Search Results for author: Liwei Jiang

Found 22 papers, 8 papers with code

Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties

1 code implementation2 Sep 2023 Taylor Sorensen, Liwei Jiang, Jena Hwang, Sydney Levine, Valentina Pyatkin, Peter West, Nouha Dziri, Ximing Lu, Kavel Rao, Chandra Bhagavatula, Maarten Sap, John Tasioulas, Yejin Choi

To improve AI systems to better reflect value pluralism, the first-order challenge is to explore the extent to which AI systems can model pluralistic human values, rights, and duties as well as their interaction.

Decision Making

Faith and Fate: Limits of Transformers on Compositionality

no code implementations29 May 2023 Nouha Dziri, Ximing Lu, Melanie Sclar, Xiang Lorraine Li, Liwei Jiang, Bill Yuchen Lin, Peter West, Chandra Bhagavatula, Ronan Le Bras, Jena D. Hwang, Soumya Sanyal, Sean Welleck, Xiang Ren, Allyson Ettinger, Zaid Harchaoui, Yejin Choi

We formulate compositional tasks as computation graphs to systematically quantify the level of complexity, and break down reasoning steps into intermediate sub-procedures.

Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for Summarization and Paraphrasing

no code implementations26 May 2023 JaeHun Jung, Peter West, Liwei Jiang, Faeze Brahman, Ximing Lu, Jillian Fisher, Taylor Sorensen, Yejin Choi

It is commonly perceived that the strongest language models (LMs) rely on a combination of massive scale, instruction data, and human feedback to perform specialized tasks -- e. g. summarization and paraphrasing, without supervision.

BiasX: "Thinking Slow" in Toxic Content Moderation with Explanations of Implied Social Biases

no code implementations23 May 2023 Yiming Zhang, Sravani Nanduri, Liwei Jiang, Tongshuang Wu, Maarten Sap

Toxicity annotators and content moderators often default to mental shortcuts when making decisions.

Asymptotic normality and optimality in nonsmooth stochastic approximation

no code implementations16 Jan 2023 Damek Davis, Dmitriy Drusvyatskiy, Liwei Jiang

In their seminal work, Polyak and Juditsky showed that stochastic approximation algorithms for solving smooth equations enjoy a central limit theorem.

Open-Ended Question Answering

A Validation Approach to Over-parameterized Matrix and Image Recovery

no code implementations21 Sep 2022 Lijun Ding, Zhen Qin, Liwei Jiang, Jinxin Zhou, Zhihui Zhu

In this paper, we study the problem of recovering a low-rank matrix from a number of noisy random linear measurements.

Image Restoration

ProsocialDialog: A Prosocial Backbone for Conversational Agents

1 code implementation25 May 2022 Hyunwoo Kim, Youngjae Yu, Liwei Jiang, Ximing Lu, Daniel Khashabi, Gunhee Kim, Yejin Choi, Maarten Sap

With this dataset, we introduce a dialogue safety detection module, Canary, capable of generating RoTs given conversational context, and a socially-informed dialogue agent, Prost.

Dialogue Generation Dialogue Safety Prediction +2

Aligning to Social Norms and Values in Interactive Narratives

no code implementations NAACL 2022 Prithviraj Ammanabrolu, Liwei Jiang, Maarten Sap, Hannaneh Hajishirzi, Yejin Choi

We focus on creating agents that act in alignment with socially beneficial norms and values in interactive narratives or text-based games -- environments wherein an agent perceives and interacts with a world through natural language.

text-based games

Algorithmic Regularization in Model-free Overparametrized Asymmetric Matrix Factorization

no code implementations6 Mar 2022 Liwei Jiang, Yudong Chen, Lijun Ding

We study the asymmetric matrix factorization problem under a natural nonconvex formulation with arbitrary overparametrization.

NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics

1 code implementation NAACL 2022 Ximing Lu, Sean Welleck, Peter West, Liwei Jiang, Jungo Kasai, Daniel Khashabi, Ronan Le Bras, Lianhui Qin, Youngjae Yu, Rowan Zellers, Noah A. Smith, Yejin Choi

To enable constrained generation, we build on NeuroLogic decoding (Lu et al., 2021), combining its flexibility in incorporating logical constraints with A*esque estimates of future constraint satisfaction.

Machine Translation Table-to-Text Generation

Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact Recovery

no code implementations NeurIPS 2021 Lijun Ding, Liwei Jiang, Yudong Chen, Qing Qu, Zhihui Zhu

We study the robust recovery of a low-rank matrix from sparsely and grossly corrupted Gaussian measurements, with no prior knowledge on the intrinsic rank.

Active manifolds, stratifications, and convergence to local minima in nonsmooth optimization

no code implementations26 Aug 2021 Damek Davis, Dmitriy Drusvyatskiy, Liwei Jiang

We show that the subgradient method converges only to local minimizers when applied to generic Lipschitz continuous and subdifferentially regular functions that are definable in an o-minimal structure.

``I'm Not Mad'': Commonsense Implications of Negation and Contradiction

no code implementations NAACL 2021 Liwei Jiang, Antoine Bosselut, Chandra Bhagavatula, Yejin Choi

In this paper, we present the first comprehensive study focusing on commonsense implications of negated statements and contradictions.

Natural Language Inference

"I'm Not Mad": Commonsense Implications of Negation and Contradiction

no code implementations13 Apr 2021 Liwei Jiang, Antoine Bosselut, Chandra Bhagavatula, Yejin Choi

In this paper, we present the first comprehensive study focusing on commonsense implications of negated statements and contradictions.

Natural Language Inference

AUL is a better optimization metric in PU learning

no code implementations1 Jan 2021 Shangchuan Huang, Songtao Wang, Dan Li, Liwei Jiang

Recent works try to recover the unbiased result by estimating the proportion of positive samples with mixture proportion estimation (MPE) algorithms, but the model performance is still limited and heavy computational cost is introduced (particularly for big datasets).

Binary Classification

Improving Positive Unlabeled Learning: Practical AUL Estimation and New Training Method for Extremely Imbalanced Data Sets

no code implementations21 Apr 2020 Liwei Jiang, Dan Li, Qisheng Wang, Shuai Wang, Songtao Wang

Secondly, we propose ProbTagging, a new training method for extremely imbalanced data sets, where the number of unlabeled samples is hundreds or thousands of times that of positive samples.

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