Sean Welleck

Agentic-R1: Distilled Dual-Strategy Reasoning EMNLP 2025 AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement ICML 2025 Evaluating Language Models as Synthetic Data Generators ACL 2025 ImProver: Agent-Based Automated Proof Optimization ICLR 2025 Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for LLM Problem-Solving ICLR 2025 Lean-STaR: Learning to Interleave Thinking and Proving ICLR 2025 miniCTX: Neural Theorem Proving with (Long-)Contexts ICLR 2025 Optimizing Temperature for Language Models with Multi-Sample Inference ICML 2025 Rewarding the Unlikely: Lifting GRPO Beyond Distribution Sharpening EMNLP 2025 The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models NAACL 2025 Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision NeurIPS 2024 Llemma: An Open Language Model for Mathematics ICLR 2024 Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models EMNLP 2024 A Survey of Deep Learning for Mathematical Reasoning ACL 2023 Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs ICLR 2023 Faith and Fate: Limits of Transformers on Compositionality NeurIPS 2023 Generating Sequences by Learning to Self-Correct ICLR 2023 Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning EMNLP 2023 MAUVE Scores for Generative Models: Theory and Practice JMLR 2023 Self-Refine: Iterative Refinement with Self-Feedback NeurIPS 2023 STEER: Unified Style Transfer with Expert Reinforcement EMNLP 2023 COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics NeurIPS 2022 Generated Knowledge Prompting for Commonsense Reasoning ACL 2022 LILA: A Unified Benchmark for Mathematical Reasoning EMNLP 2022 Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations EMNLP 2022 NaturalProver: Grounded Mathematical Proof Generation with Language Models NeurIPS 2022 NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics NAACL 2022 Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Prompts NAACL 2022 QUARK: Controllable Text Generation with Reinforced Unlearning NeurIPS 2022 Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering EMNLP 2022 Symbolic Brittleness in Sequence Models: On Systematic Generalization in Symbolic Mathematics AAAI 2022 Symbolic Knowledge Distillation: from General Language Models to Commonsense Models NAACL 2022 Divergence Frontiers for Generative Models: Sample Complexity, Quantization Effects, and Frontier Integrals NeurIPS 2021 MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers NeurIPS 2021 MLE-Guided Parameter Search for Task Loss Minimization in Neural Sequence Modeling AAAI 2021 Mode recovery in neural autoregressive sequence modeling ACL 2021 Consistency of a Recurrent Language Model With Respect to Incomplete Decoding EMNLP 2020 Don’t Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training ACL 2020 Neural Text Generation With Unlikelihood Training ICLR 2020 Dialogue Natural Language Inference ACL 2019 Non-Monotonic Sequential Text Generation ACL 2019 Non-Monotonic Sequential Text Generation ICML 2019 Loss Functions for Multiset Prediction NeurIPS 2018 Saliency-based Sequential Image Attention with Multiset Prediction NeurIPS 2017