Tatsunori Hashimoto

Auditing Prompt Caching in Language Model APIs ICML 2025 AutoBencher: Towards Declarative Benchmark Construction ICLR 2025 Benchmarking Distributional Alignment of Large Language Models NAACL 2025 Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers ICLR 2025 Eliciting Language Model Behaviors with Investigator Agents ICML 2025 Improving Pretraining Data Using Perplexity Correlations ICLR 2025 Language Confusion and Multilingual Performance: A Case Study of Thai-Adapted Large Language Models AACL 2025 Learning to (Learn at Test Time): RNNs with Expressive Hidden States ICML 2025 Locality Alignment Improves Vision-Language Models ICLR 2025 Online Conformal Prediction via Online Optimization ICML 2025 s1: Simple test-time scaling EMNLP 2025 Synthetic continued pretraining ICLR 2025 Benchmarking and Improving Generator-Validator Consistency of Language Models ICLR 2024 Graph-based Uncertainty Metrics for Long-form Language Model Generations NeurIPS 2024 Identifying the Risks of LM Agents with an LM-Emulated Sandbox ICLR 2024 Language Models with Conformal Factuality Guarantees ICML 2024 Linguistic Calibration of Long-Form Generations ICML 2024 Observational Scaling Laws and the Predictability of Langauge Model Performance NeurIPS 2024 One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention ICLR 2024 On the Fairness ROAD: Robust Optimization for Adversarial Debiasing ICLR 2024 On the Learnability of Watermarks for Language Models ICLR 2024 Proving Test Set Contamination in Black-Box Language Models ICLR 2024 Removing RLHF Protections in GPT-4 via Fine-Tuning NAACL 2024 Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions ICLR 2024 Scaling Laws for the Value of Individual Data Points in Machine Learning ICML 2024 Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution NeurIPS 2024 Trustless Audits without Revealing Data or Models ICML 2024 Understanding Finetuning for Factual Knowledge Extraction ICML 2024 Coder Reviewer Reranking for Code Generation ICML 2023 Contrastive Decoding: Open-ended Text Generation as Optimization ACL 2023 Contrastive Error Attribution for Finetuned Language Models ACL 2023 Data Feedback Loops: Model-driven Amplification of Dataset Biases ICML 2023 Evaluating Self-Supervised Learning via Risk Decomposition ICML 2023 Foundation Models and Fair Use JMLR 2023 Is a Caption Worth a Thousand Images? A Study on Representation Learning ICLR 2023 Navigating the Grey Area: How Expressions of Uncertainty and Overconfidence Affect Language Models EMNLP 2023 Out-of-Domain Robustness via Targeted Augmentations ICML 2023 Privacy-Preserving Domain Adaptation of Semantic Parsers ACL 2023 TempLM: Distilling Language Models into Template-Based Generators ACL 2023 When Do Pre-Training Biases Propagate to Downstream Tasks? A Case Study in Text Summarization EACL 2023 Whose Opinions Do Language Models Reflect? ICML 2023 Distributionally Robust Models with Parametric Likelihood Ratios ICLR 2022 Extending the WILDS Benchmark for Unsupervised Adaptation ICLR 2022 Identifiability Conditions for Domain Adaptation ICML 2022 Is Importance Weighting Incompatible with Interpolating Classifiers? ICLR 2022 Language modeling via stochastic processes ICLR 2022 Large Language Models Can Be Strong Differentially Private Learners ICLR 2022 Spurious Correlations in Reference-Free Evaluation of Text Generation ACL 2022 Measuring Conversational Uptake: A Case Study on Student-Teacher Interactions ACL 2021 Modeling the Second Player in Distributionally Robust Optimization ICLR 2021 Model Performance Scaling with Multiple Data Sources ICML 2021 The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics ACL 2021 Robustness to Spurious Correlations via Human Annotations ICML 2020 Inferring Multidimensional Rates of Aging from Cross-Sectional Data AISTATS 2019 Derivative Free Optimization Via Repeated Classification AISTATS 2018 Fairness Without Demographics in Repeated Loss Minimization ICML 2018 Learning Population-Level Diffusions with Generative RNNs ICML 2016 From random walks to distances on unweighted graphs NeurIPS 2015 Metric recovery from directed unweighted graphs AISTATS 2015