🧑‍🔬 Bodhisattwa Prasad Majumder

🏛️ Affiliations

🔬Allen Institute for Artificial IntelligenceSeattle · United States2023–2026 · 28 papersEmployment · Research Scientistcurrent🎓University of California San DiegoSan Diego · United States2018–2023 · 26 papersEmployment · PhD, Computer Science and Engineering🎓Jadavpur UniversityKolkata · India2013–2016 · 6 papers🔬Allen InstituteSeattle · United States2023–2025 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 3 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Aligning Language Models to User Opinions (2023 · 93 citations)
   The paper asks what information an LLM needs to predict an individual's views: demographic traits, ideology, the person's own earlier answers, or a combination.
2. DiscoveryBench: Towards Data-Driven Discovery with Large Language Models (2024 · 55 citations)
   DiscoveryBench tests whether LLM-based agents can independently form and check hypotheses using only supplied datasets, a setting the authors call data-driven discovery.
3. CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalization (2023 · 34 citations)
   Agents built on LLMs can act in text-based simulated worlds without costly reinforcement learning. Reflection-based methods such as Reflexion can retry a single task better, but their lessons tend to be tied to one setting and do not accumulate. CLIN (continual learning from interactions) addresses this. The model's…
4. Data-driven Discovery with Large Generative Models (2024 · 15 citations)
   This position paper, written by authors from the Allen Institute for AI and collaborators, urges the ML community to build systems that perform scientific discovery end to end using only datasets already at hand, with no new data collection or lab experiments.
5. Evaluating Language Model Pluralism through In-the-wild Crowd Discussions (2026)
   LLMs tuned with preference alignment often lean toward particular stances on subjective questions. Yet pluralism has mostly been tested with multiple-choice or rating formats, and the few open-ended benchmarks depend on costly crowd annotation for every new domain. The authors propose PluralEval, which builds…

All works

15 works of theirs in our library, the most cited first; 5 with a page here, the others link their original until we summarise them.

1. Self-Refine: Iterative Refinement with Self-Feedback ↗arXiv:2303.17651 · no summary yetAman Madaan et al.2023 · 1,962 citations
2. ReZero is All You Need: Fast Convergence at Large Depth ↗arXiv:2003.04887 · no summary yetThomas Bachlechner et al.2020 · 166 citations
3. Representation Learning for Information Extraction from Form-like Documents ↗Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · no summary yetBodhisattwa Prasad Majumder et al.2020 · 132 citations
4. Generating Personalized Recipes from Historical User Preferences ↗Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · no summary yetBodhisattwa Prasad Majumder et al.2019 · 114 citations
5. Like hiking? You probably enjoy nature: Persona-grounded Dialog with Commonsense Expansions ↗Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · no summary yetBodhisattwa Prasad Majumder et al.2020 · 108 citations
6. Aligning Language Models to User OpinionsFindings of the Association for Computational LinguisticsEunJeong Hwang, Bodhisattwa Majumder, Niket Tandon2023 · 93 citations
7. Improving Neural Story Generation by Targeted Common Sense Grounding ↗Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · no summary yetHuanru Henry Mao et al.2019 · 72 citations
8. DiscoveryBench: Towards Data-Driven Discovery with Large Language ModelsarXiv:2407.01725Bodhisattwa Prasad Majumder, Harshit Surana, Dhruv Agarwal, et al.2024 · 55 citations
9. DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents ↗arXiv:2406.06769 · no summary yetPeter Jansen et al.2024 · 43 citations
10. CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and GeneralizationarXiv:2310.10134Bodhisattwa Prasad Majumder, Bhavana Dalvi Mishra, Peter Jansen, et al.2023 · 34 citations
11. CodeScientist: End-to-End Semi-Automated Scientific Discovery with Code-based Experimentation ↗arXiv:2503.22708 · ACL 2025 (Findings) · no summary yetPeter Jansen et al.2025 · 31 citations
12. AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite ↗arXiv:2510.21652 · no summary yetJonathan Bragg et al.2025 · 19 citations
13. Data-driven Discovery with Large Generative ModelsarXiv:2402.13610Bodhisattwa Prasad Majumder, Harshit Surana, Dhruv Agarwal, et al.2024 · 15 citations
14. Social Intelligence in the Age of LLMs ↗Proceedings of the 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 5: Tutorial Abstracts) · no summary yetHao Zhu et al.2025 · 1 citation
15. Evaluating Language Model Pluralism through In-the-wild Crowd DiscussionsAnnual Meeting of the Association for Computational Linguistics (ACL)Gagan Mundada, Rohan Surana, Nandhini Swaminathan, et al.2026

🤝 Co-authors here

12 of 15 co-authors with a page, the most papers together first.

• Peter Clark ×3
• Ashish Sabharwal ×2
• Bhavana Dalvi Mishra ×2
• Dhruv Agarwal ×2
• Harshit Surana ×2
• Niket Tandon ×2
• Chris Callison-Burch
• Gagan Mundada
• Julian McAuley
• Junda Wu
• Li Zhang
• Oyvind Tafjord

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Annual Meeting of the Association for Computational Linguistics (ACL) ×2: ACL 2026
• Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) ×2
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2023
• Workshop on Generation, Evaluation and Metrics (GEM)
• Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
• Proceedings of the 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 5: Tutorial Abstracts)

🔗 Cited by

Papers of our library cite their works 1,969 times (of the 149,439 papers whose bibliographies we read); 447 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/bodhisattwa-prasad-majumder/