3 papers
cs.CL2026
Conversational Speech Reveals Structural Robustness Failures in SpeechLLM Backbones
Maria Teleki, Sai Janjur, Haoran Liu +11
LLMs serve as the backbone in SpeechLLMs, yet their behavior on spontaneous conversational input remains poorly understood. Conversational speech contains pervasive disfluencies --…
cs.CL2025
CHOIR: Collaborative Harmonization fOr Inference Robustness
Xiangjue Dong, Cong Wang, Maria Teleki +2
Persona-assigned Large Language Models (LLMs) can adopt diverse roles, enabling personalized and context-aware reasoning. However, even minor demographic perturbations in personas,…
cs.CL2025
Z-Scores: A Metric for Linguistically Assessing Disfluency Removal
Maria Teleki, Sai Janjur, Haoran Liu +10
Evaluating disfluency removal in speech requires more than aggregate token-level scores. Traditional word-based metrics such as precision, recall, and F1 (E-Scores) capture overall…