3 papers
cs.MA2025
An Adversary-Resistant Multi-Agent LLM System via Credibility Scoring
Sana Ebrahimi, Mohsen Dehghankar, Abolfazl Asudeh
While multi-agent LLM systems show strong capabilities in various domains, they are highly vulnerable to adversarial and low-performing agents. To resolve this issue, in this paper…
cs.CL2024
REQUAL-LM: Reliability and Equity through Aggregation in Large Language Models
Sana Ebrahimi, Nima Shahbazi, Abolfazl Asudeh
The extensive scope of large language models (LLMs) across various domains underscores the critical importance of responsibility in their application, beyond natural language proce…
cs.CL2024
AXOLOTL: Fairness through Assisted Self-Debiasing of Large Language Model Outputs
Sana Ebrahimi, Kaiwen Chen, Abolfazl Asudeh +2
Pre-trained Large Language Models (LLMs) have significantly advanced natural language processing capabilities but are susceptible to biases present in their training data, leading…