AI RESEARCH
From Automation to Collaboration: Human-in-the-Loop Methods for Safe and Trustworthy NLP
arXiv CS.CL
•
ArXi:2605.25226v1 Announce Type: new Large language models are widely deployed in high-stakes NLP tasks, yet risks such as bias, hallucination, adversarial vulnerability and unreliable generalization remain. Probe-based auditing reveals inconsistencies in model behavior. Adversarial text generation uncovers robustness gaps, especially in lower-resourced languages with limited benchmarks. Enterprise text-to-SQL settings expose the difficulty of validating outputs over private and large-scale databases.