Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
PolyAlign: Conditional Human-Distribution Alignment
L. D. M. S. Sai Teja, Ufaq Khan, Sathira Silva +2
Post-training methods such as supervised fine-tuning (SFT) and preference optimization typically align language models toward a single global assistant behavior. While effective fo…
cs.CL2026
Disentangling Direction and Magnitude in Transformer Representations: A Double Dissociation Through L2-Matched Perturbation Analysis
Mangadoddi Srikar Vardhan, Lekkala Sai Teja
Transformer hidden states encode information as high-dimensional vectors, yet whether direction (orientation in representational space) and magnitude (vector norm) serve distinct f…
cs.CL2026
DAMASHA: Detecting AI in Mixed Adversarial Texts via Segmentation with Human-interpretable Attribution
L. D. M. S. Sai Teja, N. Siva Gopala Krishna, Ufaq Khan +2
In the age of advanced large language models (LLMs), the boundaries between human and AI-generated text are becoming increasingly blurred. We address the challenge of segmenting mi…