4 papers
The Knowing-Saying Gap: When Probes See Errors that Confidence Misses
Jyotin Goel, Ipshita Bandyopadhyay, Justin Shenk
Linear probes detect corrupted context in language models with near-perfect accuracy, yet this does not translate into reliable failure prediction. The result is a dissociation wit…
Learning to Stay Safe: Adaptive Regularization Against Safety Degradation during Fine-Tuning
Jyotin Goel, Souvik Maji, Pratik Mazumder
Instruction-following language models are trained to be helpful and safe, yet their safety behavior can deteriorate under benign fine-tuning and worsen under adversarial updates. E…
PlotTwist: A Creative Plot Generation Framework with Small Language Models
Abhinav Thorat, Ravi Kolla, Jyotin Goel +2
Creative plot generation presents a fundamental challenge for language models: transforming a concise premise into a coherent narrative that sustains global coherence, character de…
A Traditional Approach to Symbolic Piano Continuation
Christian Zhou-Zheng, John Backsund, Dun Li Chan +6
We present a traditional approach to symbolic piano music continuation for the MIREX 2025 Symbolic Music Generation challenge. While computational music generation has recently foc…