Get started
Author

William Jurayj

Gaps or Hallucinations? Scrutinizing Machine-Generated Legal Analysis for Fine-grained Text Evaluations
2024 · Abe Hou, William Jurayj, et al. · Natural Legal Language Processing Workshop (NLLP) · 4
PDF
Garden Path Traversal in GPT-2
2022 · William Jurayj, William Rudman, et al. · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP) · 4
PDF
Language Models and Logic Programs for Trustworthy Tax Reasoning
2026 · William Jurayj, Nils Holzenberger, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 1
PDF
Is That Your Final Answer? Test-Time Scaling Improves Selective Question Answering
2025 · William Jurayj, Jeffrey Cheng, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting · 1
PDF
FOCUS: Active Critic Learning for Long-Horizon Language Model Agents
2026 · Jiang, Zhengping, Jurayj, William, et al. · arXiv (Cornell University)
PDF
CrossWeave: Bridging Perspectives Across Online Communities with a Dual-Pane Design
2026 · Fei Fang, Reva Hirave, et al. · ACM Conference on Computer Supported Cooperative Work (CSCW)
Better, Faster, Stronger: Programmatic Skill Learning Best Reduces Agent Cost
2026 · Huang, Zixi, Wang, Xiheng, et al. · arXiv (Cornell University)
PDF
Self-Compacting Language Model Agents
2026 · Li, Tianjian, Zhang, Jingyu, et al. · arXiv (Cornell University)
PDF
DAR: Deontic Reasoning with Agentic Harnesses
2026 · Dou, Guangyao, Jurayj, William, et al. · arXiv (Cornell University)
PDF
Can Coding Agents Reproduce Findings in Computational Materials Science?
2026 · Huang, Ziyang, Cao, Yi, et al. · arXiv (Cornell University)
PDF
Process Supervision of Confidence Margin for Calibrated LLM Reasoning
2026 · Wang, Liaoyaqi, Zuo, Chunsheng, et al. · arXiv (Cornell University)
PDF
Weird Generalization is Weirdly Brittle
2026 · Wanner, Miriam, Collison, Hannah, et al. · arXiv (Cornell University)
PDF
Unified Multimodal Uncertain Inference
2026 · Zhang, Dengjia, Martin, Alexander, et al. · arXiv (Cornell University)
PDF
DeonticBench: A Benchmark for Reasoning over Rules
2026 · Dou, Guangyao, Brena, Luis, et al. · arXiv (Cornell University)
PDF
Conformal Thinking: Risk Control for Reasoning on a Compute Budget
2026 · Wang, Xi, Suresh, Anushri, et al. · arXiv (Cornell University)
PDF
Many-Tier Instruction Hierarchy in LLM Agents
2026 · Jingyu Zhang, Tianjian Li, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
Rethinking LoRA Memory Through the Lens of KV Cache Compression
2026 · Chunsheng Zuo, Liaoyaqi Wang, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Mining Legal Arguments in U.S. Corporate Case Law
2026 · Luis Brena, William Jurayj, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
Language Models and Logic Programs for Trustworthy Tax Reasoning
2025 · Jurayj, William, Holzenberger, Nils, et al. · arXiv (Cornell University)
PDF
CLAIMCHECK: How Grounded are LLM Critiques of Scientific Papers?
2025 · Ou, Jiefu, Walden, William Gantt, et al. · arXiv (Cornell University)
PDF
CLAIMCHECK: How Grounded are LLM Critiques of Scientific Papers?
2025 · Jiefu Ou, William Gantt Walden, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
Gaps or Hallucinations? Gazing into Machine-Generated Legal Analysis for Fine-grained Text Evaluations
2024 · Hou, Abe Bohan, Jurayj, William, et al. · arXiv (Cornell University)
PDF
Works count: 24
Citation count: 10
H-index: 2
I10-index:
Year
Topic
Type