---
title: "Ashish Sabharwal — all works — Elamur Research"
description: "All 52 works of Ashish Sabharwal 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/ashish-sabharwal/works/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/ashish-sabharwal/works/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Ashish Sabharwal](https://md.research.elamur.ai/free/en/authors/ashish-sabharwal/) / all works

# Ashish Sabharwal — all works

52 works · [← Ashish Sabharwal](https://md.research.elamur.ai/free/en/authors/ashish-sabharwal/)

1. [**Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge arXiv:1803.05457**Peter Clark, Isaac Cowhey, Oren Etzioni, et al.*2018 · 2,394 citations*](https://md.research.elamur.ai/free/en/papers/clark-2018-think-have-solved-question-answering/)
2. **[Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering ↗](https://aclanthology.org/D18-1260/) Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · no summary yet**Todor Mihaylov et al.*2018 · 1,687 citations*
3. **[UNIFIEDQA: Crossing Format Boundaries with a Single QA System](https://md.research.elamur.ai/free/en/papers/khashabi-2020-unifiedqa-crossing-format-boundaries-single/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Daniel Khashabi, Sewon Min, Tushar Khot, et al.*2020 · 857 citations*
4. **[Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://md.research.elamur.ai/free/en/papers/trivedi-2022-interleaving-retrieval-chain-thought-reasoning/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, et al.*2022 · 716 citations*
5. **[Parsing Algebraic Word Problems into Equations ↗](https://aclanthology.org/Q15-1042/) Transactions of the Association for Computational Linguistics · no summary yet**Rik Koncel-Kedziorski et al.*2015 · 404 citations*
6. **[Decomposed Prompting: A Modular Approach for Solving Complex Tasks ↗](https://arxiv.org/abs/2210.02406) ICLR 2023 (arXiv 2210.02406) · no summary yet**Tushar Khot et al.*2023 · 390 citations*
7. **[♫ MuSiQue: Multihop Questions via Single-hop Question Composition](https://md.research.elamur.ai/free/en/papers/trivedi-2022-musique-multihop-questions-single-hop/) [Transactions of the Association for Computational Linguistics (TACL)](https://md.research.elamur.ai/free/en/venues/tacl/)**Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, et al.*2022 · 390 citations*
8. [**Complexity-Based Prompting for Multi-Step Reasoning arXiv:2210.00720**Yao Fu, Hao Peng, Ashish Sabharwal, et al.*2022 · 345 citations*](https://md.research.elamur.ai/free/en/papers/fu-2022-complexity-based-prompting-multi-step/)
9. [**Specializing Smaller Language Models towards Multi-Step Reasoning arXiv:2301.12726**Yao Fu, Hao Peng, Litu Ou, et al.*2023 · 224 citations*](https://md.research.elamur.ai/free/en/papers/fu-2023-specializing-smaller-language-models-towards/)
10. **[Combining Retrieval, Statistics, and Inference to Answer Elementary Science Questions ↗](https://doi.org/10.1609/aaai.v30i1.10325) Proceedings of the AAAI Conference on Artificial Intelligence · no summary yet**Peter E. Clark et al.*2016 · 191 citations*
11. **[LILA: A Unified Benchmark for Mathematical Reasoning](https://md.research.elamur.ai/free/en/papers/mishra-2022-lila-unified-benchmark-mathematical-reasoning/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Swaroop Mishra, Matthew Finlayson, Pan Lu, et al.*2022 · 179 citations*
12. **[UNQOVERing Stereotyping Biases via Underspecified Questions](https://md.research.elamur.ai/free/en/papers/li-2020-unqovering-stereotyping-biases-underspecified-questions/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Tao Li, Daniel Khashabi, Tushar Khot, et al.*2020 · 145 citations*
13. **[Answering Complex Questions Using Open Information Extraction](https://md.research.elamur.ai/free/en/papers/khot-2017-answering-complex-questions-open-information/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Tushar Khot, Ashish Sabharwal, Peter Clark*2017 · 134 citations*
14. **[Question Answering via Integer Programming over Semi-Structured Knowledge ↗](https://arxiv.org/abs/1604.06076) arXiv (Cornell University) · no summary yet**Daniel Khashabi et al.*2016 · 117 citations*
15. **[Temporal Reasoning on Implicit Events from Distant Supervision ↗](https://aclanthology.org/2021.naacl-main.107/) Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · no summary yet**Ben Zhou et al.*2021 · 111 citations*
16. **[Question Answering as Global Reasoning Over Semantic Abstractions ↗](https://doi.org/10.1609/aaai.v32i1.11574) Proceedings of the AAAI Conference on Artificial Intelligence · no summary yet**Daniel Khashabi et al.*2018 · 107 citations*
17. **[More Bang for Your Buck: Natural Perturbation for Robust Question Answering ↗](https://aclanthology.org/2020.emnlp-main.12/) Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · no summary yet**Daniel Khashabi, Tushar Khot, Ashish Sabharwal*2020 · 102 citations*
18. **[Probing Natural Language Inference Models through Semantic Fragments](https://md.research.elamur.ai/free/en/papers/richardson-2019-probing-natural-language-inference-models/) [Proceedings of the AAAI Conference on Artificial Intelligence](https://md.research.elamur.ai/free/en/venues/proceedings-of-the-aaai-conference-on-artificial-intelligence/)**Kyle Richardson, Hai Hu, Lawrence S. Moss, et al.*2019 · 102 citations*
19. **[Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models](https://md.research.elamur.ai/free/en/papers/khot-2021-text-modular-networks-learning-decompose/) [Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)](https://md.research.elamur.ai/free/en/venues/naacl/)**Tushar Khot, Daniel Khashabi, Kyle Richardson, et al.*2021 · 95 citations*
20. **[AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples ↗](https://aclanthology.org/P18-1225/) Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yet**Dongyeop Kang et al.*2018 · 94 citations*
21. **[Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs ↗](https://arxiv.org/abs/2311.04892) arXiv:2311.04892 · no summary yet**Shashank Gupta et al.*2023 · 91 citations*
22. **[ADaPT: As-Needed Decomposition and Planning with Language Models](https://md.research.elamur.ai/free/en/papers/prasad-2024-adapt-as-needed-decomposition-planning/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Archiki Prasad, Alexander Koller, Mareike Hartmann, et al.*2024 · 89 citations*
23. **[AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents](https://md.research.elamur.ai/free/en/papers/trivedi-2024-appworld-controllable-world-apps-people/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Harsh Trivedi, Tushar Khot, Mareike Hartmann, et al.*2024 · 80 citations*
24. **[Taming the Curse of Dimensionality: Discrete Integration by Hashing and Optimization ↗](https://arxiv.org/abs/1302.6677) arXiv (Cornell University) · no summary yet**Stefano Ermon et al.*2013 · 76 citations*
25. **[Embed and Project: Discrete Sampling with Universal Hashing ↗](https://openalex.org/W2112904372) no summary yet**Stefano Ermon et al.*2013 · 62 citations*
26. **[ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning ↗](https://arxiv.org/abs/2502.01100) arXiv:2502.01100 · no summary yet**Bill Yuchen Lin et al.*2025 · 60 citations*
27. **[Low-density Parity Constraints for Hashing-Based Discrete Integration ↗](https://openalex.org/W2171035569) no summary yet**Stefano Ermon et al.*2014 · 60 citations*
28. **[Learning What is Essential in Questions ↗](https://aclanthology.org/K17-1010/) Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017) · no summary yet**Daniel Khashabi et al.*2017 · 59 citations*
29. **[What Does My QA Model Know? Devising Controlled Probes Using Expert Knowledge](https://md.research.elamur.ai/free/en/papers/richardson-2020-what-does-my-qa-model/) [Transactions of the Association for Computational Linguistics (TACL)](https://md.research.elamur.ai/free/en/venues/tacl/)**Kyle Richardson, Ashish Sabharwal*2020 · 58 citations*
30. **[DiscoveryBench: Towards Data-Driven Discovery with Large Language Models ↗](https://arxiv.org/abs/2407.01725) arXiv:2407.01725 · no summary yet**Bodhisattwa Prasad Majumder et al.*2024 · 55 citations*
31. **[Exploring Markov Logic Networks for Question Answering ↗](https://aclanthology.org/D15-1080/) Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · no summary yet**Tushar Khot et al.*2015 · 55 citations*
32. [**Improving Language Models via Plug-and-Play Retrieval Feedback arXiv:2305.14002**Wenhao Yu, Zhihan Zhang, Zhenwen Liang, et al.*2023 · 54 citations*](https://md.research.elamur.ai/free/en/papers/yu-2023-improving-language-models-plug-play/)
33. **[From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project ↗](https://arxiv.org/abs/1909.01958) arXiv:1909.01958 · no summary yet**Peter Clark et al.*2019 · 48 citations*
34. [**IfQA: A Dataset for Open-domain Question Answering under Counterfactual Presuppositions**Wenhao Yu, Meng Jiang, Peter Clark, et al.*English · 26 citations*](https://md.research.elamur.ai/free/en/papers/yu-2023-ifqa-dataset-open-domain-question/)
35. **[Not All Claims are Created Equal: Choosing the Right Statistical Approach to Assess Hypotheses ↗](https://aclanthology.org/2020.acl-main.506/) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · no summary yet**Erfan Sadeqi Azer et al.*2020 · 26 citations*
36. **[Adaptive Concentration Inequalities for Sequential Decision Problems ↗](https://openalex.org/W2552366573) neural information processing systems · no summary yet**Shengjia Zhao et al.*2016 · 26 citations*
37. **[Belief Propagation Neural Networks ↗](https://arxiv.org/abs/2007.00295) arXiv (Cornell University) · no summary yet**Jonathan Kuck et al.*2020 · 25 citations*
38. **[Exact Sampling with Integer Linear Programs and Random Perturbations ↗](https://doi.org/10.1609/aaai.v30i1.10421) Proceedings of the AAAI Conference on Artificial Intelligence · no summary yet**Carolyn Kim, Ashish Sabharwal, Stefano Ermon*2016 · 25 citations*
39. **[On the Capabilities and Limitations of Reasoning for Natural Language Understanding. ↗](https://arxiv.org/abs/1901.02522) arXiv (Cornell University) · no summary yet**Daniel Khashabi et al.*2019 · 22 citations*
40. **[AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite ↗](https://arxiv.org/abs/2510.21652) arXiv:2510.21652 · no summary yet**Jonathan Bragg et al.*2025 · 19 citations*
41. **[Closing the Gap Between Short and Long XORs for Model Counting ↗](https://doi.org/10.1609/aaai.v30i1.10430) Proceedings of the AAAI Conference on Artificial Intelligence · no summary yet**Shengjia Zhao et al.*2016 · 19 citations*
42. **[Optimization With Parity Constraints: From Binary Codes to Discrete Integration ↗](https://arxiv.org/abs/1309.6827) arXiv (Cornell University) · no summary yet**Stefano Ermon et al.*2013 · 19 citations*
43. [**Data-driven Discovery with Large Generative Models arXiv:2402.13610**Bodhisattwa Prasad Majumder, Harshit Surana, Dhruv Agarwal, et al.*2024 · 15 citations*](https://md.research.elamur.ai/free/en/papers/majumder-2024-data-driven-discovery-large-generative/)
44. **[Designing Fast Absorbing Markov Chains ↗](https://doi.org/10.1609/aaai.v28i1.8843) Proceedings of the AAAI Conference on Artificial Intelligence · no summary yet**Stefano Ermon et al.*2014 · 15 citations*
45. **[Beyond parity constraints: Fourier analysis of hash functions for inference ↗](https://openalex.org/W2471078913) International Conference on Machine Learning · no summary yet**Tudor Achim, Ashish Sabharwal, Stefano Ermon*2016 · 9 citations*
46. **[Markov Logic Networks for Natural Language Question Answering ↗](https://arxiv.org/abs/1507.03045) arXiv (Cornell University) · no summary yet**Tushar Khot et al.*2015 · 8 citations*
47. **[Adaptive Hashing for Model Counting. ↗](https://openalex.org/W2966479870) Uncertainty in Artificial Intelligence · no summary yet**Jonathan Kuck et al.*2019 · 7 citations*
48. **[Accelerated Adaptive Markov Chain for Partition Function Computation ↗](https://openalex.org/W2136961580) no summary yet**Stefano Ermon et al.*2011 · 6 citations*
49. **[MoNaCo: More Natural and Complex Questions for Reasoning Across Dozens of Documents](https://md.research.elamur.ai/free/en/papers/wolfson-2026-monaco-more-natural-complex-questions/) [Transactions of the Association for Computational Linguistics (TACL)](https://md.research.elamur.ai/free/en/venues/tacl/)**Tomer Wolfson, Harsh Trivedi, Mor Geva, et al.*2026 · 5 citations*
50. **[Approximating the Permanent by Sampling from Adaptive Partitions ↗](https://arxiv.org/abs/1911.11856) arXiv (Cornell University) · no summary yet**Jonathan Kuck et al.*2019 · 5 citations*
51. **[Density Propagation and Improved Bounds on the Partition Function ↗](https://openalex.org/W2165126939) no summary yet**Stefano Ermon et al.*2012 · 1 citation*
52. **[Discrete Integration by Decoding Binary Codes ↗](https://openalex.org/W2901036207) no summary yet**Stefano Ermon et al.*2013*