2 papers
cs.AI2026
Retrieval-Augmented Generation Must Move Beyond Factual Grounding to Represent Diverse Opinions
Aditya Agrawal, Alwarappan Nakkiran, Darshan Fofadiya +3
This position paper argues that Retrieval-Augmented Generation (RAG) systems exhibit a factual bias-optimizing for epistemic uncertainty reduction while ignoring the aleatoric unce…
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…