3 papers
cs.AI2026
LLMs Don't Pay for the Jump
Paras Balani, Subhrakanta Panda
Zahavy [2026] argues that Large Language Models, despite their capabilities in induction and deduction, cannot perform the abductive "Jump" that produced Einstein's equivalence pri…
cs.CL2026
Self-Referential Induction Increases Response Instability Relative to Unresolvable and Verifiable Questions in Large Language Models
Paras Balani, Subhrakanta Panda
Self-referential prompting has been shown to reliably induce large language models to produce first-person reports resembling subjective experience, but no prior work measures how…
gr-qc2026
Observational Signatures of Static and Rotating Wormholes Embedded in Dark Matter
Zinnat Hassan, Paras Balani, P. K. Sahoo
We study static and slowly rotating traversable wormholes embedded in two contrasting dark matter environments, the cuspy Navarro-Frenk-White (NFW) halo and the cored solitonic wav…