4 papers
When Bigger Becomes Brittle: Why Compression Hurts More as Language Models Scale
Gautam Gupta, Dikshant Kukreja, Unique Kumar +7
Quantization and pruning reduce the cost of deploying language models, but their effects are usually reported as benchmark scores. Such scores record only the loss that remains at…
The Intrusion Pathway: How Non-Evidential Context Degrades Language Model Performance
Dikshant Kukreja, Gautam Gupta, Avni Mittal +8
Language models lose accuracy when a prompt contains non-evidential context: irrelevant statements from unrelated domains, or random off-distribution tokens, with no competing answ…
Better and Worse with Scale: How Contextual Entrainment Diverges with Model Size
Dikshant Kukreja, Kshitij Sah, Gautam Gupta +5
Larger language models become simultaneously better and worse at handling contextual information -- better at ignoring false claims, worse at ignoring irrelevant tokens. We formali…
MAC: Multi-Agent Constitution Learning
Rushil Thareja, Gautam Gupta, Francesco Pinto +1
Constitutional AI is a method to oversee and control LLMs based on a set of rules written in natural language. These rules are typically written by human experts, but could in prin…