Alexander M Rush

15 papers · 2021–2025 · 6 conferences · across top CS/AI conferences

Achievements

🌉 Interdisciplinary Bridge 🐝 Cross-Pollinator (13) 🧭 Keyword Pioneer 🌍 Conference Polyglot (6) 🗺️ Taxonomy Completionist (16) 👥 Mega-Team (40) ❓ The Questioner (2) 🔥 Unstoppable (5) 💎 Century Club (15) ⚡ Prolific Year (9)

Conferences

ICLR (9) NAACL (2) AACL (1) EMNLP (1) ICML (1) IJCNLP (1)

Top co-authors

Wenting Zhao (6) Celine Lee (4) Thomas Wolf (2) Keyon Vafa (2) Claire Cardie (2) Justin T Chiu (2) Victor Sanh (2) John Xavier Morris (2) Thomas Wang (1) Subham Sekhar Sahoo (1)

Keywords

task complexity (2) reasoning token (2) optimal reasoning (2) llm evaluation (1) annotator reliability (1) language model (1) downstream task (1) multi-hop reasoning (1) commonsense reasoning (1) human evaluation (1) annotation quality (1) preference datum (1) semantic retrieval (1) unanswerable question (1) chain of thought (1) llm benchmark (1) reasoning length (1) verbalized reasoning (1) chatbot arena (1) trustworthy benchmark (1)

Papers

Challenges in Trustworthy Human Evaluation of Chatbots NAACL 2025

Contextual Document Embeddings ICLR 2025

Simple Guidance Mechanisms for Discrete Diffusion Models ICLR 2025

Multi-Turn Code Generation Through Single-Step Rewards ICML 2025

Critical Thinking: Which Kinds of Complexity Govern Optimal Reasoning Length? IJCNLP 2025

Great Memory, Shallow Reasoning: Limits of kNN-LMs NAACL 2025

Critical Thinking: Which Kinds of Complexity Govern Optimal Reasoning Length? AACL 2025

Commit0: Library Generation from Scratch ICLR 2025

Compute-Constrained Data Selection ICLR 2025

I Could’ve Asked That: Reformulating Unanswerable Questions EMNLP 2024

Guess & Sketch: Language Model Guided Transpilation ICLR 2024

Language Model Inversion ICLR 2024

Markup-to-Image Diffusion Models with Scheduled Sampling ICLR 2023

Multitask Prompted Training Enables Zero-Shot Task Generalization ICLR 2022

Learning from others' mistakes: Avoiding dataset biases without modeling them ICLR 2021