Noah Goodman

Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability JMLR 2025 Eliciting Human Preferences with Language Models ICLR 2025 Value Profiles for Encoding Human Variation EMNLP 2025 What Makes a Maze Look Like a Maze? ICLR 2025 Automated Statistical Model Discovery with Language Models ICML 2024 Backtracing: Retrieving the Cause of the Query EACL 2024 Codebook Features: Sparse and Discrete Interpretability for Neural Networks ICML 2024 Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations CLeaR 2024 Hypothesis Search: Inductive Reasoning with Language Models ICLR 2024 pyvene: A Library for Understanding and Improving PyTorch Models via Interventions NAACL 2024 Feature Dropout: Revisiting the Role of Augmentations in Contrastive Learning NeurIPS 2023 Generating Language Corrections for Teaching Physical Control Tasks ICML 2023 Interpretability at Scale: Identifying Causal Mechanisms in Alpaca NeurIPS 2023 Learning to Compress Prompts with Gist Tokens NeurIPS 2023 Parsel🐍: Algorithmic Reasoning with Language Models by Composing Decompositions NeurIPS 2023 SIGHT: A Large Annotated Dataset on Student Insights Gathered from Higher Education Transcripts ACL 2023 Task Ambiguity in Humans and Language Models ICLR 2023 Understanding Social Reasoning in Language Models with Language Models NeurIPS 2023 Why think step by step? Reasoning emerges from the locality of experience NeurIPS 2023 Active Learning Helps Pretrained Models Learn the Intended Task NeurIPS 2022 Assistive Teaching of Motor Control Tasks to Humans NeurIPS 2022 Causal Distillation for Language Models NAACL 2022 CLEVRER-Humans: Describing Physical and Causal Events the Human Way NeurIPS 2022 Concadia: Towards Image-Based Text Generation with a Purpose EMNLP 2022 DABS 2.0: Improved Datasets and Algorithms for Universal Self-Supervision NeurIPS 2022 Foundation Posteriors for Approximate Probabilistic Inference NeurIPS 2022 Geoclidean: Few-Shot Generalization in Euclidean Geometry NeurIPS 2022 Improving Intrinsic Exploration with Language Abstractions NeurIPS 2022 Inducing Causal Structure for Interpretable Neural Networks ICML 2022 Language modeling via stochastic processes ICLR 2022 Mixed-effects transformers for hierarchical adaptation EMNLP 2022 STaR: Bootstrapping Reasoning With Reasoning NeurIPS 2022 Calibrate your listeners! Robust communication-based training for pragmatic speakers EMNLP 2021 Conditional Negative Sampling for Contrastive Learning of Visual Representations ICLR 2021 Contrastive Reinforcement Learning of Symbolic Reasoning Domains NeurIPS 2021 Emergent Communication of Generalizations NeurIPS 2021 Improving Compositionality of Neural Networks by Decoding Representations to Inputs NeurIPS 2021 Open-domain clarification question generation without question examples EMNLP 2021 Pragmatic Code Autocomplete AAAI 2021 Question Generation for Adaptive Education ACL 2021 Viewmaker Networks: Learning Views for Unsupervised Representation Learning ICLR 2021 Continual Adaptation for Efficient Machine Communication CoNLL 2020 Investigating Transferability in Pretrained Language Models EMNLP 2020 Language Through a Prism: A Spectral Approach for Multiscale Language Representations NeurIPS 2020 Meta-Amortized Variational Inference and Learning AAAI 2020 Shaping Visual Representations with Language for Few-Shot Classification ACL 2020 Differentiable Antithetic Sampling for Variance Reduction in Stochastic Variational Inference AISTATS 2019 DisSent: Learning Sentence Representations from Explicit Discourse Relations ACL 2019 Learning from Omission ACL 2019 Learning to Explain: Answering Why-Questions via Rephrasing ACL 2019 Lost in Machine Translation: A Method to Reduce Meaning Loss NAACL 2019 Shapeglot: Learning Language for Shape Differentiation ICCV 2019 Tensor Variable Elimination for Plated Factor Graphs ICML 2019 Variational Bayesian Optimal Experimental Design NeurIPS 2019 Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference AAAI 2019 Bias and Generalization in Deep Generative Models: An Empirical Study NeurIPS 2018 Multimodal Generative Models for Scalable Weakly-Supervised Learning NeurIPS 2018 Pragmatically Informative Image Captioning with Character-Level Inference NAACL 2018 Learning Disentangled Representations with Semi-Supervised Deep Generative Models NeurIPS 2017 C3: Lightweight Incrementalized MCMC for Probabilistic Programs using Continuations and Callsite Caching AISTATS 2016 Neurally-Guided Procedural Models: Amortized Inference for Procedural Graphics Programs using Neural Networks NeurIPS 2016 Generating Efficient MCMC Kernels from Probabilistic Programs AISTATS 2014 Learning and using language via recursive pragmatic reasoning about other agents NeurIPS 2013 Learning Stochastic Inverses NeurIPS 2013 Burn-in, bias, and the rationality of anchoring NeurIPS 2012 Lightweight Implementations of Probabilistic Programming Languages Via Transformational Compilation AISTATS 2011 Nonstandard Interpretations of Probabilistic Programs for Efficient Inference NeurIPS 2011 Help or Hinder: Bayesian Models of Social Goal Inference NeurIPS 2009 A Bayesian Framework for Cross-Situational Word-Learning NeurIPS 2007 Learning and using relational theories NeurIPS 2007