Personal information

No personal information available

Activities

Collapse all

Employment (1)

University of Southern California: Los Angeles, US

2021-08 to present | Assistant Professor (Computer Science)
Employment
Source: Self-asserted source
Robin Jia

Education and qualifications (2)

Stanford University: Stanford, US

2014-09 to 2020-08 | Ph.D. (Computer Science)
Education
Source: Self-asserted source
Robin Jia

Stanford University: Stanford, US

2010-09 to 2014-06 | B.S. (Computer Science)
Education
Source: Self-asserted source
Robin Jia

Works (31)

Pre-trained Large Language Models Use Fourier Features to Compute Addition

Conference on Neural Information Processing Systems (NeurIPS)
2024 | Conference paper | Writing - original draft
Contributors: Tianyi Zhou; Deqing Fu; Vatsal Sharan; Robin Jia
Source: Self-asserted source
Robin Jia

Proving membership in LLM pretraining data via data watermarks

Findings of the Association for Computational Linguistics ACL 2024
2024 | Conference paper
DOI: 10.18653/v1/2024.findings-acl.788
Contributors: Johnny Wei; Ryan Wang; Robin Jia
Source: Self-asserted source
Robin Jia

Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Models

Conference on Neural Information Processing Systems (NeurIPS)
2024 | Conference paper
Contributors: Deqing Fu; Tian-Qi Chen; Robin Jia; Vatsal Sharan
Source: Self-asserted source
Robin Jia

Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarks

Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
2024-06 | Conference paper
URI:

https://aclanthology.org/2024.naacl-long.176
Contributors: Chang, Ting-Yun and Thomason, Jesse and Jia, Robin; Duh, Kevin and Gomez, Helena and Bethard, Steven
Source: Self-asserted source
Robin Jia

Efficient End-to-End Visual Document Understanding with Rationale Distillation

Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
2024-06 | Conference paper
URI:

https://aclanthology.org/2024.naacl-long.465
Contributors: Zhu, Wang and Agarwal, Alekh and Joshi, Mandar and Jia, Robin and Thomason, Jesse and Toutanova, Kristina; Duh, Kevin and Gomez, Helena and Bethard, Steven
Source: Self-asserted source
Robin Jia

Are Sample-Efficient NLP Models More Robust?

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
2023 | Conference paper
DOI: 10.18653/v1/2023.acl-short.144
Contributors: Nelson F. Liu; Ananya Kumar; Percy Liang; Robin Jia
Source: Self-asserted source
Robin Jia

Benchmarking Long-tail Generalization with Likelihood Splits

Findings of the Association for Computational Linguistics: EACL 2023
2023 | Conference paper
DOI: 10.18653/v1/2023.findings-eacl.71
Contributors: Ameya Godbole; Robin Jia
Source: Self-asserted source
Robin Jia

Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
2023 | Conference paper
DOI: 10.18653/v1/2023.emnlp-main.547
Contributors: Wang Zhu; Jesse Thomason; Robin Jia
Source: Self-asserted source
Robin Jia

Contrastive Novelty-Augmented Learning: Anticipating Outliers with Large Language Models

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
2023 | Conference paper
DOI: 10.18653/v1/2023.acl-long.658
Contributors: Albert Xu; Xiang Ren; Robin Jia
Source: Self-asserted source
Robin Jia

Data Curation Alone Can Stabilize In-context Learning

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
2023 | Conference paper
DOI: 10.18653/v1/2023.acl-long.452
Contributors: Ting-Yun Chang; Robin Jia
Source: Self-asserted source
Robin Jia

Do Question Answering Modeling Improvements Hold Across Benchmarks?

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
2023 | Conference paper
DOI: 10.18653/v1/2023.acl-long.736
Contributors: Nelson F. Liu; Tony Lee; Robin Jia; Percy Liang
Source: Self-asserted source
Robin Jia

Estimating Large Language Model Capabilities without Labeled Test Data

Findings of the Association for Computational Linguistics: EMNLP 2023
2023 | Conference paper
DOI: 10.18653/v1/2023.findings-emnlp.639
Contributors: Harvey Fu; Qinyuan Ye; Albert Xu; Xiang Ren; Robin Jia
Source: Self-asserted source
Robin Jia

How Predictable Are Large Language Model Capabilities? A Case Study on BIG-bench

Findings of the Association for Computational Linguistics: EMNLP 2023
2023 | Conference paper
DOI: 10.18653/v1/2023.findings-emnlp.503
Contributors: Qinyuan Ye; Harvey Fu; Xiang Ren; Robin Jia
Source: Self-asserted source
Robin Jia

SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examples

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
2023 | Conference paper
DOI: 10.18653/v1/2023.emnlp-main.485
Contributors: Deqing Fu; Ameya Godbole; Robin Jia
Source: Self-asserted source
Robin Jia

Analyzing Dynamic Adversarial Training Data in the Limit

Findings of the Association for Computational Linguistics: ACL 2022
2022 | Conference paper
DOI: 10.18653/v1/2022.findings-acl.18
Contributors: Eric Wallace; Adina Williams; Robin Jia; Douwe Kiela
Source: Self-asserted source
Robin Jia

Generalization Differences between End-to-End and Neuro-Symbolic Vision-Language Reasoning Systems

Findings of the Association for Computational Linguistics: EMNLP 2022
2022 | Conference paper
DOI: 10.18653/v1/2022.findings-emnlp.345
Contributors: Wang Zhu; Jesse Thomason; Robin Jia
Source: Self-asserted source
Robin Jia

Models in the Loop: Aiding Crowdworkers with Generative Annotation Assistants

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
2022 | Conference paper
DOI: 10.18653/v1/2022.naacl-main.275
Contributors: Max Bartolo; Tristan Thrush; Sebastian Riedel; Pontus Stenetorp; Robin Jia; Douwe Kiela
Source: Self-asserted source
Robin Jia

On the Robustness of Reading Comprehension Models to Entity Renaming

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
2022 | Conference paper
DOI: 10.18653/v1/2022.naacl-main.37
Contributors: Jun Yan; Yang Xiao; Sagnik Mukherjee; Bill Yuchen Lin; Robin Jia; Xiang Ren
Source: Self-asserted source
Robin Jia

Question Answering Infused Pre-training of General-Purpose Contextualized Representations

Findings of the Association for Computational Linguistics: ACL 2022
2022 | Conference paper
DOI: 10.18653/v1/2022.findings-acl.59
Contributors: Robin Jia; Mike Lewis; Luke Zettlemoyer
Source: Self-asserted source
Robin Jia

Do Explanations Help Users Detect Errors in Open-Domain QA? An Evaluation of Spoken vs. Visual Explanations

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021
2021 | Conference paper
DOI: 10.18653/v1/2021.findings-acl.95
Contributors: Ana Valeria González; Gagan Bansal; Angela Fan; Yashar Mehdad; Robin Jia; Srinivasan Iyer
Source: Self-asserted source
Robin Jia

Dynabench: Rethinking Benchmarking in NLP

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
2021 | Conference paper
DOI: 10.18653/v1/2021.naacl-main.324
Contributors: Douwe Kiela; Max Bartolo; Yixin Nie; Divyansh Kaushik; Atticus Geiger; Zhengxuan Wu; Bertie Vidgen; Grusha Prasad; Amanpreet Singh; Pratik Ringshia et al.
Source: Self-asserted source
Robin Jia

Evaluation Examples are not Equally Informative: How should that change NLP Leaderboards?

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
2021 | Conference paper
DOI: 10.18653/v1/2021.acl-long.346
Contributors: Pedro Rodriguez; Joe Barrow; Alexander Miserlis Hoyle; John P. Lalor; Robin Jia; Jordan Boyd-Graber
Source: Self-asserted source
Robin Jia

Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
2021 | Conference paper
DOI: 10.18653/v1/2021.emnlp-main.696
Contributors: Max Bartolo; Tristan Thrush; Robin Jia; Sebastian Riedel; Pontus Stenetorp; Douwe Kiela
Source: Self-asserted source
Robin Jia

Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
2021 | Conference paper
DOI: 10.18653/v1/2021.emnlp-main.230
Contributors: Koustuv Sinha; Robin Jia; Dieuwke Hupkes; Joelle Pineau; Adina Williams; Douwe Kiela
Source: Self-asserted source
Robin Jia

On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise Tasks

Findings of the Association for Computational Linguistics: EMNLP 2020
2020 | Conference paper
DOI: 10.18653/v1/2020.findings-emnlp.305
Contributors: Stephen Mussmann; Robin Jia; Percy Liang
Source: Self-asserted source
Robin Jia

Robust Encodings: A Framework for Combating Adversarial Typos

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
2020 | Conference paper
DOI: 10.18653/v1/2020.acl-main.245
Contributors: Erik Jones; Robin Jia; Aditi Raghunathan; Percy Liang
Source: Self-asserted source
Robin Jia

Selective Question Answering under Domain Shift

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
2020 | Conference paper
DOI: 10.18653/v1/2020.acl-main.503
Contributors: Amita Kamath; Robin Jia; Percy Liang
Source: Self-asserted source
Robin Jia

Certified Robustness to Adversarial Word Substitutions

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
2019 | Conference paper
DOI: 10.18653/v1/d19-1423
Contributors: Robin Jia; Aditi Raghunathan; Kerem Göksel; Percy Liang
Source: Self-asserted source
Robin Jia

Know What You Don’t Know: Unanswerable Questions for SQuAD

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
2018 | Conference paper
DOI: 10.18653/v1/p18-2124
Contributors: Pranav Rajpurkar; Robin Jia; Percy Liang
Source: Self-asserted source
Robin Jia

Adversarial Examples for Evaluating Reading Comprehension Systems

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
2017 | Conference paper
DOI: 10.18653/v1/d17-1215
Contributors: Robin Jia; Percy Liang
Source: Self-asserted source
Robin Jia

Data Recombination for Neural Semantic Parsing

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
2016 | Conference paper
DOI: 10.18653/v1/p16-1002
Contributors: Robin Jia; Percy Liang
Source: Self-asserted source
Robin Jia
How many people are using ORCID?