Eric Wallace

36 papers · 2018–2025 · 6 conferences · across top CS/AI conferences

Achievements

+15 more ↓

🌈 Renaissance Researcher (6) 🌉 Interdisciplinary Bridge 🏃 Academic Marathon (7) 🌍 Conference Polyglot (6) 🗺️ Taxonomy Completionist (61)

🏃 Academic Marathon (7) 🗺️ Taxonomy Completionist (61) 🌉 Interdisciplinary Bridge 🌟 Keyword Trendsetter Combo (3) 🤝 Dynamic Duo (14) 👥 Mega-Team (26) 🧬 Topic Evolution 🏆 Keyword Champion (5) 🌱 Topic Pioneer ❓ The Questioner (3) 💎 Century Club (36) 🗃️ Keyword Collector (131) 📈 Trend Setter ⚡ Prolific Year (9) 🔥 Unstoppable (8)

Conferences

EMNLP (10) ACL (8) ICML (8) ICLR (4) IJCNLP (3) NAACL (3)

Top co-authors

Sameer Singh (14) Matt Gardner (9) Shi Feng (8) Dan Klein (6) Jordan Boyd-Graber (4) Nikhil Kandpal (4) Jens Tuyls (3) Hannaneh Hajishirzi (3) Dawn Song (3) Luke Zettlemoyer (3)

Research topics

Privacy (1)

Keywords

language model (7) adversarial attack (7) neural network (7) saliency map (5) model interpretation (4) prompt engineering (3) gradient-guided search (3) question answering (3) model robustness (3) annotation artifact (3) model interpretability (3) large language model (3) self-supervised pretraining (2) few-shot learning (2) adversarial example (2) text classification (2) natural language processing (2) training datum (2) adversarial learning (2) transfer learning (2)

Papers

Unfamiliar Finetuning Examples Control How Language Models Hallucinate NAACL 2025 What Evidence Do Language Models Find Convincing? ACL 2024 Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation ICML 2024 Stealing part of a production language model ICML 2024 SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore ICLR 2024 The False Promise of Imitating Proprietary Language Models ICLR 2024 Measuring Forgetting of Memorized Training Examples ICLR 2023 InCoder: A Generative Model for Code Infilling and Synthesis ICLR 2023 Large Language Models Struggle to Learn Long-Tail Knowledge ICML 2023 Poisoning Language Models During Instruction Tuning ICML 2023 Analyzing Dynamic Adversarial Training Data in the Limit ACL 2022 Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models ACL 2022 Deduplicating Training Data Mitigates Privacy Risks in Language Models ICML 2022 Automated Crossword Solving ACL 2022 Calibrate Before Use: Improving Few-shot Performance of Language Models ICML 2021 Concealed Data Poisoning Attacks on NLP Models NAACL 2021 Detoxifying Language Models Risks Marginalizing Minority Voices NAACL 2021 Train Big, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers ICML 2020 Imitation Attacks and Defenses for Black-box Machine Translation Systems EMNLP 2020 Pretrained Transformers Improve Out-of-Distribution Robustness ACL 2020 Interpreting Predictions of NLP Models EMNLP 2020 Gradient-based Analysis of NLP Models is Manipulable EMNLP 2020 Evaluating Models’ Local Decision Boundaries via Contrast Sets EMNLP 2020 AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts EMNLP 2020 Universal Adversarial Triggers for Attacking and Analyzing NLP EMNLP 2019 Do NLP Models Know Numbers? Probing Numeracy in Embeddings EMNLP 2019 AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models EMNLP 2019 Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation ICML 2019 Compositional Questions Do Not Necessitate Multi-hop Reasoning ACL 2019 Misleading Failures of Partial-input Baselines ACL 2019 Universal Adversarial Triggers for Attacking and Analyzing NLP IJCNLP 2019 Do NLP Models Know Numbers? Probing Numeracy in Embeddings IJCNLP 2019 AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models IJCNLP 2019 Trick Me If You Can: Adversarial Writing of Trivia Challenge Questions ACL 2018 Pathologies of Neural Models Make Interpretations Difficult EMNLP 2018 Interpreting Neural Networks with Nearest Neighbors EMNLP 2018