---
title: "Jacob Andreas — all works — Elamur Research"
description: "All 62 works of Jacob Andreas in the Elamur Research library, the most cited first: our summaries where we have them, else the original."
canonical: "https://research.elamur.ai/free/en/authors/jacob-andreas/works/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/jacob-andreas/works/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Jacob Andreas](https://md.research.elamur.ai/free/en/authors/jacob-andreas/) / all works

# Jacob Andreas — all works

62 works · [← Jacob Andreas](https://md.research.elamur.ai/free/en/authors/jacob-andreas/)

1. **[Neural Module Networks](https://md.research.elamur.ai/free/en/papers/andreas-2015-neural-module-networks/) [IEEE Computer Society Conference on Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/)**Jacob Andreas, Marcus Rohrbach, Trevor Darrell, et al.*2015 · 1,140 citations*
2. **[Learning to Reason: End-to-End Module Networks for Visual Question Answering ↗](https://arxiv.org/abs/1704.05526) arXiv:1704.05526 · no summary yet**Ronghang Hu et al.*2017 · 621 citations*
3. **[Learning to Compose Neural Networks for Question Answering](https://md.research.elamur.ai/free/en/papers/andreas-2016-learning-compose-neural-networks-question/) [Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)](https://md.research.elamur.ai/free/en/venues/naacl/)**Jacob Andreas, Marcus Rohrbach, Trevor Darrell, et al.*2016 · 573 citations*
4. **[Experience Grounds Language](https://md.research.elamur.ai/free/en/papers/bisk-2020-experience-grounds-language/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Yonatan Bisk, Ari Holtzman, Jesse Thomason, et al.*2020 · 439 citations*
5. **[Modeling Relationships in Referential Expressions with Compositional Modular Networks ↗](https://doi.org/10.1109/cvpr.2017.470) IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yet**Ronghang Hu et al.*2017 · 415 citations*
6. **[Speaker-Follower Models for Vision-and-Language Navigation ↗](https://arxiv.org/abs/1806.02724) arXiv:1806.02724 · no summary yet**Daniel Fried et al.*2018 · 343 citations*
7. **[Good-Enough Compositional Data Augmentation](https://md.research.elamur.ai/free/en/papers/andreas-2020-good-enough-compositional-data-augmentation/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Jacob Andreas*2020 · 313 citations*
8. **[A Minimal Span-Based Neural Constituency Parser](https://md.research.elamur.ai/free/en/papers/stern-2017-minimal-span-based-neural-constituency/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Mitchell Stern, Jacob Andreas, Dan Klein*2017 · 311 citations*
9. **[Modular Multitask Reinforcement Learning with Policy Sketches ↗](https://arxiv.org/abs/1611.01796) arXiv (Cornell University) · no summary yet**Jacob Andreas, Dan Klein, Sergey Levine*2016 · 238 citations*
10. [**What learning algorithm is in-context learning? Investigations with linear models arXiv:2211.15661**Ekin Akyürek, Dale Schuurmans, Jacob Andreas, et al.*2022 · 236 citations*](https://md.research.elamur.ai/free/en/papers/akyurek-2022-learning-algorithm-context-learning-investigations/)
11. **[A Survey of Reinforcement Learning Informed by Natural Language ↗](https://arxiv.org/abs/1906.03926) arXiv:1906.03926 · no summary yet**Jelena Luketina et al.*2019 · 231 citations*
12. **[Reasoning about Pragmatics with Neural Listeners and Speakers](https://md.research.elamur.ai/free/en/papers/andreas-2016-reasoning-about-pragmatics-neural-listeners/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Jacob Andreas, Dan Klein*2016 · 205 citations*
13. [**Semantics-Based Machine Translation with Hyperedge Replacement Grammars**Bevan Jones, Jacob Andreas, Daniel Bauer, et al.*Machine translation · 180 citations*](https://md.research.elamur.ai/free/en/papers/jones-2012-semantics-based-machine-translation-hyperedge/)
14. **[Implicit Representations of Meaning in Neural Language Models ↗](https://aclanthology.org/2021.acl-long.143/) 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) · no summary yet**Belinda Z. Li, Maxwell Nye, Jacob Andreas*2021 · 175 citations*
15. **[Language Models as Agent Models](https://md.research.elamur.ai/free/en/papers/andreas-2022-language-models-as-agent-models/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Jacob Andreas*2022 · 165 citations*
16. **[Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks ↗](https://arxiv.org/abs/2307.02477) arXiv:2307.02477 · no summary yet**Zhaofeng Wu et al.*2023 · 139 citations*
17. **[Pre-Trained Language Models for Interactive Decision-Making ↗](https://arxiv.org/abs/2202.01771) arXiv:2202.01771 · no summary yet**Shuang Li et al.*2022 · 124 citations*
18. **[Semantic Parsing as Machine Translation ↗](https://aclanthology.org/P13-2009/) Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · no summary yet**Jacob Andreas, Andreas Vlachos, Stephen Clark*2013 · 123 citations*
19. **[Task-Oriented Dialogue as Dataflow Synthesis](https://md.research.elamur.ai/free/en/papers/andreas-2020-task-oriented-dialogue-as-dataflow/) [Transactions of the Association for Computational Linguistics (TACL)](https://md.research.elamur.ai/free/en/venues/tacl/)**Jacob Andreas, John Bufe, David Burkett, et al.*2020 · 121 citations*
20. **[Learning with Latent Language ↗](https://aclanthology.org/N18-1197/) Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · no summary yet**Jacob Andreas, Dan Klein, Sergey Levine*2018 · 121 citations*
21. **[Inspecting and Editing Knowledge Representations in Language Models ↗](https://arxiv.org/abs/2304.00740) arXiv:2304.00740 · no summary yet**Evan Hernandez, Belinda Z. Li, Jacob Andreas*2023 · 115 citations*
22. **[Unified Pragmatic Models for Generating and Following Instructions](https://md.research.elamur.ai/free/en/papers/fried-2018-unified-pragmatic-models-generating-following/) [Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)](https://md.research.elamur.ai/free/en/venues/naacl/)**Daniel Fried, Jacob Andreas, Dan Klein*2018 · 115 citations*
23. **[Alignment-Based Compositional Semantics for Instruction Following ↗](https://aclanthology.org/D15-1138/) Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · no summary yet**Jacob Andreas, Dan Klein*2015 · 114 citations*
24. **[Linearity of Relation Decoding in Transformer Language Models ↗](https://arxiv.org/abs/2308.09124) arXiv:2308.09124 · no summary yet**Evan Hernandez et al.*2023 · 82 citations*
25. [**Pragmatically Informative Text Generation**Sheng Shen, Daniel Fried, Jacob Andreas, et al.*English · 78 citations*](https://md.research.elamur.ai/free/en/papers/shen-2019-pragmatically-informative-text-generation/)
26. **[Guiding Pretraining in Reinforcement Learning with Large Language Models ↗](https://arxiv.org/abs/2302.06692) arXiv:2302.06692 · no summary yet**Yuqing Du et al.*2023 · 77 citations*
27. **[What Context Features Can Transformer Language Models Use?](https://md.research.elamur.ai/free/en/papers/connor-2021-what-context-features-can-transformer/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Joe O'Connor, Jacob Andreas*2021 · 77 citations*
28. **[How much do word embeddings encode about syntax? ↗](https://aclanthology.org/P14-2133/) Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · no summary yet**Jacob Andreas, Dan Klein*2014 · 77 citations*
29. **[Skill Induction and Planning with Latent Language ↗](https://arxiv.org/abs/2110.01517) arXiv:2110.01517 · no summary yet**Pratyusha Sharma, Antonio Torralba, Jacob Andreas*2021 · 73 citations*
30. **[Compositional Generalization for Neural Semantic Parsing via Span-level Supervised Attention ↗](https://aclanthology.org/2021.naacl-main.225/) Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · no summary yet**Pengcheng Yin et al.*2021 · 72 citations*
31. [**ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning arXiv:2504.01296**Bairu Hou, Yang Zhang, Jiabao Ji, et al.*2025 · 67 citations*](https://md.research.elamur.ai/free/en/papers/hou-2025-thinkprune-pruning-long-chain-thought/)
32. **[Decision-Oriented Dialogue for Human-AI Collaboration](https://md.research.elamur.ai/free/en/papers/lin-2024-decision-oriented-dialogue-human-ai/) [Transactions of the Association for Computational Linguistics (TACL)](https://md.research.elamur.ai/free/en/venues/tacl/)**Jessy Lin, Nicholas Tomlin, Jacob Andreas, et al.*2024 · 57 citations*
33. **[When and why are log-linear models self-normalizing? ↗](https://aclanthology.org/N15-1027/) Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · no summary yet**Jacob Andreas, Dan Klein*2015 · 55 citations*
34. **[Translating Neuralese ↗](https://aclanthology.org/P17-1022/) Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yet**Jacob Andreas, Anca Dragan, Dan Klein*2017 · 54 citations*
35. **[Characterizing Intrinsic Compositionality in Transformers with Tree Projections ↗](https://arxiv.org/abs/2211.01288) arXiv (Cornell University) · no summary yet**Shikhar Murty et al.*2022 · 43 citations*
36. **[Grokking of Hierarchical Structure in Vanilla Transformers ↗](https://aclanthology.org/2023.acl-short.38/) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · no summary yet**Shikhar Murty et al.*2023 · 39 citations*
37. **[In-Context Language Learning: Architectures and Algorithms ↗](https://arxiv.org/abs/2401.12973) arXiv (Cornell University) · no summary yet**Ekin Akyürek et al.*2024 · 37 citations*
38. **[The Surprising Effectiveness of Test-Time Training for Few-Shot Learning ↗](https://arxiv.org/abs/2411.07279) arXiv:2411.07279 · no summary yet**Ekin Akyürek et al.*2024 · 36 citations*
39. **[Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty ↗](https://arxiv.org/abs/2507.16806) arXiv (Cornell University) · no summary yet**Mehul Damani et al.*2025 · 24 citations*
40. **[Value-Agnostic Conversational Semantic Parsing ↗](https://aclanthology.org/2021.acl-long.284/) 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) · no summary yet**Emmanouil Antonios Platanios et al.*2021 · 23 citations*
41. **[Learning How Hard to Think: Input-Adaptive Allocation of LM Computation ↗](https://arxiv.org/abs/2410.04707) arXiv:2410.04707 · no summary yet**Mehul Damani et al.*2024 · 22 citations*
42. **[Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games? ↗](https://arxiv.org/abs/1711.02301) arXiv (Cornell University) · no summary yet**Maithra Raghu et al.*2017 · 21 citations*
43. **[Grounding Language with Points and Paths in Continuous Spaces ↗](https://aclanthology.org/W14-1607/) Proceedings of the Eighteenth Conference on Computational Natural Language Learning · no summary yet**Jacob Andreas, Dan Klein*2014 · 21 citations*
44. **[Pushdown Layers: Encoding Recursive Structure in Transformer Language Models ↗](https://aclanthology.org/2023.emnlp-main.195/) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · no summary yet**Shikhar Murty et al.*2023 · 16 citations*
45. **[Quantifying Adaptability in Pre-trained Language Models with 500 Tasks ↗](https://aclanthology.org/2022.naacl-main.346/) Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · no summary yet**Belinda Li et al.*2022 · 15 citations*
46. **[On the accuracy of self-normalized log-linear models ↗](https://arxiv.org/abs/1506.04147) arXiv (Cornell University) · no summary yet**Jacob Andreas et al.*2015 · 15 citations*
47. **[A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation](https://md.research.elamur.ai/free/en/papers/hou-2025-probabilistic-framework-llm-hallucination-detection/) [Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)](https://md.research.elamur.ai/free/en/venues/naacl/)**Bairu Hou, Yang Zhang, Jacob Andreas, et al.*2025 · 12 citations*
48. [**An Incomplete Loop: Deductive, Inductive, and Abductive Reasoning in Language Models arXiv:2404.03028**Emmy Liu, Graham Neubig, Jacob Andreas*2024 · 12 citations*](https://md.research.elamur.ai/free/en/papers/liu-2024-incomplete-loop-deductive-inductive-abductive/)
49. **[Analogs of Linguistic Structure in Deep Representations ↗](https://aclanthology.org/D17-1311/) Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · no summary yet**Jacob Andreas, Dan Klein*2017 · 10 citations*
50. **[Fuzzy Syntactic Reordering for Phrase-based Statistical Machine Translation ↗](https://aclanthology.org/W11-2127/) Proceedings of the Sixth Workshop on Statistical Machine Translation · no summary yet**Jacob Andreas, Nizar Habash, Owen Rambow*2011 · 10 citations*
51. [**Towards Semi-Automated Annotation for Prepositional Phrase Attachment**Sara Rosenthal, William Lipovsky, Kathleen McKeown, et al.*English · 10 citations*](https://md.research.elamur.ai/free/en/papers/rosenthal-2010-semi-automated-annotation-prepositional-phrase/)
52. **[Hierarchical Phrase-Based Sequence-to-Sequence Learning ↗](https://aclanthology.org/2022.emnlp-main.563/) Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · no summary yet**Bailin Wang et al.*2022 · 9 citations*
53. **[Bayesian Preference Elicitation with Language Models ↗](https://arxiv.org/abs/2403.05534) arXiv:2403.05534 · no summary yet**Kunal Handa et al.*2024 · 8 citations*
54. **[Training Language Models to Explain Their Own Computations ↗](https://arxiv.org/abs/2511.08579) arXiv (Cornell University) · no summary yet**Belinda Z. Li et al.*2025 · 7 citations*
55. **[The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding ↗](https://aclanthology.org/2023.findings-acl.351/) Findings of the Association for Computational Linguistics: ACL 2023 · no summary yet**Hao Fang et al.*2023 · 6 citations*
56. **[Language Modeling with Editable External Knowledge ↗](https://aclanthology.org/2025.findings-naacl.168/) Findings of the Association for Computational Linguistics: NAACL 2025 · no summary yet**Belinda Z. Li et al.*2025 · 4 citations*
57. **[ELF: Embedded Language Flows ↗](https://arxiv.org/abs/2605.10938) arXiv (Cornell University) · no summary yet**Keya Hu et al.*2026 · 3 citations*
58. **[ARC Is a Vision Problem! ↗](https://arxiv.org/abs/2511.14761) arXiv (Cornell University) · no summary yet**Hu, Keya et al.*2025 · 3 citations*
59. **[Regularized Conventions: Equilibrium Computation as a Model of Pragmatic Reasoning](https://md.research.elamur.ai/free/en/papers/jacob-2024-regularized-conventions-equilibrium-computation-as/) [Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)](https://md.research.elamur.ai/free/en/venues/naacl/)**Athul Jacob, Gabriele Farina, Jacob Andreas*2024 · 1 citation*
60. **[Alignment via Mutual Information ↗](https://aclanthology.org/2023.conll-1.32/) Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL) · no summary yet**Shinjini Ghosh et al.*2023 · 1 citation*
61. **[ExperienceIndex: Artifact-Grounded Memory ↗](https://arxiv.org/abs/2610.10091) arXiv (Cornell University) · no summary yet**Peter Baile Chen et al.*2026*
62. **[Teachable Reinforcement Learning via Advice Distillation ↗](https://arxiv.org/abs/2203.11197) arXiv (Cornell University) · no summary yet**Olivia Watkins et al.*2022*