Search Results for author: Yuning Mao

Found 31 papers, 26 papers with code

Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts

no code implementations26 Feb 2024 Mikayel Samvelyan, Sharath Chandra Raparthy, Andrei Lupu, Eric Hambro, Aram H. Markosyan, Manish Bhatt, Yuning Mao, Minqi Jiang, Jack Parker-Holder, Jakob Foerster, Tim Rocktäschel, Roberta Raileanu

As large language models (LLMs) become increasingly prevalent across many real-world applications, understanding and enhancing their robustness to user inputs is of paramount importance.

Question Answering

RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training

1 code implementation7 Dec 2023 Jaehyung Kim, Yuning Mao, Rui Hou, Hanchao Yu, Davis Liang, Pascale Fung, Qifan Wang, Fuli Feng, Lifu Huang, Madian Khabsa

Under a unified evaluation of fine-tuned LMs by incorporating four representative perspectives of model robustness, we demonstrate the effectiveness of RoAST compared to state-of-the-art fine-tuning methods on six different types of LMs, which indicates its usefulness in practice.

Adversarial Robustness

MART: Improving LLM Safety with Multi-round Automatic Red-Teaming

no code implementations13 Nov 2023 Suyu Ge, Chunting Zhou, Rui Hou, Madian Khabsa, Yi-Chia Wang, Qifan Wang, Jiawei Han, Yuning Mao

Specifically, an adversarial LLM and a target LLM interplay with each other in an iterative manner, where the adversarial LLM aims to generate challenging prompts that elicit unsafe responses from the target LLM, while the target LLM is fine-tuned with safety aligned data on these adversarial prompts.

Instruction Following Response Generation

LIMA: Less Is More for Alignment

5 code implementations NeurIPS 2023 Chunting Zhou, PengFei Liu, Puxin Xu, Srini Iyer, Jiao Sun, Yuning Mao, Xuezhe Ma, Avia Efrat, Ping Yu, Lili Yu, Susan Zhang, Gargi Ghosh, Mike Lewis, Luke Zettlemoyer, Omer Levy

Large language models are trained in two stages: (1) unsupervised pretraining from raw text, to learn general-purpose representations, and (2) large scale instruction tuning and reinforcement learning, to better align to end tasks and user preferences.

Language Modelling reinforcement-learning

Residual Prompt Tuning: Improving Prompt Tuning with Residual Reparameterization

1 code implementation6 May 2023 Anastasia Razdaibiedina, Yuning Mao, Rui Hou, Madian Khabsa, Mike Lewis, Jimmy Ba, Amjad Almahairi

In this work, we introduce Residual Prompt Tuning - a simple and efficient method that significantly improves the performance and stability of prompt tuning.

Representation Deficiency in Masked Language Modeling

1 code implementation4 Feb 2023 Yu Meng, Jitin Krishnan, Sinong Wang, Qifan Wang, Yuning Mao, Han Fang, Marjan Ghazvininejad, Jiawei Han, Luke Zettlemoyer

In this work, we offer a new perspective on the consequence of such a discrepancy: We demonstrate empirically and theoretically that MLM pretraining allocates some model dimensions exclusively for representing $\texttt{[MASK]}$ tokens, resulting in a representation deficiency for real tokens and limiting the pretrained model's expressiveness when it is adapted to downstream data without $\texttt{[MASK]}$ tokens.

Language Modelling Masked Language Modeling

Progressive Prompts: Continual Learning for Language Models

2 code implementations29 Jan 2023 Anastasia Razdaibiedina, Yuning Mao, Rui Hou, Madian Khabsa, Mike Lewis, Amjad Almahairi

We introduce Progressive Prompts - a simple and efficient approach for continual learning in language models.

Continual Learning

Towards a Unified Multi-Dimensional Evaluator for Text Generation

2 code implementations13 Oct 2022 Ming Zhong, Yang Liu, Da Yin, Yuning Mao, Yizhu Jiao, PengFei Liu, Chenguang Zhu, Heng Ji, Jiawei Han

We re-frame NLG evaluation as a Boolean Question Answering (QA) task, and by guiding the model with different questions, we can use one evaluator to evaluate from multiple dimensions.

nlg evaluation Question Answering +4

UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning

1 code implementation ACL 2022 Yuning Mao, Lambert Mathias, Rui Hou, Amjad Almahairi, Hao Ma, Jiawei Han, Wen-tau Yih, Madian Khabsa

Recent parameter-efficient language model tuning (PELT) methods manage to match the performance of fine-tuning with much fewer trainable parameters and perform especially well when training data is limited.

Language Modelling Model Selection

Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusion

1 code implementation Findings (ACL) 2022 Yiqing Xie, Jiaming Shen, Sha Li, Yuning Mao, Jiawei Han

Typical DocRE methods blindly take the full document as input, while a subset of the sentences in the document, noted as the evidence, are often sufficient for humans to predict the relation of an entity pair.

Document-level Relation Extraction Relation

Extract, Denoise and Enforce: Evaluating and Improving Concept Preservation for Text-to-Text Generation

2 code implementations EMNLP 2021 Yuning Mao, Wenchang Ma, Deren Lei, Jiawei Han, Xiang Ren

In this paper, we present a systematic analysis that studies whether current seq2seq models, especially pre-trained language models, are good enough for preserving important input concepts and to what extent explicitly guiding generation with the concepts as lexical constraints is beneficial.

Conditional Text Generation Denoising

Taxonomy Completion via Triplet Matching Network

1 code implementation6 Jan 2021 Jieyu Zhang, Xiangchen Song, Ying Zeng, Jiaze Chen, Jiaming Shen, Yuning Mao, Lei LI

Previous approaches focus on the taxonomy expansion, i. e. finding an appropriate hypernym concept from the taxonomy for a new query concept.

Taxonomy Expansion

Rider: Reader-Guided Passage Reranking for Open-Domain Question Answering

1 code implementation1 Jan 2021 Yuning Mao, Pengcheng He, Xiaodong Liu, Yelong Shen, Jianfeng Gao, Jiawei Han, Weizhu Chen

Current open-domain question answering systems often follow a Retriever-Reader architecture, where the retriever first retrieves relevant passages and the reader then reads the retrieved passages to form an answer.

Natural Questions Open-Domain Question Answering +2

Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generation

2 code implementations24 Oct 2020 Yuning Mao, Xiang Ren, Heng Ji, Jiawei Han

Despite significant progress, state-of-the-art abstractive summarization methods are still prone to hallucinate content inconsistent with the source document.

Abstractive Text Summarization Keyphrase Extraction

Generation-Augmented Retrieval for Open-domain Question Answering

1 code implementation ACL 2021 Yuning Mao, Pengcheng He, Xiaodong Liu, Yelong Shen, Jianfeng Gao, Jiawei Han, Weizhu Chen

We demonstrate that the generated contexts substantially enrich the semantics of the queries and GAR with sparse representations (BM25) achieves comparable or better performance than state-of-the-art dense retrieval methods such as DPR.

Natural Questions Open-Domain Question Answering +4

Octet: Online Catalog Taxonomy Enrichment with Self-Supervision

no code implementations18 Jun 2020 Yuning Mao, Tong Zhao, Andrey Kan, Chenwei Zhang, Xin Luna Dong, Christos Faloutsos, Jiawei Han

We propose to distantly train a sequence labeling model for term extraction and employ graph neural networks (GNNs) to capture the taxonomy structure as well as the query-item-taxonomy interactions for term attachment.

Term Extraction

Learning Collaborative Agents with Rule Guidance for Knowledge Graph Reasoning

1 code implementation EMNLP 2020 Deren Lei, Gangrong Jiang, Xiaotao Gu, Kexuan Sun, Yuning Mao, Xiang Ren

Walk-based models have shown their advantages in knowledge graph (KG) reasoning by achieving decent performance while providing interpretable decisions.

reinforcement-learning Reinforcement Learning (RL)

Generating Representative Headlines for News Stories

2 code implementations26 Jan 2020 Xiaotao Gu, Yuning Mao, Jiawei Han, Jialu Liu, Hongkun Yu, You Wu, Cong Yu, Daniel Finnie, Jiaqi Zhai, Nicholas Zukoski

In this work, we study the problem of generating representative headlines for news stories.

Hierarchical Text Classification with Reinforced Label Assignment

1 code implementation IJCNLP 2019 Yuning Mao, Jingjing Tian, Jiawei Han, Xiang Ren

While existing hierarchical text classification (HTC) methods attempt to capture label hierarchies for model training, they either make local decisions regarding each label or completely ignore the hierarchy information during inference.

 Ranked #1 on Text Classification on RCV1 (Macro F1 metric)

General Classification text-classification +1

Facet-Aware Evaluation for Extractive Summarization

1 code implementation ACL 2020 Yuning Mao, Liyuan Liu, Qi Zhu, Xiang Ren, Jiawei Han

In this paper, we present a facet-aware evaluation setup for better assessment of the information coverage in extracted summaries.

Extractive Summarization Sentence +1

End-to-End Hierarchical Text Classification with Label Assignment Policy

no code implementations27 Sep 2018 Yuning Mao, Jingjing Tian, Jiawei Han, Xiang Ren

We present an end-to-end reinforcement learning approach to hierarchical text classification where documents are labeled by placing them at the right positions in a given hierarchy.

text-classification Text Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.