---
title: "Sean Welleck — all works — Elamur Research"
description: "All 50 works of Sean Welleck 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/sean-welleck/works/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/sean-welleck/works/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Sean Welleck](https://md.research.elamur.ai/free/en/authors/sean-welleck/) / all works

# Sean Welleck — all works

50 works · [← Sean Welleck](https://md.research.elamur.ai/free/en/authors/sean-welleck/)

1. **[Self-Refine: Iterative Refinement with Self-Feedback ↗](https://arxiv.org/abs/2303.17651) arXiv:2303.17651 · no summary yet**Aman Madaan et al.*2023 · 1,962 citations*
2. [**Neural Text Generation with Unlikelihood Training arXiv:1908.04319**Sean Welleck, Ilia Kulikov, Stephen Roller, et al.*2019 · 513 citations*](https://md.research.elamur.ai/free/en/papers/welleck-2019-neural-text-generation-unlikelihood-training/)
3. **[Dialogue Natural Language Inference](https://md.research.elamur.ai/free/en/papers/welleck-2019-dialogue-natural-language-inference/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Sean Welleck, Jason Weston, Arthur Szlam, et al.*2019 · 385 citations*
4. **[Symbolic Knowledge Distillation: from General Language Models to Commonsense Models](https://md.research.elamur.ai/free/en/papers/west-2022-symbolic-knowledge-distillation-general-language/) [Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)](https://md.research.elamur.ai/free/en/venues/naacl/)**Peter West, Chandra Bhagavatula, Jack Hessel, et al.*2022 · 349 citations*
5. **[Generated Knowledge Prompting for Commonsense Reasoning ↗](https://aclanthology.org/2022.acl-long.225/) Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yet**Jiacheng Liu et al.*2022 · 329 citations*
6. **[Faith and Fate: Limits of Transformers on Compositionality](https://md.research.elamur.ai/free/en/papers/dziri-2023-faith-fate-limits-transformers-compositionality/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**Nouha Dziri, Ximing Lu, Melanie Sclar, et al.*2023 · 327 citations*
7. [**Llemma: An Open Language Model For Mathematics arXiv:2310.10631**Zhangir Azerbayev, Hailey Schoelkopf, Keiran Paster, et al.*2023 · 286 citations*](https://md.research.elamur.ai/free/en/papers/azerbayev-2023-llemma-open-language-model-mathematics/)
8. [**MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers arXiv:2102.01454**Krishna Pillutla, Swabha Swayamdipta, Rowan Zellers, et al.*2021 · 251 citations*](https://md.research.elamur.ai/free/en/papers/pillutla-2021-mauve-measuring-gap-between-neural/)
9. [**Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models arXiv:2405.01535**Seungone Kim, Juyoung Suk, Shayne Longpre, et al.*2024 · 234 citations*](https://md.research.elamur.ai/free/en/papers/kim-2024-prometheus-2-open-source-language/)
10. **[Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations](https://md.research.elamur.ai/free/en/papers/jung-2022-maieutic-prompting-logically-consistent-reasoning/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Jaehun Jung, Lianhui Qin, Sean Welleck, et al.*2022 · 219 citations*
11. **[Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training](https://md.research.elamur.ai/free/en/papers/li-2020-don-t-say-that-making/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Margaret Li, Stephen Roller, Ilia Kulikov, et al.*2020 · 217 citations*
12. **[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*
13. [**Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs arXiv:2210.12283**Albert Q. Jiang, Sean Welleck, Jin Peng Zhou, et al.*2022 · 178 citations*](https://md.research.elamur.ai/free/en/papers/jiang-2022-draft-sketch-prove-guiding-formal/)
14. [**Generating Sequences by Learning to Self-Correct arXiv:2211.00053**Sean Welleck, Ximing Lu, Peter West, et al.*2022 · 172 citations*](https://md.research.elamur.ai/free/en/papers/welleck-2022-generating-sequences-learning-self-correct/)
15. **[Quark: Controllable Text Generation with Reinforced Unlearning](https://md.research.elamur.ai/free/en/papers/lu-2022-quark-controllable-text-generation-reinforced/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**Ximing Lu, Sean Welleck, Jack Hessel, et al.*2022 · 170 citations*
16. **[A Survey of Deep Learning for Mathematical Reasoning ↗](https://aclanthology.org/2023.acl-long.817/) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yet**Pan Lu et al.*2023 · 149 citations*
17. **[NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics](https://md.research.elamur.ai/free/en/papers/lu-2022-neurologic-esque-decoding-constrained-text/) [Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)](https://md.research.elamur.ai/free/en/venues/naacl/)**Ximing Lu, Sean Welleck, Peter West, et al.*2022 · 140 citations*
18. [**L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning arXiv:2503.04697**Pranjal Aggarwal, Sean Welleck*2025 · 125 citations*](https://md.research.elamur.ai/free/en/papers/aggarwal-2025-l1-controlling-long-reasoning-model/)
19. [**Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models arXiv:2408.00724**Yangzhen Wu, Zhiqing Sun, Shanda Li, et al.*2024 · 122 citations*](https://md.research.elamur.ai/free/en/papers/wu-2024-inference-scaling-laws-empirical-analysis/)
20. **[Non-Monotonic Sequential Text Generation ↗](https://arxiv.org/abs/1902.02192) arXiv (Cornell University) · no summary yet**Sean Welleck et al.*2019 · 101 citations*
21. **[Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering](https://md.research.elamur.ai/free/en/papers/liu-2022-rainier-reinforced-knowledge-introspector-commonsense/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Jiacheng Liu, Skyler Hallinan, Ximing Lu, et al.*2022 · 82 citations*
22. **[Consistency of a Recurrent Language Model With Respect to Incomplete Decoding ↗](https://aclanthology.org/2020.emnlp-main.448/) Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · no summary yet**Sean Welleck et al.*2020 · 79 citations*
23. [**NaturalProofs: Mathematical Theorem Proving in Natural Language arXiv:2104.01112**Sean Welleck, Jiacheng Liu, Ronan Le Bras, et al.*2021 · 76 citations*](https://md.research.elamur.ai/free/en/papers/welleck-2021-naturalproofs-mathematical-theorem-proving-natural/)
24. **[NaturalProver: Grounded Mathematical Proof Generation with Language Models](https://md.research.elamur.ai/free/en/papers/welleck-2022-naturalprover-grounded-mathematical-proof-generation/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**Sean Welleck, Jiacheng Liu, Ximing Lu, et al.*2022 · 62 citations*
25. **[The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models ↗](https://aclanthology.org/2025.naacl-long.303/) Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) · no summary yet**Seungone Kim et al.*2025 · 57 citations*
26. [**From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models arXiv:2406.16838**Sean Welleck, Amanda Bertsch, Matthew Finlayson, et al.*2024 · 51 citations*](https://md.research.elamur.ai/free/en/papers/welleck-2024-decoding-meta-generation-inference-time/)
27. **[Lean-STaR: Learning to Interleave Thinking and Proving ↗](https://arxiv.org/abs/2407.10040) arXiv:2407.10040 · no summary yet**Haohan Lin et al.*2024 · 51 citations*
28. **[Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision ↗](https://arxiv.org/abs/2403.09472) arXiv:2403.09472 · no summary yet**Zhiqing Sun et al.*2024 · 51 citations*
29. **[Evaluating Language Models as Synthetic Data Generators](https://md.research.elamur.ai/free/en/papers/kim-2025-evaluating-language-models-as-synthetic/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Seungone Kim, Juyoung Suk, Xiang Yue, et al.*2025 · 32 citations*
30. **[LLMSTEP: LLM proofstep suggestions in Lean ↗](https://arxiv.org/abs/2310.18457) arXiv:2310.18457 · no summary yet**Sean Welleck, Rahul Saha*2023 · 22 citations*
31. **[Saliency-based Sequential Image Attention with Multiset Prediction ↗](https://arxiv.org/abs/1711.05165) arXiv (Cornell University) · no summary yet**Sean Welleck et al.*2017 · 21 citations*
32. **[miniCTX: Neural Theorem Proving with (Long-)Contexts ↗](https://arxiv.org/abs/2408.03350) arXiv:2408.03350 · no summary yet**Jiewen Hu, Thomas Zhu, Sean Welleck*2024 · 18 citations*
33. **[Loss Functions for Multiset Prediction ↗](https://arxiv.org/abs/1711.05246) arXiv (Cornell University) · no summary yet**Sean Welleck et al.*2017 · 17 citations*
34. **[STEER: Unified Style Transfer with Expert Reinforcement ↗](https://aclanthology.org/2023.findings-emnlp.506/) Findings of the Association for Computational Linguistics: EMNLP 2023 · no summary yet**Skyler Hallinan et al.*2023 · 16 citations*
35. **[Rewarding the Unlikely: Lifting GRPO Beyond Distribution Sharpening](https://md.research.elamur.ai/free/en/papers/he-2025-rewarding-unlikely-lifting-grpo-beyond/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Andre Wang He, Daniel Fried, Sean Welleck*2025 · 15 citations*
36. **[AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement ↗](https://arxiv.org/abs/2412.06176) arXiv:2412.06176 · no summary yet**Pranjal Aggarwal, Bryan Parno, Sean Welleck*2024 · 11 citations*
37. **[MLE-Guided Parameter Search for Task Loss Minimization in Neural Sequence Modeling ↗](https://doi.org/10.1609/aaai.v35i16.17652) Proceedings of the AAAI Conference on Artificial Intelligence · no summary yet**Sean Welleck, Kyunghyun Cho*2021 · 11 citations*
38. **[Training Proactive and Personalized LLM Agents ↗](https://arxiv.org/abs/2511.02208) arXiv (Cornell University) · no summary yet**Weiwei Sun et al.*2025 · 10 citations*
39. **[Mind the Sim2Real Gap in User Simulation for Agentic Tasks ↗](https://arxiv.org/abs/2603.11245) arXiv (Cornell University) · no summary yet**Xuhui Zhou et al.*2026 · 6 citations*
40. **[Gym-Anything: Turn any Software into an Agent Environment ↗](https://arxiv.org/abs/2604.06126) arXiv (Cornell University) · no summary yet**Pranjal Aggarwal, Graham Neubig, Sean Welleck*2026 · 5 citations*
41. **[Premise Selection for a Lean Hammer ↗](https://arxiv.org/abs/2506.07477) arXiv:2506.07477 · no summary yet**Thomas Zhu et al.*2025 · 5 citations*
42. **[ImProver: Agent-Based Automated Proof Optimization ↗](https://arxiv.org/abs/2410.04753) arXiv:2410.04753 · no summary yet**Riyaz Ahuja et al.*2024 · 5 citations*
43. **[The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think ↗](https://arxiv.org/abs/2505.10185) arXiv (Cornell University) · no summary yet**Seongyun Lee et al.*2025 · 4 citations*
44. **[On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists ↗](https://arxiv.org/abs/2605.20668) arXiv:2605.20668 · no summary yet**Seungone Kim et al.*2026 · 2 citations*
45. **[Reasoning over mathematical objects: on-policy reward modeling and test time aggregation ↗](https://arxiv.org/abs/2603.18886) arXiv (Cornell University) · no summary yet**Pranjal Aggarwal et al.*2026 · 1 citation*
46. **[Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs ↗](https://arxiv.org/abs/2605.09063) arXiv:2605.09063 · no summary yet**Guijin Son et al.*2026 · 1 citation*
47. **[cua-speedrun: Standardized Benchmarking of the Speed of Computer-Use Agents ↗](https://arxiv.org/abs/2609.40284) arXiv (Cornell University) · no summary yet**Pranjal Aggarwal et al.*2026*
48. **[Reinforcing Human Behavior Simulation via Verbal Feedback ↗](https://arxiv.org/abs/2605.20506) arXiv (Cornell University) · no summary yet**Weiwei Sun et al.*2026*
49. **[Mode recovery in neural autoregressive sequence modeling ↗](https://aclanthology.org/2021.spnlp-1.5/) Proceedings of the 5th Workshop on Structured Prediction for NLP (SPNLP 2021) · no summary yet**Ilia Kulikov, Sean Welleck, Kyunghyun Cho*2021*
50. **[Sequential Graph Dependency Parser ↗](https://aclanthology.org/R19-1153/) Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019) · no summary yet**Sean Welleck, Kyunghyun Cho*2019*