Robin Jia

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models ACL 2026 Robust Data Watermarking in Language Models by Injecting Fictitious Knowledge ACL 2025 Language Models Can Infer Action Semantics for Symbolic Planners from Environment Feedback NAACL 2025 Mechanistic Interpretability of Emotion Inference in Large Language Models ACL 2025 Why Do Some Inputs Break Low-Bit LLM Quantization? EMNLP 2025 Verify with Caution: The Pitfalls of Relying on Imperfect Factuality Metrics ACL 2025 TLDR: Token-Level Detective Reward Model for Large Vision Language Models ICLR 2025 TokenSmith: Streamlining Data Editing, Search, and Inspection for Large-Scale Language Model Training and Interpretability EMNLP 2025 Rethinking Backdoor Detection Evaluation for Language Models EMNLP 2025 Promote, Suppress, Iterate: How Language Models Answer One-to-Many Factual Queries EMNLP 2025 When Parts Are Greater Than Sums: Individual LLM Components Can Outperform Full Models EMNLP 2024 Efficient End-to-End Visual Document Understanding with Rationale Distillation NAACL 2024 Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarks NAACL 2024 Pre-trained Large Language Models Use Fourier Features to Compute Addition NIPS 2024 Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression NIPS 2024 Proving membership in LLM pretraining data via data watermarks ACL 2024 Do Question Answering Modeling Improvements Hold Across Benchmarks? ACL 2023 Are Sample-Efficient NLP Models More Robust? ACL 2023 Estimating Large Language Model Capabilities without Labeled Test Data EMNLP 2023 Data Curation Alone Can Stabilize In-context Learning ACL 2023 SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examples EMNLP 2023 Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering EMNLP 2023 Benchmarking Long-tail Generalization with Likelihood Splits EACL 2023 How Predictable Are Large Language Model Capabilities? A Case Study on BIG-bench EMNLP 2023 Contrastive Novelty-Augmented Learning: Anticipating Outliers with Large Language Models ACL 2023 Knowledge Base Question Answering by Case-based Reasoning over Subgraphs ICML 2022 On Continual Model Refinement in Out-of-Distribution Data Streams ACL 2022 Analyzing Dynamic Adversarial Training Data in the Limit ACL 2022 Question Answering Infused Pre-training of General-Purpose Contextualized Representations ACL 2022 Generalization Differences between End-to-End and Neuro-Symbolic Vision-Language Reasoning Systems EMNLP 2022 On the Robustness of Reading Comprehension Models to Entity Renaming NAACL 2022 Models in the Loop: Aiding Crowdworkers with Generative Annotation Assistants NAACL 2022 To what extent do human explanations of model behavior align with actual model behavior? EMNLP 2021 Do Explanations Help Users Detect Errors in Open-Domain QA? An Evaluation of Spoken vs. Visual Explanations ACL 2021 The statistical advantage of automatic NLG metrics at the system level ACL 2021 Evaluation Examples are not Equally Informative: How should that change NLP Leaderboards? ACL 2021 Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking NIPS 2021 Evaluation Examples are not Equally Informative: How should that change NLP Leaderboards? IJCNLP 2021 The statistical advantage of automatic NLG metrics at the system level IJCNLP 2021 Do Explanations Help Users Detect Errors in Open-Domain QA? An Evaluation of Spoken vs. Visual Explanations IJCNLP 2021 Dynabench: Rethinking Benchmarking in NLP NAACL 2021 Swords: A Benchmark for Lexical Substitution with Improved Data Coverage and Quality NAACL 2021 Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little EMNLP 2021 Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation EMNLP 2021 Robustness and Adversarial Examples in Natural Language Processing EMNLP 2021 With Little Power Comes Great Responsibility EMNLP 2020 Selective Question Answering under Domain Shift ACL 2020 Robust Encodings: A Framework for Combating Adversarial Typos ACL 2020 On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise Tasks EMNLP 2020 Document-Level N-ary Relation Extraction with Multiscale Representation Learning NAACL 2019 MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehension EMNLP 2019 Proceedings of the 2nd Workshop on Machine Reading for Question Answering EMNLP 2019 Certified Robustness to Adversarial Word Substitutions EMNLP 2019 Certified Robustness to Adversarial Word Substitutions IJCNLP 2019 Know What You Don’t Know: Unanswerable Questions for SQuAD ACL 2018 Proceedings of the Workshop on Machine Reading for Question Answering ACL 2018 Delete, Retrieve, Generate: a Simple Approach to Sentiment and Style Transfer NAACL 2018 Adversarial Examples for Evaluating Reading Comprehension Systems EMNLP 2017 Data Recombination for Neural Semantic Parsing ACL 2016