6 papers
Separating Prompt Harmfulness from Interaction Safety via Partial Generation
Ram Vikas Mishra, Shashank Aggarwal, Jahnavi Kumar +1
LLM-based information systems need safety guardrails. Most guardrails classify the prompt alone. If the prompt looks harmful, the system rejects it before any answer is generated.…
Improving the Performance of Compressed Transformers with Post-Hoc Embedding Alignment
Rohit Raj Rai, Abhishek Dhaka, Amit Awekar
Model compression is necessary for deployment of transformer models in resource-constrained environments. However, compression reduces the performance of transformer models on down…
Models in the Same Family are NOT Trust-Equivalent
Rohit Raj Rai, Chirag Kothari, Siddhesh Shelke +2
Within a model family, a smaller variant is often deployed as a drop-in replacement for a larger one when their performance is similar. However, performance alone does not tell the…
Application Specific Compression of Deep Learning Models
Rohit Raj Rai, Angana Borah, Amit Awekar
Large Deep Learning models are compressed and deployed for specific applications. However, current Deep Learning model compression methods do not utilize the information about the…
Compressed models are NOT miniature versions of large models
Rohit Raj Rai, Rishant Pal, Amit Awekar
Large neural models are often compressed before deployment. Model compression is necessary for many practical reasons, such as inference latency, memory footprint, and energy consu…
Effect of dimensionality change on the bias of word embeddings
Rohit Raj Rai, Amit Awekar
Word embedding methods (WEMs) are extensively used for representing text data. The dimensionality of these embeddings varies across various tasks and implementations. The effect of…