Showing cs.CLShow all
2 papers · 1 filter
cs.CL2025
Idea-Gated Transformers: Enforcing Semantic Coherence via Differentiable Vocabulary Pruning
Darshan Fofadiya
Autoregressive Language Models (LLMs) trained on Next-Token Prediction (NTP) often suffer from Topic Drift where the generation wanders away from the initial prompt due to a relian…
cs.CL2021
Error Detection in Large-Scale Natural Language Understanding Systems Using Transformer Models
Rakesh Chada, Pradeep Natarajan, Darshan Fofadiya +1
Large-scale conversational assistants like Alexa, Siri, Cortana and Google Assistant process every utterance using multiple models for domain, intent and named entity recognition.…