🧑‍🔬 Swarnadeep Saha

🏛️ Affiliations

🎓University of North Carolina at Chapel HillChapel Hill · United States2019–2025 · 17 papers🏢IBMBengaluru · India2018–2019 · 6 papers🏢IBMArmonk · United States2018–2020 · 4 papers🔬IBM Research - IndiaNew Delhi · India2018–2019 · 4 papers

🏛️Oregon Heart Center, PCSalem · United States2017Employment since 2017 · Cardiologist and Cardiac Electrophysiologist

🎓Rush UniversityChicago · United States2014–2016Education 2014–2016 · Master of Science - Clinical Research, Graduate College🎓King Edward Memorial Hospital and Seth G.S. Medical CollegeMumbai · India1996–2002Education 1996–2002 · Bachelor of Medicine and Bachelor of Surgery (M.B.,B.S.)

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions on single bylines are not listed.

🧭 Concepts, shelves and topics

Of its works in our library: the number of works on each and its rating among them.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs (2024 · 154 citations)
   Single-model reasoning methods such as self-reflection can get stuck repeating their own confident mistakes.
2. PRover: Proof Generation for Interpretable Reasoning over Rules (2020 · 101 citations)
   Clark et al. (2020) showed that RuleTakers, a fine-tuned RoBERTa, can decide whether a statement follows from facts and rules written in English. However, it gives no justification for its answers. PRover addresses this by producing an answer together with an explicit proof. Each proof is a directed graph whose nodes…
3. ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness (2023 · 68 citations)
   Language models increasingly produce step-by-step rationales, but they are usually judged only by whether the final answer is right.
4. ConjNLI: Natural Language Inference Over Conjunctive Sentences (2020 · 50 citations)
   ConjNLI is a stress-test for natural language inference (NLI) built around coordinating conjunctions ("and", "or", "but", "nor").

All works

6 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

1. ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMsJustin Chen, Swarnadeep Saha, Mohit BansalAnnual Meeting of the Association for Computational Linguistics (ACL) · 154 citations
2. PRover: Proof Generation for Interpretable Reasoning over RulesSwarnadeep Saha, Sayan Ghosh, Shashank Srivastava, et al.Conference on Empirical Methods in Natural Language Processing (EMNLP) · 101 citations
3. ReCEval: Evaluating Reasoning Chains via Correctness and InformativenessArchiki Prasad, Swarnadeep Saha, Xiang Zhou, et al.Conference on Empirical Methods in Natural Language Processing (EMNLP) · 68 citations
4. Branch-Solve-Merge Improves Large Language Model Evaluation and Generation · original ↗ · no summary yet · arXiv:2310.15123Swarnadeep Saha et al.2023 · 66 citations
5. ConjNLI: Natural Language Inference Over Conjunctive SentencesSwarnadeep Saha, Yixin Nie, Mohit BansalConference on Empirical Methods in Natural Language Processing (EMNLP) · 50 citations
6. MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning · original ↗ · no summary yet · Proceedings of the 2025 Conference on Empirical Methods in Natural Language…Justin Chen et al.2025 · 20 citations

🤝 Co-authors here

5 co-authors with a page, the most papers together first.

• Mohit Bansal ×4
• Archiki Prasad
• Shashank Srivastava
• Xiang Zhou
• Yixin Nie

Venues

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

• Conference on Empirical Methods in Natural Language Processing (EMNLP) ×4: EMNLP 2023, EMNLP 2020 ×2
• Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2024

🔗 Cited by

Papers of our library cite their works 310 times (of the 141,840 papers whose bibliographies we read); 19 citing papers with a page here →.

Updated 24 October 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/swarnadeep-saha/