Author

Ali Payani

Observed name: Payani, Ali

OpenAlex ID: A5120230673

MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems

2024 · Bin Lei, Yi Zhang, et al. · neural information processing systems · 5

PDF

SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models

2025 · Zirui He, Mingyu Jin, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 2

PDF

Towards Uncovering How Large Language ModelsWork: An Interpretability Perspective

2025 · Haiyan Zhao, Fan Yang, et al. · ACM SIGKDD Explorations Newsletter · 1

Can Knowledge Editing Really Correct Hallucinations?

2024 · Huang, Baixiang, Chen, Canyu, et al. · arXiv (Cornell University) · 1

PDF

Towards Strong Certified Defense with Universal Asymmetric Randomization

2026 · Hanbin Hong, Ashish Kundu, et al. · IEEE Computer Security Foundations Workshop (CSFW)

PDF

Scaling Teams or Scaling Time? Memory Enabled Lifelong Learning in LLM Multi-Agent Systems

2026 · Wu, Shanglin, Luo, Yuyang, et al. · arXiv (Cornell University)

PDF

Benchmarking LLMs for Political Science: A United Nations Perspective

2026 · Yueqing Liang, Liangwei Yang, et al. · Proceedings of the AAAI Conference on Artificial Intelligence

PDF

Model Editing as a Double-Edged Sword: Steering Agent Behavior Toward Beneficence or Harm

2026 · Baixiang Huang, Zhen Tan, et al. · Proceedings of the AAAI Conference on Artificial Intelligence

A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents

2026 · Huang, Wei-Chieh, Zhang, Weizhi, et al. · arXiv (Cornell University)

PDF

Model Editing as a Double-Edged Sword: Steering Agent Behavior Toward Beneficence or Harm

2026 · Association for Artificial Intelligence 2026, Chen, Tianlong, et al. · Underline Science Inc.

Benchmarking LLMs for Political Science: A United Nations Perspective

2026 · Association for Artificial Intelligence 2026, Liang, Yueqing, et al. · Underline Science Inc.

D3-Gym: Constructing Real-World Verifiable Environments for Data-Driven Discovery

2026 · Hanane Nour Moussa, Yifei Li, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)

PDF

Universal Activation Verbalizer: A Unified Framework for Cross-Model Activation Explanation

2026 · Haiyan Zhao, Zirui He, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)

PDF

Unreasonable effectiveness of LLM reasoning:A doubly cautionary tale of temporal question-answering

2025 · Panas, Daga, Payani, Ali, et al. · Edinburgh Research Explorer (University of Edinburgh)

Rep2Text: Decoding Full Text from a Single LLM Token Representation

2025 · Zhao, Haiyan, He, Zirui, et al. · arXiv (Cornell University)

PDF

LogitTrace: Detecting Benchmark Contamination via Layerwise Logit Trajectories

2025 · He, Zirui, Zhao, Haiyan, et al. · arXiv (Cornell University)

PDF

Model Editing as a Double-Edged Sword: Steering Agent Ethical Behavior Toward Beneficence or Harm

2025 · Huang, Baixiang, Tan, Zhen, et al. · arXiv (Cornell University)

PDF

LMO-DP: Optimizing the Randomization Mechanism for Differentially Private Fine-Tuning (Large) Language Models

2024 · Yang, Qin, Mohammad, Meisam, et al. · arXiv (Cornell University)

PDF

Works count: 18

Citation count: 9

H-index: 2

I10-index: