem.
1 code implementation • TACL 2018 • Wenpeng Yin, Hinrich Schütze
We hypothesize that this is because the attention in CNNs has been mainly implemented as attentive pooling (i. e., it is applied to pooling) rather than as attentive convolution (i. e., it is integrated into convolution).
no code implementations • ACL 2017 • Mo Yu, Wenpeng Yin, Kazi Saidul Hasan, Cicero dos Santos, Bing Xiang, Bo-Wen Zhou
Relation detection is a core component for many NLP applications including Knowledge Base Question Answering (KBQA).
4 code implementations • 7 Feb 2017 • Wenpeng Yin, Katharina Kann, Mo Yu, Hinrich Schütze
Deep neural networks (DNN) have revolutionized the field of natural language processing (NLP).
no code implementations • EACL 2017 • Wenpeng Yin, Hinrich Schütze
This work studies comparatively two typical sentence matching tasks: textual entailment (TE) and answer selection (AS), observing that weaker phrase alignments are more critical in TE, while stronger phrase alignments deserve more attention in AS.
no code implementations • COLING 2016 • Wenpeng Yin, Mo Yu, Bing Xiang, Bo-Wen Zhou, Hinrich Schütze
In fact selection, we match the subject entity in a fact candidate with the entity mention in the question by a character-level convolutional neural network (char-CNN), and match the predicate in that fact with the question by a word-level CNN (word-CNN).
no code implementations • 23 Apr 2016 • Wenpeng Yin, Hinrich Schütze
We address the problems of identifying phrase alignments of flexible granularity and pooling alignments of different intensities for these tasks.
no code implementations • HLT 2015 • Wenpeng Yin, Hinrich Schütze
This work, concerning paraphrase identification task, on one hand contributes to expanding deep learning embeddings to include continuous and discontinuous linguistic phrases.
no code implementations • EMNLP 2015 • Wenpeng Yin, Tobias Schnabel, Hinrich Schütze
We propose online unsupervised domain adaptation (DA), which is performed incrementally as data comes in and is applicable when batch DA is not possible.
Online unsupervised domain adaptation Part-Of-Speech Tagging +2
no code implementations • CONLL 2015 • Wenpeng Yin, Hinrich Schütze
We propose MVCNN, a convolution neural network (CNN) architecture for sentence classification.
no code implementations • WS 2016 • Wenpeng Yin, Sebastian Ebert, Hinrich Schütze
Understanding open-domain text is one of the primary challenges in natural language processing (NLP).
8 code implementations • TACL 2016 • Wenpeng Yin, Hinrich Schütze, Bing Xiang, Bo-Wen Zhou
(ii) We propose three attention schemes that integrate mutual influence between sentences into CNN; thus, the representation of each sentence takes into consideration its counterpart.
1 code implementation • 18 Aug 2015 • Wenpeng Yin, Hinrich Schütze
Word embeddings -- distributed representations of words -- in deep learning are beneficial for many tasks in natural language processing (NLP).
no code implementations • 18 Dec 2013 • Wenpeng Yin, Hinrich Schütze
Deep learning embeddings have been successfully used for many natural language processing problems.